Algorithms and Psychiatry

Prior research has associated spoken language use with depression, yet studies often involve small or non-clinical samples and face challenges in the manual transcription of speech. This paper aimed to automatically identify depression-related topics in speech recordings collected from clinical samples.

Emotional dysregulation (ED) refers to the inability to manage emotional experiences or expressions hindering goal-oriented behavior. Moderate impairment on at least two domains among temper control, affective lability, and emotional over-reactivity has been proposed to identify ED in adults with attention-deficit/hyperactivity disorder (ADHD). No screening measure designed for use in diverse psychiatric samples exists. We aimed to develop a self-report screening tool for ED based on the 40-item version of the Reactivity, Intensity, Polarity, and Stability questionnaire (RIPoSt-40).

Gambling disorder affects 0.5-2% of the population, and of those who receive treatment, dropout tends to be relatively high. Very little is known about participant-specific variables linked to treatment discontinuation/dropout in gambling disorder, especially in pharmacological clinical trial settings.

Parkinson's disease (PD) is associated with the development of psychosis (PDP), including hallucinations and delusions, in more than half of the patient population. Optimal PD management must therefore involve considerations about both motor and non-motor symptoms. Often, clinicians fail to diagnosis psychosis in patients with PD and, when it is recognized, treat it suboptimally, despite the availability of multiple interventions. In this paper, we provide a summary of the current guidelines and clinical evidence for treating PDP with antipsychotics. We also provide recommendations for diagnosis and follow-up. Finally, an updated treatment algorithm for PDP that incorporates the use of pimavanserin, the only US FDA-approved drug for the treatment of PDP, was developed by extrapolating from a limited evidence base to bridge to clinical practice using expert opinion and experience. Because pimavanserin is only approved for the treatment of PDP in the US, in other parts of the world other recommendations and algorithms must be considered.

By combining theory-driven and data-driven methods, this study aimed to develop dementia predictive algorithms among Chinese older adults guided by the cognitive footprint theory.

Timely tests are warranted to assess the association between generative artificial intelligence (GenAI) use and physicians' work efforts.

Interventions and care that can evoke positive emotions and reduce apathy or agitation are important for people with dementia. In recent years, socially assistive robots used for better dementia care have been found to be feasible. However, the immediate responses of people with dementia when they are given multiple sensory modalities from socially assistive robots have not yet been sufficiently elucidated.

In this paper we present a method that allows leveraging 3D electron density information to train a deep neural network pipeline to segment regions of high, medium and low electronegativity and classify substances as health hazardous or non-hazardous. We show that this can be used for use-cases such as cosmetics and food products. For this purpose, we first generate 3D electron density cubes using semiempirical molecular calculations for a custom European Chemicals Agency (ECHA) subset consisting of substances labelled as hazardous and non-hazardous for cosmetic usage. Together with their 3-class electronegativity maps we train a modified 3D-UNet with electron density cubes to segment reactive sites in molecules and classify substances with an accuracy of 78.1%. We perform the same process on a custom food dataset (CompFood) consisting of hazardous and non-hazardous substances compiled from European Food Safety Authority (EFSA) OpenFoodTox, Food and Drug Administration (FDA) Generally Recognized as Safe (GRAS) and FooDB datasets to achieve a classification accuracy of 64.1%. Our results show that 3D electron densities and particularly masked electron densities, calculated by taking a product of original electron densities and regions of high and low electronegativity can be used to classify molecules for different use-cases and thus serve not only to guide safe-by-design product development but also aid in regulatory decisions. SCIENTIFIC CONTRIBUTION: We aim to contribute to the diverse 3D molecular representations used for training machine learning algorithms by showing that a deep learning network can be trained on 3D electron density representation of molecules. This approach has previously not been used to train machine learning models and it allows utilization of the true spatial domain of the molecule for prediction of properties such as their suitability for usage in cosmetics and food products and in future, to other molecular properties. The data and code used for training is accessible at https://github.com/s-singh-ivv/eDen-Substances .

To better assess the pathology of neurodegenerative disorders and the efficacy of neuroprotective interventions, it is necessary to develop biomarkers that can accurately capture age-related biological changes in the human brain. Brain serotonin 2A receptors (5-HT2AR) show a particularly profound age-related decline and are also reduced in neurodegenerative disorders, such as Alzheimer's disease. This study investigates whether the decline in 5-HT2AR binding, measured in vivo using positron emission tomography (PET), can be used as a biomarker for brain aging. Specifically, we aim to (1) predict brain age using 5-HT2AR binding outcomes, (2) compare 5-HT2AR-based predictions of brain age to predictions based on gray matter (GM) volume, as determined with structural magnetic resonance imaging (MRI), and (3) investigate whether combining 5-HT2AR and GM volume data improves prediction. We used PET and MR images from 209 healthy individuals aged between 18 and 85 years (mean = 38, std = 18) and estimated 5-HT2AR binding and GM volume for 14 cortical and subcortical regions. Different machine learning algorithms were applied to predict chronological age based on 5-HT2AR binding, GM volume, and the combined measures. The mean absolute error (MAE) and a cross-validation approach were used for evaluation and model comparison. We find that both the cerebral 5-HT2AR binding (mean MAE = 6.63 years, std = 0.74 years) and GM volume (mean MAE = 6.95 years, std = 0.83 years) predict chronological age accurately. Combining the two measures improves the prediction further (mean MAE = 5.54 years, std = 0.68). In conclusion, 5-HT2AR binding measured using PET might be useful for improving the quantification of a biomarker for brain aging.

Alterations in motor activity are well-established symptoms of bipolar disorder, and time series of motor activity can be considered complex dynamical systems. In such systems, early warning signals (EWS) occur in a critical transition period preceding a sudden shift (tipping point) in the system. EWS are statistical observations occurring due to a system's declining ability to maintain homeostasis when approaching a tipping point. The aim was to identify critical transition periods preceding bipolar mood state changes.

This study aimed to compare the breastfeeding (BF) duration of the younger siblings of children with ASD in an enriched-likelihood cohort for autism spectrum disorder (ASD), and to determine whether longer BF duration was associated with differences in neurodevelopmental outcomes in this cohort. Information on BF practices was collected via surveys in the MARBLES (Markers of Autism Risk in Babies-Learning Early Signs) study. Developmental evaluations, including the Mullen Scales of Early Learning and the Autism Diagnostic Observation Schedule, were conducted by expert clinicians. Participants' neurodevelopmental outcome was classified by an algorithm into three groups: typical development, ASD, and non-typical development. The median duration of BF was 10.70 months (interquartile range of 12.07 months). There were no significant differences in the distribution of duration of BF among the three neurodevelopmental outcome categories. Children in this enriched-likelihood cohort who were breastfed for > 12 months had significantly higher scores on cognitive testing compared to those who were breastfed for 0-3 months. There was no significant difference in ASD symptomatology or ASD risk based on BF duration.

: Inherited metabolic disorders (IEMs) can be represented in children and adolescents by psychiatric disorders. The early diagnosis of IEMs is crucial for clinical outcome and treatment. The aim of this review is to analyze the most recurrent and specific psychiatric features related to IEMs in pediatrics, based on the onset type and psychiatric phenotypes. Following the PRISMA Statement, a systematic literature review was performed using a predefined algorithm to find suitable publications in scientific databases of interest. After removing duplicates and screening titles and abstracts, suitable papers were analyzed and screened for inclusion and exclusion criteria. Finally, the data of interest were retrieved from the remaining articles. The results of this study are reported by type of symptoms onset (acute and chronic) and by possible psychiatric features related to IEMs. Psychiatric phenomenology has been grouped into five main clinical manifestations: mood and anxiety disorders; schizophrenia-spectrum disorders; catatonia; eating disorders; and self-injurious behaviors. The inclusion of a variety of psychiatric manifestations in children and adolescents with different IEMs is a key strength of this study, which allowed us to explore the facets of seemingly different disorders in depth, avoiding possible misdiagnoses, with the related delay of early and appropriate treatments.

Numerous physiological processes are cyclical, but sampling these processes densely enough to perform frequency decomposition and subsequent analyses can be challenging. Mathematical approaches for decomposition and reconstruction of sparsely and irregularly sampled signals are well established but have been under-utilized in physiological applications. We developed a basis pursuit denoising with polynomial detrending (BPWP) model that recovers oscillations and trends from sparse and irregularly sampled timeseries. We validated this model on a unique dataset of long-term inter-ictal epileptiform discharge (IED) rates from human hippocampus recorded with a novel investigational device with continuous local field potential sensing. IED rates have well established circadian and multiday cycles related to sleep, wakefulness, and seizure clusters. Given sparse and irregular samples of IED rates from multi-month intracranial EEG recordings from ambulatory humans, we used BPWP to compute narrowband spectral power and polynomial trend coefficients and identify IED rate cycles in three subjects. In select cases, we propose that random and irregular sampling may be leveraged for frequency decomposition of physiological signals. Trial Registration: NCT03946618.

Deconvolution is an efficient approach for detecting cell-type-specific (cs) transcriptomic signals without cellular segmentation. However, this type of methods may require a reference profile from the same molecular source and tissue type. Here, we present a method to dissect bulk proteome by leveraging tissue-matched transcriptome and proteome without using a proteomics reference panel. Our method also selects the proteins contributing to the cellular heterogeneity shared between bulk transcriptome and proteome. The deconvoluted result enables downstream analyses such as cs-protein Quantitative Trait Loci (cspQTL) mapping. We benchmarked the performance of this multimodal deconvolution approach through CITE-seq pseudo bulk data, a simulation study, and the bulk multi-omics data from human brain normal tissues and breast cancer tumors, individually, showing robust and accurate cell abundance quantification across different datasets. This algorithm is implemented in a tool MICSQTL that also provides cspQTL and multi-omics integrative visualization, available at https://bioconductor.org/packages/MICSQTL .

The response variability to repetitive transcranial magnetic stimulation (rTMS) challenges the effective use of this treatment option in patients with schizophrenia. This variability may be deciphered by leveraging predictive information in structural MRI, clinical, sociodemographic, and genetic data using artificial intelligence. We developed and cross-validated rTMS response prediction models in patients with schizophrenia drawn from the multisite RESIS trial. The models incorporated pre-treatment sMRI, clinical, sociodemographic, and polygenic risk score (PRS) data. Patients were randomly assigned to receive active (N = 45) or sham (N = 47) rTMS treatment. The prediction target was individual response, defined as ≥20% reduction in pre-treatment negative symptom sum scores of the Positive and Negative Syndrome Scale. Our multimodal sequential prediction workflow achieved a balanced accuracy (BAC) of 94% (non-responders: 92%, responders: 95%) in the active-treated group and 50% in the sham-treated group. The clinical, clinical + PRS, and sMRI-based classifiers yielded BACs of 65%, 76%, and 80%, respectively. Apparent sadness, inability to feel, educational attainment PRS, and unemployment were most predictive of non-response in the clinical + PRS model, while grey matter density reductions in the default mode, limbic networks, and the cerebellum were most predictive in the sMRI model. Our sequential modelling approach provided superior predictive performance while minimising the diagnostic burden in the clinical setting. Predictive patterns suggest that rTMS responders may have higher levels of brain grey matter in the default mode and salience networks which increases their likelihood of profiting from plasticity-inducing brain stimulation methods, such as rTMS. The future clinical implementation of our models requires findings to be replicated at the international scale using stratified clinical trial designs.

With advances in our understanding regarding the neurochemical underpinnings of neurological and psychiatric diseases, there is an increased demand for advanced computational methods for neurochemical analysis. Despite having a variety of techniques for measuring tonic extracellular concentrations of neurotransmitters, including voltammetry, enzyme-based sensors, amperometry, and in vivo microdialysis, there is currently no means to resolve concentrations of structurally similar neurotransmitters from mixtures in the in vivo environment with high spatiotemporal resolution and limited tissue damage. Since a variety of research and clinical investigations involve brain regions containing electrochemically similar monoamines, such as dopamine and norepinephrine, developing a model to resolve the respective contributions of these neurotransmitters is of vital importance. Here we have developed a deep learning network, DiscrimNet, a convolutional autoencoder capable of accurately predicting individual tonic concentrations of dopamine, norepinephrine, and serotonin from both in vitro mixtures and the in vivo environment in anesthetized rats, measured using voltammetry. The architecture of DiscrimNet is described, and its ability to accurately predict in vitro and unseen in vivo concentrations is shown to vastly outperform a variety of shallow learning algorithms previously used for neurotransmitter discrimination. DiscrimNet is shown to generalize well to data captured from electrodes unseen during model training, eliminating the need to retrain the model for each new electrode. DiscrimNet is also shown to accurately predict the expected changes in dopamine and serotonin after cocaine and oxycodone administration in anesthetized rats in vivo. DiscrimNet therefore offers an exciting new method for real-time resolution of in vivo voltammetric signals into component neurotransmitters.

Depression is prevalent among Operation Enduring Freedom and Operation Iraqi Freedom (OEF/OIF) Veterans, yet rates of Veteran mental health care utilization remain modest. The current study examined: factors in electronic health records (EHR) associated with lack of treatment initiation and treatment delay; the accuracy of regression and machine learning models to predict initiation of treatment.

Bipolar disorder (BD) is a leading cause of disability worldwide, as it can lead to cognitive and functional impairment and premature mortality. The first episode of BD is usually a depressive episode and is often misdiagnosed as major depressive disorder (MDD). Growing evidence indicates that peripheral immune activation and inflammation are involved in the pathophysiology of BD and MDD. Recently, by developing a panel of RNA editing-based blood biomarkers able to discriminate MDD from depressive BD, we have provided clinicians a new tool to reduce the misdiagnosis delay observed in patients suffering from BD. The present study aimed at validating the diagnostic value of this panel in an external independent multicentric Switzerland-based cohort of 143 patients suffering from moderate to major depression. The RNA-editing based blood biomarker (BMK) algorithm developped allowed to accurately discriminate MDD from depressive BD in an external cohort, with high accuracy, sensitivity and specificity values (82.5 %, 86.4 % and 80.8 %, respectively). These findings further confirm the important role of RNA editing in the physiopathology of mental disorders and emphasize the possible clinical usefulness of the biomarker panel for optimization treatment delay in patients suffering from BD.

Sharing data from clinical studies can accelerate scientific progress, improve transparency, and increase the potential for innovation and collaboration. However, privacy concerns remain a barrier to data sharing. Certain concerns, such as reidentification risk, can be addressed through the application of anonymization algorithms, whereby data are altered so that it is no longer reasonably related to a person. Yet, such alterations have the potential to influence the data set's statistical properties, such that the privacy-utility trade-off must be considered. This has been studied in theory, but evidence based on real-world individual-level clinical data is rare, and anonymization has not broadly been adopted in clinical practice.

Post-hoc analysis to evaluate the effect of daridorexant on sleep architecture in people with insomnia, focusing on features associated with hyperarousal.

Decision-making in healthcare is increasingly complex; notably in hospital environments where the information density is high, e.g., emergency departments, oncology departments, and psychiatry departments. This study aims to discover decisions from logged data to improve the decision-making process.

The objective of this study is to determine demographic and diagnostic distributions of physical pain recorded in clinical notes of a mental health electronic health records database by using natural language processing and examine the overlap in recorded physical pain between primary and secondary care.

Individual testing of samples is time- and cost-intensive, particularly during an ongoing pandemic. Better practical alternatives to individual testing can significantly decrease the burden of disease on the healthcare system. Herein, we presented the clinical validation of Segtnan™ on 3929 patients. Segtnan™ is available as a mobile application entailing an AI-integrated personalized risk assessment approach with a novel data-driven equation for pooling of biological samples. The AI was selected from a comparison between 15 machine learning classifiers (highest accuracy = 80.14%) and a feed-forward neural network with an accuracy of 81.38% in predicting the rRT-PCR test results based on a designed survey with minimal clinical questions. Furthermore, we derived a novel pool-size equation from the pooling data of 54 published original studies. The results demonstrated testing capacity increase of 750%, 60%, and 5% at prevalence rates of 0.05%, 22%, and 50%, respectively. Compared to Dorfman's method, our novel equation saved more tests significantly at high prevalence, i.e., 28% (p = 0.006), 40% (p = 0.00001), and 66% (p = 0.02). Lastly, we illustrated the feasibility of the Segtnan™ usage in clinically complex settings like emergency and psychiatric departments.

Healthcare professionals are known to suffer from workplace stress and burnout, which can negatively affect their empathy for patients and quality of care. While existing research has identified factors associated with wellbeing and empathy in healthcare professionals, these efforts are typically focused on the group level, ignoring potentially important individual differences and implications for individualized intervention approaches. In the current study, we implemented N-of-1 personalized machine learning (PML) to predict wellbeing and empathy in healthcare professionals at the individual level, leveraging ecological momentary assessments (EMAs) and smartwatch wearable data. A total of 47 mood and lifestyle feature variables (relating to sleep, diet, exercise, and social connections) were collected daily for up to three months followed by applying eight supervised machine learning (ML) models in a PML pipeline to predict wellbeing and empathy separately. Predictive insight into the model architecture was obtained using Shapley statistics for each of the best-fit personalized models, ranking the importance of each feature for each participant. The best-fit model and top features varied across participants, with anxious mood (13/19) and depressed mood (10/19) being the top predictors in most models. Social connection was a top predictor for wellbeing in 9/12 participants but not for empathy models (1/7). Additionally, empathy and wellbeing were the top predictors of each other in 64% of cases. These findings highlight shared and individual features of wellbeing and empathy in healthcare professionals and suggest that a one-size-fits-all approach to addressing modifiable factors to improve wellbeing and empathy will likely be suboptimal. In the future, such personalized models may serve as actionable insights for healthcare professionals that lead to increased wellness and quality of patient care.

Transgender and gender diverse (TGD) individuals have greater access to genital surgery (GS) with improved insurance coverage and access to trained surgeons and interdisciplinary gender affirming providers.

Attention-deficit/hyperactivity disorder (ADHD) is associated with various cognitive, behavioral, and mood symptoms that complicate diagnosis and treatment. The heterogeneity of these symptoms may also vary depending on certain sociodemographic factors. It is therefore important to establish more homogenous symptom profiles in patients with ADHD and determine their association with the patient's sociodemographic makeup. The current study used unsupervised machine learning to identify symptom profiles across various cognitive, behavioral, and mood symptoms in adults with ADHD. It was then examined whether symptom profiles differed based on relevant sociodemographic factors.

Primary care physicians often lack resources and training to correctly diagnose and manage chronic insomnia disorder. Tools supporting chronic insomnia diagnosis and management could fill this critical gap. A survey was conducted to understand insomnia disorder diagnosis and treatment practices among primary care physicians, and to evaluate a diagnosis and treatment algorithm on its use, to identify ways to optimize it specifically for these providers.

Memory clinic patients are a heterogeneous population representing various aetiologies of pathological aging. It is unknown if divergent spatiotemporal progression patterns of brain atrophy, as previously described in Alzheimer's disease (AD) patients, are prevalent and clinically meaningful in this group of older adults. To uncover distinct atrophy subtypes, we applied the Subtype and Stage Inference (SuStaIn) algorithm to baseline structural MRI data from 813 participants enrolled in the DELCODE cohort (mean ± SD age = 70.67 ± 6.07 years, 52% females). Participants were cognitively unimpaired (CU; n = 285) or fulfilled diagnostic criteria for subjective cognitive decline (SCD; n = 342), mild cognitive impairment (MCI; n = 118), or dementia of the Alzheimer's type (n = 68). Atrophy subtypes were compared in baseline demographics, fluid AD biomarker levels, the Preclinical Alzheimer Cognitive Composite (PACC-5), as well as episodic memory and executive functioning. PACC-5 trajectories over up to 240 weeks were examined. To test if baseline atrophy subtype and stage predicted clinical trajectories before manifest cognitive impairment, we analysed PACC-5 trajectories and MCI conversion rates of CU and SCD participants. Limbic-predominant and hippocampal-sparing atrophy subtypes were identified. Limbic-predominant atrophy first affected the medial temporal lobes, followed by further temporal and, finally, the remaining cortical regions. At baseline, this subtype was related to older age, more pathological AD biomarker levels, APOE ε4 carriership, and an amnestic cognitive impairment. Hippocampal-sparing atrophy initially occurred outside the temporal lobe with the medial temporal lobe spared up to advanced atrophy stages. This atrophy pattern also affected individuals with positive AD biomarkers and was associated with more generalised cognitive impairment. Limbic-predominant atrophy, in all and in only unimpaired participants, was linked to more negative longitudinal PACC-5 slopes than observed in participants without or with hippocampal-sparing atrophy and increased the risk of MCI conversion. SuStaIn modelling was repeated in a sample from the Swedish BioFINDER-2 cohort. Highly similar atrophy progression patterns and associated cognitive profiles were identified. Cross-cohort model generalizability, both on the subject and group level, were excellent, indicating reliable performance in previously unseen data. The proposed model is a promising tool for capturing heterogeneity among older adults at early at-risk states for AD in applied settings. The implementation of atrophy subtype- and stage-specific end-points may increase the statistical power of pharmacological trials targeting early AD.

We developed a video-based tool to quantitatively assess the Glabellar Tap Reflex (GTR) in patients with idiopathic Parkinson's disease (iPD) as well as healthy age-matched participants. We also video-graphically assessed the effect of dopaminergic medication on the GTR in iPD patients, as well as the frequency and blinking duration of reflex and non-reflex blinks. The Glabellar Tap Reflex is a clinical sign seen in patients e.g. suffering from iPD. Reliable tools to quantify this sign are lacking.

To assess the predictive value of four cardiovascular (CV) risk algorithms for identifying high-risk psoriatic arthritis (PsA) patients.

While there is data assessing the test performance of artificial intelligence (AI) chatbots, including the Generative Pre-trained Transformer 4.0 (GPT 4) chatbot (ChatGPT 4.0), there is scarce data on its diagnostic accuracy of clinical cases. We assessed the large language model (LLM), ChatGPT 4.0, on its ability to answer questions from the United States Medical Licensing Exam (USMLE) Step 2, as well as its ability to generate a differential diagnosis based on corresponding clinical vignettes from published case reports. A total of 109 Step 2 Clinical Knowledge (CK) practice questions were inputted into both ChatGPT 3.5 and ChatGPT 4.0, asking ChatGPT to pick the correct answer. Compared to its previous version, ChatGPT 3.5, we found improved accuracy of ChatGPT 4.0 when answering these questions, from 47.7 to 87.2% (p = 0.035) respectively. Utilizing the topics tested on Step 2 CK questions, we additionally found 63 corresponding published case report vignettes and asked ChatGPT 4.0 to come up with its top three differential diagnosis. ChatGPT 4.0 accurately created a shortlist of differential diagnoses in 74.6% of the 63 case reports (74.6%). We analyzed ChatGPT 4.0's confidence in its diagnosis by asking it to rank its top three differentials from most to least likely. Out of the 47 correct diagnoses, 33 were the first (70.2%) on the differential diagnosis list, 11 were second (23.4%), and three were third (6.4%). Our study shows the continued iterative improvement in ChatGPT's ability to answer standardized USMLE questions accurately and provides insights into ChatGPT's clinical diagnostic accuracy.

The severity of antipsychotic-induced cervical dystonia has traditionally been evaluated visually. However, recent advances in information technology made quantification possible in this field through the introduction of engineering methodologies like machine learning. This study was conducted from June 2021 to March 2023. Psychiatrists rated the severity of cervical dystonia into 4 levels (0: none, 1: minimal, 2: mild, and 3: moderate) for 101 videoclips, recorded from 87 psychiatric patients receiving antipsychotics. The Face Mesh function of the open-source framework MediaPipe was employed to calculate the tilt angles of anterocollis or retrocollis, laterocollis, and torticollis. These were calculated to examine the range of tilt angles for the 4 levels of severity of the different types of cervical dystonia. The tilt angles calculated using Face Mesh for each level of dystonia were 0° ≤ θ < 6° for none, 6° ≤ θ < 11° for minimal, 11° ≤ θ < 25° for mild, and 25° ≤ θ for moderate laterocollis; 0° ≤ θ < 11° for none, 11° ≤ θ < 18° for minimal, 18° ≤ θ <25° for mild, and 25° ≤ θ for moderate anterocollis or retrocollis; and 0° ≤ θ < 9° for none, 9° ≤ θ < 17° for minimal, 17° ≤ θ < 32° for mild, and 32° ≤ θ for moderate torticollis. While further validation with new cases is needed, the range of tilt angles in this study could provide a standard for future artificial intelligence devices for cervical dystonia.

The neurodevelopmental outcomes of preterm infants can be stratified based on the level of prematurity. We explored brain structural networks in extremely preterm (EP; < 28 weeks of gestation) and very-to-late (V-LP; ≥ 28 and < 37 weeks of gestation) preterm infants at term-equivalent age to predict 2-year neurodevelopmental outcomes. Using MRI and diffusion MRI on 62 EP and 131 V-LP infants, we built a multimodal feature set for volumetric and structural network analysis. We employed linear and nonlinear machine learning models to predict the Bayley Scales of Infant and Toddler Development, Third Edition (BSID-III) scores, assessing predictive accuracy and feature importance. Our findings revealed that models incorporating local connectivity features demonstrated high predictive performance for BSID-III subsets in preterm infants. Specifically, for cognitive scores in preterm (variance explained, 17%) and V-LP infants (variance explained, 17%), and for motor scores in EP infants (variance explained, 15%), models with local connectivity features outperformed others. Additionally, a model using only local connectivity features effectively predicted language scores in preterm infants (variance explained, 15%). This study underscores the value of multimodal feature sets, particularly local connectivity, in predicting neurodevelopmental outcomes, highlighting the utility of machine learning in understanding microstructural changes and their implications for early intervention.

Professionals are reluctant to make use of machine learning results for tasks like curriculum development if they do not understand how the results were generated and what they mean. Visualizations of peer reviewed medical literature can summarize enormous amounts of information but are difficult to interpret. This article reports the validation of the meaning of a self-organizing map derived from the Medline/PubMed index of peer reviewed medical literature by its capacity to coherently summarize the references of a core psychiatric textbook.

AI tools intend to transform mental healthcare by providing remote estimates of depression risk using behavioral data collected by sensors embedded in smartphones. While these tools accurately predict elevated depression symptoms in small, homogenous populations, recent studies show that these tools are less accurate in larger, more diverse populations. In this work, we show that accuracy is reduced because sensed-behaviors are unreliable predictors of depression across individuals: sensed-behaviors that predict depression risk are inconsistent across demographic and socioeconomic subgroups. We first identified subgroups where a developed AI tool underperformed by measuring algorithmic bias, where subgroups with depression were incorrectly predicted to be at lower risk than healthier subgroups. We then found inconsistencies between sensed-behaviors predictive of depression across these subgroups. Our findings suggest that researchers developing AI tools predicting mental health from sensed-behaviors should think critically about the generalizability of these tools, and consider tailored solutions for targeted populations.

Type 2 diabetes mellitus (T2DM) is one of the leading causes of cardiovascular disease and powerful predictor for new-onset heart failure (HF).

Recently, we developed Research and Diagnostic Algorithm Rules (RADAR) to assess the clinical and pathway features of mood disorders. The aims of this paper are to review a) the methodology for developing continuous RADAR scores that describe the clinical and pathway features of schizophrenia, and b) a new method to visualize the clinical status of patients and the pathways implicated in RADAR graphs. We review how to interpret clinical RADAR scores, which serve as valuable tools for monitoring the staging of illness, lifetime suicidal behaviors, overall severity of illness, a general cognitive decline index, and a behavior-cognitive-psychosocial (BCPS) index that represents the "defect"; and b) pathway RADAR scores which reflect various protective (including the compensatory immune- inflammatory system) and adverse (including neuro-immune, neuro-oxidative, and neurotoxic biomarkers) outcome pathways. Using RADAR scores and machine learning, we created new, qualitatively different types of schizophrenia, such as major neurocognitive psychosis and simple psychosis. We also made RADAR graphs, which give us a quick way to compare the patient's clinical condition and pathways to those of healthy controls. We generated a personalized fingerprint for each patient, encompassing various clinical and pathway features of the disorder represented through RADAR graphs. The latter is utilized in clinical practice to assess the clinical condition of patients and identify treatment-required pathways to mitigate the risk of recurrent episodes, worsening BCPS, and increasing staging. The quantitative clinical RADAR scores should be used in schizophrenia research as dependent variables and regressed on the pathway RADAR scores.

Relative cell type fraction estimates in bulk RNA-sequencing data are important to control for cell composition differences across heterogenous tissue samples. Current computational tools estimate relative RNA abundances rather than cell type proportions in tissues with varying cell sizes, leading to biased estimates. We present , a computational tool to accurately deconvolute cell types with varying sizes. Our software wraps existing deconvolution algorithms in a standardized framework. Using simulated and real datasets, we demonstrate how adjusts for differences in cell sizes to improve the accuracy of cell composition. Software is available from https://bioconductor.org/packages/lute.

Electroencephalogram (EEG) recorded as response to transcranial magnetic stimulation (TMS) can be highly informative of cortical reactivity and connectivity. Reliable EEG interpretation requires artifact removal as the TMS-evoked EEG can contain high-amplitude artifacts. Several methods have been proposed to uncover clean neuronal EEG responses. In practice, determining which method to select for different types of artifacts is often difficult. Here, we used a unified data cleaning framework based on beamforming to improve the algorithm selection and adaptation to the recorded signals. Beamforming properties are well understood, so they can be used to yield customized methods for EEG cleaning based on prior knowledge of the artifacts and the data. The beamforming implementations also cover, but are not limited to, the popular TMS-EEG cleaning methods: independent component analysis (ICA), signal-space projection (SSP), signal-space-projection-source-informed-reconstruction method (SSP-SIR), the source-estimate-utilizing noise-discarding algorithm (SOUND), data-driven Wiener filter (DDWiener), and the multiple-source approach. In addition to these established methods, beamforming provides a flexible way to derive novel artifact suppression algorithms by considering the properties of the recorded data. With simulated and measured TMS-EEG data, we show how to adapt the beamforming-based cleaning to different data and artifact types, namely TMS-evoked muscle artifacts, ocular artifacts, TMS-related peripheral responses, and channel noise. Importantly, beamforming implementations are fast to execute: We demonstrate how the SOUND algorithm becomes orders of magnitudes faster via beamforming. Overall, the beamforming-based spatial filtering framework can greatly enhance the selection, adaptability, and speed of EEG artifact removal.

Dementia has a long prodromal stage with various pathophysiological manifestations; however, the progression of pre-diagnostic changes remains unclear. We aimed to determine the evolutional trajectories of multiple-domain clinical assessments and health conditions up to 15 years before the diagnosis of dementia.

Several studies show great heterogeneity in the type of genetic test requested and in the clinicopathological characteristics of patients with ASD. The following study aims, firstly, to explore the factors that might influence professionals' decisions about the appropriateness of requesting genetic testing for their patients with ASD and, secondly, to determine the prevalence of genetic alterations in a representative sample of children with a diagnosis of ASD. Methods: We studied the clinical factors associated with the request for genetic testing in a sample of 440 children with ASD and the clinical factors of present genetic alterations. Even though the main guidelines recommend genetic testing all children with an ASD diagnosis, only 56% of children with an ASD diagnosis were genetically tested. The prevalence of genetic alterations was 17.5%. These alterations were more often associated with intellectual disability and dysmorphic features. There are no objective data to explicitly justify the request for genetic testing, nor are there objective data to justify requesting one genetic study versus multiple studies. Remarkably, only 28% of males were genetically tested with the recommended tests (fragile X and CMA). Children with dysmorphic features and organic comorbidities were more likely to be genetic tested than those without. Previous diagnosis of ASD (family history of ASD) and attendance at specialist services were also associated with Genetically tested Autism Spectrum Disorder GTASD. Our findings emphasize the importance of establishing algorithms to facilitate targeted genetic consultation for individuals with ASD who are likely to benefit, considering clinical phenotypes, efficiency, ethics, and benefits.

Self-management of opioid use disorder (OUD) is an important component of treatment. Many patients receiving opioid agonist treatment in methadone maintenance treatment settings benefit from counseling treatments to help them improve their recovery skills but have insufficient access to these treatments between clinic appointments. In addition, many addiction medicine clinicians treating patients with OUD in a general medical clinic setting do not have consistent access to counseling referrals for their patients. This can lead to decreases in both treatment retention and overall progress in the patient's recovery from substance misuse. Digital apps may help to bridge this gap by coaching, supporting, and reinforcing behavioral change that is initiated and directed by their psychosocial and medical providers.

Undergraduate medical studies represent a wide range of learning opportunities served in the form of various teaching-learning modalities for medical learners. A clinical scenario is frequently used as a modality, followed by multiple-choice and open-ended questions among other learning and teaching methods. As such, script concordance tests (SCTs) can be used to promote a higher level of clinical reasoning. Recent technological developments have made generative artificial intelligence (AI)-based systems such as ChatGPT (OpenAI) available to assist clinician-educators in creating instructional materials.

Altered nonverbal communication patterns especially with regard to gaze interactions are commonly reported for persons with autism spectrum disorder (ASD). In this study we investigate and differentiate for the first time the interplay of attention allocation, the establishment of shared focus (eye contact and joint attention) and the recognition of intentions in gaze interactions in adults with ASD compared to control persons. Participants interacted via gaze with a virtual character (VC), who they believed was controlled by another person. Participants were instructed to ascertain whether their partner was trying to interact with them. In fact, the VC was fully algorithm-controlled and showed either interactive or non-interactive gaze behavior. Participants with ASD were specifically impaired in ascertaining whether their partner was trying to interact with them or not as compared to participants without ASD whereas neither the allocation of attention nor the ability to establish a shared focus were affected. Thus, perception and production of gaze cues seem preserved while the evaluation of gaze cues appeared to be impaired. An additional exploratory analysis suggests that especially the interpretation of contingencies between the interactants' actions are altered in ASD and should be investigated more closely.

Methods that measure the association between two intensively measured time series are of interest to researchers studying the symmetry of behaviors during social interaction. Such methods have historically focused on aggregating the amount of symmetry across all measurement occasions. However, it is rarely expected that symmetry is present at all measurement occasions. The current method, the pairwise approximate spatiotemporal symmetry (PASS) algorithm, is an approach that may be used to determine which measurement occasions in pairwise time series are indicative of symmetry and which are not. This process thus divides time series into symmetric and nonsymmetric segments. The PASS algorithm is demonstrated here on representative simulated data and naturalistic psychotherapy data. Results suggest that the PASS algorithm has the potential to extract meaningful symmetry segments from human signals. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Alcohol consumption may impact and shape brain development through perturbed biological pathways and impaired molecular functions. We investigated the relationship between alcohol consumption rates and neuron-enriched extracellular vesicles' (EVs') microRNA (miRNA) expression to better understand the impact of alcohol use on early life brain biology. Neuron-enriched EVs' miRNA expression was measured from plasma samples collected from young people using a commercially available microarray platform while alcohol consumption was measured using the Alcohol Use Disorders Identification Test. Linear regression and network analyses were used to identify significantly differentially expressed miRNAs and to characterize the implicated biological pathways, respectively. Compared to alcohol naïve controls, young people reporting high alcohol consumption exhibited significantly higher expression of three neuron-enriched EVs' miRNAs including miR-30a-5p, miR-194-5p, and miR-339-3p, although only miR-30a-5p and miR-194-5p survived multiple test correction. The miRNA-miRNA interaction network inferred by a network inference algorithm did not detect any differentially expressed miRNAs with a high cutoff on edge scores. However, when the cutoff of the algorithm was reduced, five miRNAs were identified as interacting with miR-194-5p and miR-30a-5p. These seven miRNAs were associated with 25 biological functions; miR-194-5p was the most highly connected node and was highly correlated with the other miRNAs in this cluster. Our observed association between neuron-enriched EVs' miRNAs and alcohol consumption concurs with results from experimental animal models of alcohol use and suggests that high rates of alcohol consumption during the adolescent/young adult years may impact brain functioning and development by modulating miRNA expression.

One of the challenges of psychiatry is the staging of patients, especially those with severe mental disorders. Therefore, we aim to develop an empirical staging model for schizophrenia.

Multiscale neuroscience conceptualizes mental illness as arising from aberrant interactions across and within multiple biopsychosocial scales. We leverage this framework to propose a multiscale disease progression model of psychosis, in which hippocampal-cortical dysconnectivity precedes impairments in episodic memory and social cognition, which lead to more severe negative symptoms and lower functional outcome. As psychosis represents a heterogeneous collection of biological and behavioral alterations that evolve over time, we further predict this disease progression for a subtype of the patient sample, with other patients showing normal-range performance on all variables. We sampled data from two cross-sectional datasets of first- and multi-episode psychosis, resulting in a sample of 163 patients and 119 non-clinical controls. To address our proposed disease progression model and evaluate potential heterogeneity, we applied a machine-learning algorithm, SuStaIn, to the patient data. SuStaIn uniquely integrates clustering and disease progression modeling and identified three patient subtypes. Subtype 0 showed normal-range performance on all variables. In comparison, Subtype 1 showed lower episodic memory, social cognition, functional outcome, and higher negative symptoms, while Subtype 2 showed lower hippocampal-cortical connectivity and episodic memory. Subtype 1 deteriorated from episodic memory to social cognition, negative symptoms, functional outcome to bilateral hippocampal-cortical dysconnectivity, while Subtype 2 deteriorated from bilateral hippocampal-cortical dysconnectivity to episodic memory and social cognition, functional outcome to negative symptoms. This first application of SuStaIn in a multiscale psychiatric model provides distinct disease trajectories of hippocampal-cortical connectivity, which might underlie the heterogeneous behavioral manifestations of psychosis.

Novel features derived from imaging and artificial intelligence systems are commonly coupled to construct computer-aided diagnosis (CAD) systems that are intended as clinical support tools or for investigation of complex biological patterns. This study used sulcal patterns from structural images of the brain as the basis for classifying patients with schizophrenia from unaffected controls. Statistical, machine learning and deep learning techniques were sequentially applied as a demonstration of how a CAD system might be comprehensively evaluated in the absence of prior empirical work or extant literature to guide development, and the availability of only small sample datasets. Sulcal features of the entire cerebral cortex were derived from 58 schizophrenia patients and 56 healthy controls. No similar CAD systems has been reported that uses sulcal features from the entire cortex. We considered all the stages in a CAD system workflow: preprocessing, feature selection and extraction, and classification. The explainable AI techniques Local Interpretable Model-agnostic Explanations and SHapley Additive exPlanations were applied to detect the relevance of features to classification. At each stage, alternatives were compared in terms of their performance in the context of a small sample. Differentiating sulcal patterns were located in temporal and precentral areas, as well as the collateral fissure. We also verified the benefits of applying dimensionality reduction techniques and validation methods, such as resubstitution with upper bound correction, to optimize performance.

Diagnostic accuracy of autism spectrum disorder (ASD) is crucial to track and characterize ASD, as well as to guide appropriate interventions at the individual level. However, under-diagnosis, over-diagnosis, and misdiagnosis of ASD are still prevalent.

Obstructive sleep apnea (OSA) is a common condition that is increasing in prevalence worldwide. Untreated OSA has a negative impact on health-related quality of life and is an independent risk factor for cardiovascular diseases. Despite available data suggesting that cardiovascular risk might differ according to clinical phenotypes and comorbidities, current approaches to OSA treatment usually take a "one size fits all" approach. Identification of cardiovascular vulnerability biomarkers and clinical phenotypes associated with response to positive airway pressure (PAP) therapy could help to redefine the standard treatment paradigm. The new PAP-RES (PAP-RESponsive) algorithm is based on the identification of OSA phenotypes that are likely to impact therapeutic goals and modalities. The paradigm shift is to propose a simplified approach that defines therapeutic goals based on OSA phenotype: from a predominantly "symptomatic phenotype" (individuals with high symptom burden that negatively impacts on daily life and/or accident risk or clinically significant insomnia) to a "vulnerable cardiovascular phenotype" (individuals with comorbidities [serious cardiovascular or respiratory disease or obesity] that have a negative impact on cardiovascular prognosis or a biomarker of hypoxic burden and/or autonomic nervous system dysfunction). Each phenotype requires a different PAP therapy care pathway based on differing health issues and treatment objectives.

Approximately half of generalised anxiety disorder (GAD) patients do not recover from first-line treatments, and no validated prediction models exist to inform individuals or clinicians of potential treatment benefits. This study aimed to develop and validate an accurate and explainable prediction model of post-treatment GAD symptom severity. Data from adults receiving treatment for GAD in eight Improving Access to Psychological Therapies (IAPT) services (n=15,859) were separated into training, validation and holdout datasets. Thirteen machine learning algorithms were compared using 10-fold cross-validation, against two simple clinically relevant comparison models. The best-performing model was tested on the holdout dataset and model-specific explainability measures identified the most important predictors. A Bayesian Additive Regression Trees model out-performed all comparison models (MSE=16.54 [95 % CI=15.58; 17.51]; MAE=3.19; R²=0.33, including a single predictor linear regression model: MSE=20.70 [95 % CI=19.58; 21.82]; MAE=3.94; R²=0.14). The five most important predictors were: PHQ-9 anhedonia, GAD-7 annoyance/irritability, restlessness and fear items, then the referral-assessment waiting time. The best-performing model accurately predicted post-treatment GAD symptom severity using only pre-treatment data, outperforming comparison models that approximated clinical judgement and remaining within the GAD-7 error of measurement and minimal clinically important differences. This model could inform treatment decision-making and provide desired information to clinicians and patients receiving treatment for GAD.

Auditory system plasticity is a promising target for neuromodulation, cognitive rehabilitation and therapeutic development in schizophrenia (SZ). Auditory-based targeted cognitive training (TCT) is a 'bottom up' intervention designed to enhance the speed and accuracy of auditory information processing, which has been shown to improve neurocognition in certain SZ patients. However, the dynamics of TCT learning as a function of training exercises and their impact on neurocognitive functioning and therapeutic outcomes are unknown.

Major Depressive Disorder (MDD) is a widespread psychiatric condition that affects a significant portion of the global population. The classification and diagnosis of MDD is crucial for effective treatment. Traditional methods, based on clinical assessment, are subjective and rely on healthcare professionals' expertise. Recently, there's growing interest in using Resting-State Functional Magnetic Resonance Imaging (rs-fMRI) to objectively understand MDD's neurobiology, complementing traditional diagnostics. The posterior cingulate cortex (PCC) is a pivotal brain region implicated in MDD which could be used to identify MDD from healthy controls. Thus, this study presents an intelligent approach based on rs-fMRI data to enhance the classification of MDD. Original rs-fMRI data were collected from a cohort of 430 participants, comprising 197 patients and 233 healthy controls. Subsequently, the data underwent preprocessing using DPARSF, and the amplitudes of low-frequency fluctuation values were computed to reduce data dimensionality and feature count. Then data associated with the PCC were extracted. After eliminating redundant features, various types of Support Vector Machines (SVMs) were employed as classifiers for intelligent categorization. Ultimately, we compared the performance of each algorithm, along with its respective optimal classifier, based on classification accuracy, true positive rate, and the area under the receiver operating characteristic curve (AUC-ROC). Upon analyzing the comparison results, we determined that the Random Forest (RF) algorithm, in conjunction with a sophisticated Gaussian SVM classifier, demonstrated the highest performance. Remarkably, this combination achieved a classification accuracy of 81.9 % and a true positive rate of 92.9 %. In conclusion, our study improves the classification of MDD by supplementing traditional methods with rs-fMRI and machine learning techniques, offering deeper neurobiological insights and aiding accuracy, while emphasizing its role as an adjunct to clinical assessment.

Although effective treatments for common mental health problems are available, individual responses to treatments are difficult to predict. Treatment efficacy could be optimized by targeting interventions using individual predictions of treatment outcomes. The aim of this study was to develop a prediction algorithm using data from one of the largest randomized controlled trials on psychological interventions for common mental health problems.

The co-occurrence and familial clustering of neurodevelopmental disorders and immune disorders suggest shared genetic risk factors. Based on genome-wide association summary statistics from five neurodevelopmental disorders and four immune disorders, we conducted genome-wide, local genetic correlation and polygenic overlap analysis. We further performed a cross-trait GWAS meta-analysis. Pleotropic loci shared between the two categories of diseases were mapped to candidate genes using multiple algorithms and approaches. Significant genetic correlations were observed between neurodevelopmental disorders and immune disorders, including both positive and negative correlations. Neurodevelopmental disorders exhibited higher polygenicity compared to immune disorders. Around 50%-90% of genetic variants of the immune disorders were shared with neurodevelopmental disorders. The cross-trait meta-analysis revealed 154 genome-wide significant loci, including 8 novel pleiotropic loci. Significant associations were observed for 30 loci with both types of diseases. Pathway analysis on the candidate genes at these loci revealed common pathways shared by the two types of diseases, including neural signaling, inflammatory. Response, and PI3K-Akt signaling pathway. In addition, 26 of the 30 lead SNPs were associated with blood cell traits. Neurodevelopmental disorders exhibit complex polygenic architecture, with a subset of individuals being at a heightened genetic risk for both neurodevelopmental and immune disorders. The identification of pleiotropic loci has important implications for exploring opportunities for drug repurposing, enabling more accurate patient stratification, and advancing genomics-informed precision in the medical field of neurodevelopmental disorders.

A significant level of stigma and inequality exists in mental healthcare, especially in under-served populations. Inequalities are reflected in the data collected for scientific purposes. When not properly accounted for, machine learning (ML) models learned from data can reinforce these structural inequalities or biases. Here, we present a systematic study of bias in ML models designed to predict depression in four different case studies covering different countries and populations. We find that standard ML approaches regularly present biased behaviors. We also show that mitigation techniques, both standard and our own post-hoc method, can be effective in reducing the level of unfair bias. There is no one best ML model for depression prediction that provides equality of outcomes. This emphasizes the importance of analyzing fairness during model selection and transparent reporting about the impact of debiasing interventions. Finally, we also identify positive habits and open challenges that practitioners could follow to enhance fairness in their models.

This perspective encompasses a focused review of the literature leading to a tipping point in electroanalytical chemistry. We tie together the threads of a "revolution" quietly in the making for years through the work of many authors. Long-held misconceptions about the use of background subtraction in fast voltammetry are addressed. We lay out future advantages that accompany background-inclusive voltammetry, particularly when paired with modern machine-learning algorithms for data analysis.

Mental health is a complex, multidimensional concept that goes beyond clinical diagnoses, including psychological distress, life stress and well-being. This study aims to use unsupervised clustering approaches to identify multidimensional mental health profiles that exist in the population, and their associated service use patterns. The data source for this study is the 2012 Canadian Community Health Survey- Mental Health linked to administrative healthcare data holdings, included were all Ontario adult respondents. We used a Partioning Around Medoids clustering algorithm with Gower's proximity to identify groups with distinct combinations of mental health indicators and described them by their sociodemographic and service use characteristics. We identified four groups with distinct mental health profiles, including one group who met the clinical threshold for a depressive diagnosis, with the remaining three groups expressing differences in positive mental health, life stress and self-rated mental health. The four groups had different age, employment and income profiles and exhibited differential access to mental healthcare services. This study represents the first step in identifying complex profiles of mental health at the population level in Ontario, Canada. Further research is required to better understand the potential causes and consequences of belonging to each of the mental health profiles identified.

Previous studies have developed and explored magnetic resonance imaging (MRI)-based machine learning models for predicting Alzheimer's disease (AD). However, limited research has focused on models incorporating diverse patient populations. This study aimed to build a clinically useful prediction model for amyloid-beta (Aβ) deposition using source-based morphometry, using a data-driven algorithm based on independent component analyses. Additionally, we assessed how the predictive accuracies varied with the feature combinations. Data from 118 participants clinically diagnosed with various conditions such as AD, mild cognitive impairment, frontotemporal lobar degeneration, corticobasal syndrome, progressive supranuclear palsy, and psychiatric disorders, as well as healthy controls were used for the development of the model. We used structural MR images, cognitive test results, and apolipoprotein E status for feature selection. Three-dimensional T1-weighted images were preprocessed into voxel-based gray matter images and then subjected to source-based morphometry. We used a support vector machine as a classifier. We applied SHapley Additive exPlanations, a game-theoretical approach, to ensure model accountability. The final model that was based on MR-images, cognitive test results, and apolipoprotein E status yielded 89.8% accuracy and a receiver operating characteristic curve of 0.888. The model based on MR-images alone showed 84.7% accuracy. Aβ-positivity was correctly detected in non-AD patients. One of the seven independent components derived from source-based morphometry was considered to represent an AD-related gray matter volume pattern and showed the strongest impact on the model output. Aβ-positivity across neurological and psychiatric disorders was predicted with moderate-to-high accuracy and was associated with a probable AD-related gray matter volume pattern. An MRI-based data-driven machine learning approach can be beneficial as a diagnostic aid.

Frontotemporal Lobar Degeneration (FTLD) causes a heterogeneous group of neurodegenerative disorders with a wide range of clinical features. This might delay time to diagnosis. The aim of the present study is to establish time to diagnosis and its predictors in patients with FTLD-associated syndromes.

Early and accurate diagnosis is crucial for effective treatment and improved outcomes, yet identifying psychotic episodes presents significant challenges due to its complex nature and the varied presentation of symptoms among individuals. One of the primary difficulties lies in the underreporting and underdiagnosis of psychosis, compounded by the stigma surrounding mental health and the individuals' often diminished insight into their condition. Existing efforts leveraging Electronic Health Records (EHRs) to retrospectively identify psychosis typically rely on structured data, such as medical codes and patient demographics, which frequently lack essential information. Addressing these challenges, our study leverages Natural Language Processing (NLP) algorithms to analyze psychiatric admission notes for the diagnosis of psychosis, providing a detailed evaluation of rule-based algorithms, machine learning models, and pre-trained language models. Additionally, the study investigates the effectiveness of employing keywords to streamline extensive note data before training and evaluating the models. Analyzing 4,617 initial psychiatric admission notes (1,196 cases of psychosis versus 3,433 controls) from 2005 to 2019, we discovered that the XGBoost classifier employing Term Frequency-Inverse Document Frequency (TF-IDF) features derived from notes pre-selected by expert-curated keywords, attained the highest performance with an F1 score of 0.8881 (AUROC [95% CI]: 0.9725 [0.9717, 0.9733]). BlueBERT demonstrated comparable efficacy an F1 score of 0.8841 (AUROC [95% CI]: 0.97 [0.9580,0.9820]) on the same set of notes. Both models markedly outperformed traditional International Classification of Diseases (ICD) code-based detection methods from discharge summaries, which had an F1 score of 0.7608, thus improving the margin by 0.12. Furthermore, our findings indicate that keyword pre-selection markedly enhances the performance of both machine learning and pre-trained language models. This study illustrates the potential of NLP techniques to improve psychosis detection within admission notes and aims to serve as a foundational reference for future research on applying NLP for psychosis identification in EHR notes.

The Fugl-Meyer assessment for upper extremity (FMA-UE) is a measure for assessing upper extremity motor function in patients with stroke. However, the considerable administration time of the assessment decreases its feasibility. This study aimed to develop an accumulative assessment system of upper extremity motor function (AAS-UE) based on the FMA-UE to improve administrative efficiency while retaining sufficient psychometric properties.

This narrative literature review undertakes a comprehensive examination of the burgeoning field, tracing the development of artificial intelligence (AI)-powered tools for depression and anxiety detection from the level of intricate algorithms to practical applications. Delivering essential mental health care services is now a significant public health priority. In recent years, AI has become a game-changer in the early identification and intervention of these pervasive mental health disorders. AI tools can potentially empower behavioral healthcare services by helping psychiatrists collect objective data on patients' progress and tasks. This study emphasizes the current understanding of AI, the different types of AI, its current use in multiple mental health disorders, advantages, disadvantages, and future potentials. As technology develops and the digitalization of the modern era increases, there will be a rise in the application of artificial intelligence in psychiatry; therefore, a comprehensive understanding will be needed. We searched PubMed, Google Scholar, and Science Direct using keywords for this. In a recent review of studies using electronic health records (EHR) with AI and machine learning techniques for diagnosing all clinical conditions, roughly 99 publications have been found. Out of these, 35 studies were identified for mental health disorders in all age groups, and among them, six studies utilized EHR data sources. By critically analyzing prominent scholarly works, we aim to illuminate the current state of this technology, exploring its successes, limitations, and future directions. In doing so, we hope to contribute to a nuanced understanding of AI's potential to revolutionize mental health diagnostics and pave the way for further research and development in this critically important domain.

Owing to the heterogenic picture of bipolar disorder, it takes approximately 8.8 years to reach a correct diagnosis. Early recognition and early intervention might not only increase quality of life, but also increase life expectancy as a whole in individuals with bipolar disorder. Therefore, we hypothesize that implementing machine learning techniques can be used to support the diagnostic process of bipolar disorder and minimize misdiagnosis rates.

Early and accurate diagnosis is crucial for effective treatment and improved outcomes, yet identifying psychotic episodes presents significant challenges due to its complex nature and the varied presentation of symptoms among individuals. One of the primary difficulties lies in the underreporting and underdiagnosis of psychosis, compounded by the stigma surrounding mental health and the individuals' often diminished insight into their condition. Existing efforts leveraging Electronic Health Records (EHRs) to retrospectively identify psychosis typically rely on structured data, such as medical codes and patient demographics, which frequently lack essential information. Addressing these challenges, our study leverages Natural Language Processing (NLP) algorithms to analyze psychiatric admission notes for the diagnosis of psychosis, providing a detailed evaluation of rule-based algorithms, machine learning models, and pre-trained language models. Additionally, the study investigates the effectiveness of employing keywords to streamline extensive note data before training and evaluating the models. Analyzing 4,617 initial psychiatric admission notes (1,196 cases of psychosis versus 3,433 controls) from 2005 to 2019, we discovered that the XGBoost classifier employing Term Frequency-Inverse Document Frequency (TF-IDF) features derived from notes pre-selected by expert-curated keywords, attained the highest performance with an F1 score of 0.8881 (AUROC [95% CI]: 0.9725 [0.9717, 0.9733]). BlueBERT demonstrated comparable efficacy an F1 score of 0.8841 (AUROC [95% CI]: 0.97 [0.9580, 0.9820]) on the same set of notes. Both models markedly outperformed traditional International Classification of Diseases (ICD) code-based detection methods from discharge summaries, which had an F1 score of 0.7608, thus improving the margin by 0.12. Furthermore, our findings indicate that keyword pre-selection markedly enhances the performance of both machine learning and pre-trained language models. This study illustrates the potential of NLP techniques to improve psychosis detection within admission notes and aims to serve as a foundational reference for future research on applying NLP for psychosis identification in EHR notes.

To establish the predictive value of the QRESEARCH risk estimator version 3 (QRISK3) algorithm in identifying Spanish patients with ankylosing spondylitis (AS) at high risk of cardiovascular (CV) events and CV mortality. We also sought to determine whether to combine QRISK3 with another CV risk algorithm: the traditional SCORE, the modified SCORE (mSCORE) EULAR 2015/2016 or the SCORE2 may increase the identification of AS patients with high-risk CV disease.

The aim of this study is to consider limitations to the heuristics 'treatment-resistant depression' (TRD) and 'difficult-to-treat' depression (DTD) and to offer a revisionist model.

Youth of color are often exposed to racism at both systemic and individual levels. Interpersonal racial/ethnic discrimination is the behavioral manifestation of individual racism. While direct individual experiences of racism (eg, comments directed at the individual) have deleterious effects for the socioemotional well-being of youth of color, research also points to the negative effects of broader exposure to racism (eg, viewing racist comments, images, or videos online) that is not experienced directly. Now that social media (SM) has become a prominent and ubiquitous source of social interactions for adolescents, research on the influence of racism on youth must contend with this new medium. This is especially the case for youth of color, particularly Black and Hispanic/Latine youth, who report more SM use than White youth who do not identify as Hispanic/Latine. The unique features of SM, including its permanence, publicness, and personalized algorithms, may increase both direct and indirect experiences of online racism for youth of color, particularly due to its constant availability and highly visual nature, which likely expose and re-expose youth of color to a variety of online racist experiences. Approximately 20% of all Black adolescents sampled in a large national survey reported that they were the target of online bullying or harassment because of their racial or ethnic identity. Indeed, exposure to direct and indirect online racism is associated with negative mental health outcomes for youth of color, including posttraumatic symptoms, depression, and anxiety.

Guidelines on the management of depression recommend that practitioners use patient-reported outcome measures for the follow-up monitoring of symptoms, but there is a lack of evidence of benefit in terms of patient outcomes.

Comprehensive, continuous quantitative monitoring of intricately orchestrated physiological processes and behavioral states in living organisms can yield essential data for elucidating the function of neural circuits under healthy and diseased conditions, for defining the effects of potential drugs and treatments, and for tracking disease progression and recovery. Here, we report a wireless, battery-free implantable device and a set of associated algorithms that enable continuous, multiparametric physio-behavioral monitoring in freely behaving small animals and interacting groups. Through advanced analytics approaches applied to mechano-acoustic signals of diverse body processes, the device yields heart rate, respiratory rate, physical activity, temperature, and behavioral states. Demonstrations in pharmacological, locomotor, and acute and social stress tests and in optogenetic studies offer unique insights into the coordination of physio-behavioral characteristics associated with healthy and perturbed states. This technology has broad utility in neuroscience, physiology, behavior, and other areas that rely on studies of freely moving, small animal models.

Transcranial direct current stimulation (tDCS) is a non-invasive neuromodulation technique gaining more attention in neurodevelopmental disorders (NDDs). Due to the phenotypic heterogeneity of NDDs, tDCS is unlikely to be equally effective in all individuals. The present study aimed to establish neuroanatomical markers in typical developing (TD) individuals that may be used for the prediction of individual responses to tDCS. 57 TD male and female children received 2mA anodal and sham tDCS, targeting the left dorsolateral prefrontal cortex (DLPFC), right inferior frontal gyrus, and bilateral temporo-parietal junction. Response to tDCS was assessed based on task performance differences between anodal and sham tDCS in different neurocognitive tasks (N-back, Flanker, Mooney Faces Detection, Attentional Emotional Recognition task). Measures of cortical thickness (CT) and surface area (SA) were derived from 3-Tesla structural MRI scans. Associations between neuroanatomy and task performance were assessed using a general linear model. Machine learning (ML) algorithms were employed to predict responses to tDCS. Overall, vertex-wise estimates of SA were more closely linked to differences in task performance than measures of CT. Across ML algorithms, highest accuracies were observed for the prediction of N-back task performance differences following stimulation of the DLPFC, where 65% of behavioural variance was explained by variability in SA. Lower accuracies were observed for all other tasks and stimulated regions. This suggests that it may be possible to predict individual responses to tDCS for some behavioural measures and target regions. In the future, these models might be extended to predict treatment outcome in individuals with NDDs. Transcranial direct current stimulation (tDCS) is a non-invasive neuromodulation technique that has recently gained more attention in neurodevelopmental disorders (NDDs), such as autism and attention-deficit/hyperactivity disorder. However, due to the phenotypic heterogeneity of NDDs, tDCS is unlikely to be equally effective in all individuals. The present study aimed to establish neuroanatomical biomarkers in typical developing individuals that may be used for the prediction of individual responses to tDCS. Our findings suggest that it may be possible to accurately predict individual responses to tDCS for some behavioural measures using measures of neuroanatomy. In the future, our models might be extended to predict treatment outcome in individuals with clinical diagnoses, and may allow for more individualized, person-centred interventions.

Less than a third of patients with depression achieve successful remission with standard first-step antidepressant monotherapy. The process for determining appropriate second-step care is often based on clinical intuition and involves a protracted course of trial and error, resulting in substantial patient burden and unnecessary delay in the provision of optimal treatment. To address this problem, we adopt an ensemble machine learning approach to improve prediction accuracy of remission in response to second-step treatments.

Exercise interventions are nowadays considered as effective add-on treatments in people with schizophrenia but are usually associated with high dropout rates. Therefore, the present study investigated potential predictors of adherence from a large multicenter study, encompassing two types of exercise training, conducted over a 6-month period with individuals with schizophrenia. First, we examined the role of multiple participants' characteristics, including levels of functioning, symptom severity, cognitive performance, quality of life, and physical fitness. Second, we used K-means clustering to identify clinical subgroups of participants that potentially exhibited superior adherence. Last, we explored if adherence could be predicted on the individual level using Random Forest, Logistic Regression, and Ridge Regression. We found that individuals with higher levels of functioning at baseline were more likely to adhere to the exercise interventions, while other factors such as symptom severity, cognitive performance, quality of life or physical fitness seemed to be less influential. Accordingly, the high-functioning group with low symptoms exhibited a greater likelihood of adhering to the interventions compared to the severely ill group. Despite incorporating various algorithms, it was not possible to predict adherence at the individual level. These findings add to the understanding of the factors that influence adherence to exercise interventions. They underscore the predictive importance of daily life functioning while indicating a lack of association between symptom severity and adherence. Future research should focus on developing targeted strategies to improve adherence, particularly for people with schizophrenia who suffer from impairments in daily functioning.Clinical trials registration The study of this manuscript which the manuscript is based was registered in the International Clinical Trials Database, ClinicalTrials.gov (NCT number: NCT03466112, https://clinicaltrials.gov/ct2/show/NCT03466112?term=NCT03466112&draw=2&rank=1 ) and in the German Clinical Trials Register (DRKS-ID: DRKS00009804.

Through the application of machine learning algorithms to neuroimaging data the brain age methodology was shown to provide a useful individual-level biological age prediction and identify key brain regions responsible for the prediction. In this study, we present the methodology of constructing a rhesus macaque brain age model using a machine learning algorithm and discuss the key predictive brain regions in comparison to the human brain, to shed light on cross-species primate similarities and differences. Structural information of the brain (e.g., parcellated volumes) from brain magnetic resonance imaging of 43 rhesus macaques were used to develop brain atlas-based features to build a brain age model that predicts biological age. The best-performing model used 22 selected features and achieved an R of 0.72. We also identified interpretable predictive brain features including Right Fronto-orbital Cortex, Right Frontal Pole, Right Inferior Lateral Parietal Cortex, and Bilateral Posterior Central Operculum. Our findings provide converging evidence of the parallel and comparable brain regions responsible for both non-human primates and human biological age prediction.

Artificial intelligence (AI) is rapidly transforming the field of medicine, announcing a new era of innovation and efficiency. Among AI programs designed for general use, ChatGPT holds a prominent position, using an innovative language model developed by OpenAI. Thanks to the use of deep learning techniques, ChatGPT stands out as an exceptionally viable tool, renowned for generating human-like responses to queries. Various medical specialties, including rheumatology, oncology, psychiatry, internal medicine, and ophthalmology, have been explored for ChatGPT integration, with pilot studies and trials revealing each field's potential benefits and challenges. However, the field of genetics and genetic counseling, as well as that of rare disorders, represents an area suitable for exploration, with its complex datasets and the need for personalized patient care. In this review, we synthesize the wide range of potential applications for ChatGPT in the medical field, highlighting its benefits and limitations. We pay special attention to rare and genetic disorders, aiming to shed light on the future roles of AI-driven chatbots in healthcare. Our goal is to pave the way for a healthcare system that is more knowledgeable, efficient, and centered around patient needs.

To develop and evaluate a multidimensional comorbidity index (MCI) that identifies ovarian cancer patients at risk of early mortality more accurately than the Charlson Comorbidity Index (CCI) for use in health services research.

More in-depth evidence about the complex relationships between different risk factors and mental health among adolescents has been warranted. Thus, the aim of the study was to examine the direct and indirect effects of experiencing social pressure, bullying, and low social support on mental health problems in adolescence.

Linguistic features, particularly the use of first-person singular pronouns (FPSPs), have been identified as potential indicators of suicidal ideation. Machine learning (ML) and natural language processing (NLP) have shown potential in suicide detection, but their clinical applicability remains underexplored. This study aimed to identify linguistic features associated with suicidal ideation and develop ML models for detection. NLP techniques were applied to clinical interview transcripts ( = 319) to extract relevant features, including four cases of FPSP (subjective, objective, dative, and possessive cases) and first-person plural pronouns (FPPPs). Logistic regression analyses were conducted for each linguistic feature, controlling for age, gender, and depression. Gradient boosting, support vector machine, random forest, decision tree, and logistic regression were trained and evaluated. Results indicated that all four cases of FPSPs were associated with depression ( < 0.05) but only the use of objective FPSPs was significantly associated with suicidal ideation ( = 0.02). Logistic regression and support vector machine models successfully detected suicidal ideation, achieving an area under the curve (AUC) of 0.57 ( < 0.05). In conclusion, FPSPs identified during clinical interviews might be a promising indicator of suicidal ideation in Chinese patients. ML algorithms might have the potential to aid clinicians in improving the detection of suicidal ideation in clinical settings.

In this study, for the first time, we explored a dataset of functional magnetic resonance images collected during focused attention and open monitoring meditation before and after a five-day psilocybin-assisted meditation retreat using a recently established approach, based on the Mapper algorithm from topological data analysis. After generating subject-specific maps for two groups (psilocybin vs. placebo, 18 subjects/group) of experienced meditators, organizational principles were uncovered using graph topological tools, including the optimal transport (OT) distance, a geometrically rich measure of similarity between brain activity patterns. This revealed characteristics of the topology (i.e. shape) in space (i.e. abstract space of voxels) and time dimension of whole-brain activity patterns during different styles of meditation and psilocybin-induced alterations. Most interestingly, we found that (psilocybin-induced) positive derealization, which fosters insightfulness specifically when accompanied by enhanced open-monitoring meditation, was linked to the OT distance between open-monitoring and resting state. Our findings suggest that enhanced meta-awareness through meditation practice in experienced meditators combined with potential psilocybin-induced positive alterations in perception mediate insightfulness. Together, these findings provide a novel perspective on meditation and psychedelics that may reveal potential novel brain markers for positive synergistic effects between mindfulness practices and psilocybin.

This study introduces a novel approach for integrating sensitive patient information within medical images with minimal impact on their diagnostic quality. Utilizing the mask region-based convolutional neural network for identifying regions of minimal medical significance, the method embeds information using discrete cosine transform-based steganography. The focus is on embedding within "insignificant areas", determined by deep learning models, to ensure image quality and confidentiality are maintained. The methodology comprises three main steps: neural network training for area identification, an embedding process for data concealment, and an extraction process for retrieving embedded information. Experimental evaluations on the CHAOS dataset demonstrate the method's effectiveness, with the model achieving an average intersection over union score of 0.9146, indicating accurate segmentation. Imperceptibility metrics, including peak signal-to-noise ratio, were employed to assess the quality of stego images, with results showing high capacity embedding with minimal distortion. Furthermore, the embedding capacity and payload analysis reveal the method's high capacity for data concealment. The proposed method outperforms existing techniques by offering superior image quality, as evidenced by higher peak signal-to-noise ratio values, and efficient concealment capacity, making it a promising solution for secure medical image handling.

Mood disorders (MDs) are among the leading causes of disease burden worldwide. Limited specialized care availability remains a major bottleneck thus hindering pre-emptive interventions. MDs manifest with changes in mood, sleep, and motor activity, observable in ecological physiological recordings thanks to recent advances in wearable technology. Therefore, near-continuous and passive collection of physiological data from wearables in daily life, analyzable with machine learning (ML), could mitigate this problem, bringing MDs monitoring outside the clinician's office. Previous works predict a single label, either the disease state or a psychometric scale total score. However, clinical practice suggests that the same label may underlie different symptom profiles, requiring specific treatments. Here we bridge this gap by proposing a new task: inferring all items in HDRS and YMRS, the two most widely used standardized scales for assessing MDs symptoms, using physiological data from wearables. To that end, we develop a deep learning pipeline to score the symptoms of a large cohort of MD patients and show that agreement between predictions and assessments by an expert clinician is clinically significant (quadratic Cohen's κ and macro-average F1 score both of 0.609). While doing so, we investigate several solutions to the ML challenges associated with this task, including multi-task learning, class imbalance, ordinal target variables, and subject-invariant representations. Lastly, we illustrate the importance of testing on out-of-distribution samples.

By adolescence, two-thirds of youth report exposure to at least one traumatic event, yet the impact of trauma history is not routinely considered when evaluating the effect of psychotherapeutic interventions. Trauma may be a particularly important moderator of the effects of transdiagnostic therapies for emotional disorders, as trauma exposure is associated with risk for the development of comorbid depression and anxiety. The current study examined the history of trauma exposure and the presence of clinically significant depression as moderators of treatment outcomes in the Brief Behavioral Therapy (BBT) trial, the largest study of transdiagnostic psychotherapy for youth. Youths (age 8-16 years) were randomized to BBT (n = 89) based in pediatric primary care or assisted referral to outpatient community care (ARC; n = 86). Clinical response, functioning, anxiety symptoms, and depression symptoms were assessed at post-treatment (Week 16) and at follow-up (Week 32). A significant three-way interaction emerged between the treatment group, comorbid depression, and trauma exposure. BBT was broadly effective for 3/4 of the sample, but, for anxious-depressed youth with trauma exposure, BBT never significantly separated from ARC. Differences in outcome were not accounted for by other participant characteristics or by therapist-rated measures of alliance, youth engagement, or homework completion. Implications for models of learning and for intervention theory and development are discussed.

There is an urgent need to monitor the mental health of large populations, especially during crises such as the COVID-19 pandemic, to timely identify the most at-risk subgroups and to design targeted prevention campaigns. We therefore developed and validated surveillance indicators related to suicidality: the monthly number of hospitalisations caused by suicide attempts and the prevalence among them of five known risks factors. They were automatically computed analysing the electronic health records of fifteen university hospitals of the Paris area, France, using natural language processing algorithms based on artificial intelligence. We evaluated the relevance of these indicators conducting a retrospective cohort study. Considering 2,911,920 records contained in a common data warehouse, we tested for changes after the pandemic outbreak in the slope of the monthly number of suicide attempts by conducting an interrupted time-series analysis. We segmented the assessment time in two sub-periods: before (August 1, 2017, to February 29, 2020) and during (March 1, 2020, to June 31, 2022) the COVID-19 pandemic. We detected 14,023 hospitalisations caused by suicide attempts. Their monthly number accelerated after the COVID-19 outbreak with an estimated trend variation reaching 3.7 (95%CI 2.1-5.3), mainly driven by an increase among girls aged 8-17 (trend variation 1.8, 95%CI 1.2-2.5). After the pandemic outbreak, acts of domestic, physical and sexual violence were more often reported (prevalence ratios: 1.3, 95%CI 1.16-1.48; 1.3, 95%CI 1.10-1.64 and 1.7, 95%CI 1.48-1.98), fewer patients died (p = 0.007) and stays were shorter (p < 0.001). Our study demonstrates that textual clinical data collected in multiple hospitals can be jointly analysed to compute timely indicators describing mental health conditions of populations. Our findings also highlight the need to better take into account the violence imposed on women, especially at early ages and in the aftermath of the COVID-19 pandemic.

Identifying biomarkers is essential to obtain the optimal therapeutic benefit while treating patients with late-life depression (LLD). We compare LLD patients with healthy controls (HC) using resting-state functional magnetic resonance and diffusion tensor imaging data to identify neuroimaging biomarkers that may be potentially associated with the underlying pathophysiology of LLD. We implement a Bayesian multimodal local false discovery rate approach for functional connectivity, borrowing strength from structural connectivity to identify disrupted functional connectivity of LLD compared to HC. In the Bayesian framework, we develop an algorithm to control the overall false discovery rate of our findings. We compare our findings with the literature and show that our approach can better detect some regions never discovered before for LLD patients. The Hub of our discovery related to various neurobehavioral disorders can be used to develop behavioral interventions to treat LLD patients who do not respond to antidepressants.

Postpartum depression (PPD) is one of the most common complications of delivery and is usually disregarded. Several risk factors of PPD have been identified, but its pathogenesis has not been completely understood. Serum bilirubin has been found to be a predictor of depression, whose relationship with PPD has not been investigated.

The advent and growing popularity of generative artificial intelligence (GenAI) holds the potential to revolutionise AI applications in forensic psychiatry and criminal justice, which traditionally relied on discriminative AI algorithms. Generative AI models mark a significant shift from the previously prevailing paradigm through their ability to generate seemingly new realistic data and analyse and integrate a vast amount of unstructured content from different data formats. This potential extends beyond reshaping conventional practices, like risk assessment, diagnostic support, and treatment and rehabilitation plans, to creating new opportunities in previously underexplored areas, such as training and education. This paper examines the transformative impact of generative artificial intelligence on AI applications in forensic psychiatry and criminal justice. First, it introduces generative AI and its prevalent models. Following this, it reviews the current applications of discriminative AI in forensic psychiatry. Subsequently, it presents a thorough exploration of the potential of generative AI to transform established practices and introduce novel applications through multimodal generative models, data generation and data augmentation. Finally, it provides a comprehensive overview of ethical and legal issues associated with deploying generative AI models, focusing on their impact on individuals as well as their broader societal implications. In conclusion, this paper aims to contribute to the ongoing discourse concerning the dynamic challenges of generative AI applications in forensic contexts, highlighting potential opportunities, risks, and challenges. It advocates for interdisciplinary collaboration and emphasises the necessity for thorough, responsible evaluations of generative AI models before widespread adoption into domains where decisions with substantial life-altering consequences are routinely made.

During peacekeeping missions, military personnel may be involved in or exposed to potentially morally injurious experiences (PMIEs), such as an inability to intervene due to a limited mandate. While exposure to such morally transgressive events has been shown to lead to moral injury in combat veterans, research on moral injury in peacekeepers is limited. We aimed to determine patterns of exposure to PMIEs and associated outcome- and exposure-related factors among Dutch peacekeepers stationed in the former Yugoslavia during the Srebrenica genocide. Self-report data were collected among Dutchbat III veterans ( = 431). We used Latent Class Analysis to identify subgroups of PMIE exposure as assessed by the Moral Injury Scale-Military version. We investigated whether deployment location, posttraumatic stress disorder (PTSD), posttraumatic growth, resilience, and quality of life differentiated between latent classes. The analysis identified a three-class solution: a high exposure class ( = 79), a moderate exposure class ( = 261), and a betrayal and powerlessness-only class ( = 135). More PMIE exposure was associated with deployment location and higher odds of having probable PTSD. PMIE exposure was not associated with posttraumatic growth. Resilience and quality of life were excluded from analyses due to high correlations with PTSD. Peacekeepers may experience varying levels of PMIE exposure, with more exposure being associated with worse outcomes 25 years later. Although no causal relationship may be assumed, the results emphasize the importance of better understanding PMIEs within peacekeeping.

To assess the validity of the screening method based on EEG analysis using predictive analytics algorithms with the calculation of linear discriminant functions (LDFs), in comparison with a classification system based on psychometric self-report scales.

Metabolic bariatric surgery is a critical intervention for patients living with obesity and related health issues. Accurate classification and prediction of patient outcomes are vital for optimizing treatment strategies. This study presents a novel machine learning approach to classify patients in the context of metabolic bariatric surgery, providing insights into the efficacy of different models and variable types.

Suicide is a complex, multidimensional event, and a significant challenge for prevention globally. Artificial intelligence (AI) and machine learning (ML) have emerged to harness large-scale datasets to enhance risk detection. In order to trust and act upon the predictions made with ML, more intuitive user interfaces must be validated. Thus, Interpretable AI is one of the crucial directions which could allow policy and decision makers to make reasonable and data-driven decisions that can ultimately lead to better mental health services planning and suicide prevention. This research aimed to develop sex-specific ML models for predicting the population risk of suicide and to interpret the models. Data were from the Quebec Integrated Chronic Disease Surveillance System (QICDSS), covering up to 98% of the population in the province of Quebec and containing data for over 20,000 suicides between 2002 and 2019. We employed a case-control study design. Individuals were considered cases if they were aged 15+ and had died from suicide between January 1st, 2002, and December 31st, 2019 (n = 18339). Controls were a random sample of 1% of the Quebec population aged 15+ of each year, who were alive on December 31st of each year, from 2002 to 2019 (n = 1,307,370). We included 103 features, including individual, programmatic, systemic, and community factors, measured up to five years prior to the suicide events. We trained and then validated the sex-specific predictive risk model using supervised ML algorithms, including Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost) and Multilayer perceptron (MLP). We computed operating characteristics, including sensitivity, specificity, and Positive Predictive Value (PPV). We then generated receiver operating characteristic (ROC) curves to predict suicides and calibration measures. For interpretability, Shapley Additive Explanations (SHAP) was used with the global explanation to determine how much the input features contribute to the models' output and the largest absolute coefficients. The best sensitivity was 0.38 with logistic regression for males and 0.47 with MLP for females; the XGBoost Classifier with 0.25 for males and 0.19 for females had the best precision (PPV). This study demonstrated the useful potential of explainable AI models as tools for decision-making and population-level suicide prevention actions. The ML models included individual, programmatic, systemic, and community levels variables available routinely to decision makers and planners in a public managed care system. Caution shall be exercised in the interpretation of variables associated in a predictive model since they are not causal, and other designs are required to establish the value of individual treatments. The next steps are to produce an intuitive user interface for decision makers, planners and other stakeholders like clinicians or representatives of families and people with live experience of suicidal behaviors or death by suicide. For example, how variations in the quality of local area primary care programs for depression or substance use disorders or increased in regional mental health and addiction budgets would lower suicide rates.

Early detection of cognitive impairment in the elderly is crucial for diagnosis and appropriate care. Brief, cost-effective cognitive screening instruments are needed to help identify individuals who require further evaluation. This study presents preliminary data on a new screening technology using automated voice recording analysis software in a Spanish population.

Traumatic experiences are a significant risk factor for psychological disturbances, including disorders such as complex posttraumatic stress disorder, emotion-processing problems, and trauma-related dissociative experiences. The present investigation examined the coexistence of these symptoms using a network analysis model.

Improve detection of Attention Deficit/Hyperactivity Disorder (ADHD) in a safety net, hospital-based, academic pediatric practice by optimizing screening with the Pediatric Symptom Checklist attention score (PSC-AS) and further evaluation with the Vanderbilt ADHD Diagnostic Rating Scale (VADRS).

Schizophrenia spectrum disorders (SSD) can be associated with an increased risk of violent behavior (VB), which can harm patients, others, and properties. Prediction of VB could help reduce the SSD burden on patients and healthcare systems. Some recent studies have used machine learning (ML) algorithms to identify SSD patients at risk of VB. In this article, we aimed to review studies that used ML to predict VB in SSD patients and discuss the most successful ML methods and predictors of VB.

Clinicians collect session therapy notes within patient session records. Session records contain valuable information about patients' treatment progress. Sentiment analysis is a tool to extract emotional tones and states from text input and could be used to evaluate patients' sentiment during treatment over time. This preliminary study aims to investigate the validity of automated sentiment analysis on session patient records within an eating disorder (ED) treatment context against the performance of human raters.

Painful diabetic neuropathy (PDN) is a leading cause of pain and disability globally with a lack of consensus on the appropriate treatment of those suffering from this condition. Recent advancements in both pharmacotherapy and interventional approaches have broadened the treatment options for PDN. There exists a need for a comprehensive guideline for the safe and effective treatment of patients suffering from PDN.