Knowledge Graphs Based on Meta-Analysis Papers Improve the Quality of Case Formulation: Mixed Methods Design
AI Summary
Provision of meta-analysis knowledge graphs significantly improved case formulation correctness, completeness and feasibility compared with control large language model outputs.
Knowledge graph groups achieved feasibility comparable to human expert formulations; experts scored higher on consistency.
Knowledge graphs may raise novice therapists care quality and aid experienced therapists, though machine formulations can sound unnatural to clients.
JMIR Form Res. 2026 Jun 30;10:e76808. doi: 10.2196/76808.
ABSTRACT
BACKGROUND: Case formulation (CF) is a core skill for therapists; however, creating high-quality CFs requires considerable time.
OBJECTIVE: This study aims to demonstrate that providing a knowledge graph based on meta-analytic literature can enhance CF quality.
METHODS: Five groups were established, including 4 large language model groups and 1 human expert group, each generating 25 CFs based on 25 vignettes. The control group with Claude (Sonnet 3.7; Anthropic) produced 25 CFs. The personalization group served as the control group with additional personalization prompts. The knowledge graph group used a large language model that generated 25 CFs, which was provided with a meta-analysis knowledge graph. Further incorporation of additional personalization prompts then comprised the knowledge graph with personalization group. Finally, the expert group consisted of 25 CFs generated by a human expert. These 125 CFs in total were evaluated for general quality (ie, correctness, completeness, feasibility, and consistency) using a 7-point scale and 18 essential elements with binary scores (0 or 1) by another human expert. The CFs were also qualitatively analyzed.
RESULTS: The knowledge graph and knowledge graph with personalization groups scored significantly higher than the control group in terms of correctness, completeness, and feasibility. The expert group scored significantly higher on consistency than the machine-generated groups. Additionally, there was no significant difference in the feasibility scores among the knowledge graph, knowledge graph with personalization, and expert groups. The qualitative evaluation suggested that human CFs narrow the text to content that is easy for the client to read, whereas machine CFs are more likely to include expressions that are unnatural to the client.
CONCLUSIONS: These results indicate that providing knowledge graphs to novice therapists increases the correctness, completeness, and feasibility of CF. Providing experienced therapists with knowledge graphs is suggested to improve the quality of their CF and mental health services.
Br J Soc Psychol. 2026 Jul;65(3):e70107. doi: 10.1111/bjso.70107.ABSTRACTIn the past decades, social scientists have interrogated the racialized machinations of social space. Ahmed (2007), for example,...
PLOS Glob Public Health. 2026 Jun 30;6(6):e0006670. doi: 10.1371/journal.pgph.0006670. eCollection 2026.ABSTRACTThe COVID-19 pandemic was accompanied by lengthy lockdowns, school closures, and mandatory stay-at-home orders, causing...
Biomedica. 2026 Jun 1;46(2):211-218. doi: 10.7705/biomedica.7910.ABSTRACT¿Es la mortalidad evitable en la niñez en Colombia una forma de violencia? El análisis de la mortalidad en la...
Asian J Psychiatr. 2026 Jun 29;122:105082. doi: 10.1016/j.ajp.2026.105082. Online ahead of print.ABSTRACTBACKGROUND: Participants with psychotic-like experiences (PLEs) have higher suicide behavior (e.g., suicide attempts, suicide...
Asian J Psychiatr. 2026 Jun 28;122:105080. doi: 10.1016/j.ajp.2026.105080. Online ahead of print.NO ABSTRACTPMID:42378833 | DOI:10.1016/j.ajp.2026.105080
Asian J Psychiatr. 2026 Jun 25;122:105079. doi: 10.1016/j.ajp.2026.105079. Online ahead of print.NO ABSTRACTPMID:42378832 | DOI:10.1016/j.ajp.2026.105079
