Curr Pharm Biotechnol. 2024 Jun 6. doi: 10.2174/0113892010298852240528123911. Online ahead of print.

ABSTRACT

Early cancer identification is essential for increasing survival rates and lowering the disease’s burden in today’s society. Artificial intelligence [AI]–based algorithms may help in the early detection of cancer and resolve problems with current diagnostic methods. This article gives an overview of the prospective uses of AI in early cancer detection. The authors go over the possible applications of Artificial Intelligence algorithms used for screening risk of malignancy in asymptomatic patients, investigating as well as prioritising symptomatic individuals, and more accurately diagnosing cancer recurrence. In screening programmes, the importance of patient selection and risk stratification is emphasised, and AI may be able to assist in identifying people who are most at risk of acquiring cancer. Aside from pathology slide and peripheral blood analysis, AI can also increase the diagnostic precision of imaging methods like computed tomography [CT] and mammography. A summary of various AI techniques is given in the review, covering more sophisticated deep learning and neural networks and more traditional models like logistic regression. The advantages of deep learning algorithms in spotting intricate patterns in huge datasets and their potential to increase the precision of cancer diagnosis are emphasised by the authors. The ethical concerns surrounding the application of AI in healthcare are also discussed, and include topics like prejudice, data security, and privacy. A review of the models now employed in clinical practice is included along with a discussion of the prospective clinical implications of AI algorithms. Examined are AI’s drawbacks and hazards, such as resource requirements, data quality, and the necessity for consistent reporting. In conclusion, this study emphasises the utility of AI algorithms in the early detection of cancer and gives a general overview of the many strategies and difficulties involved in putting them into use in clinical settings.

PMID:38847160 | DOI:10.2174/0113892010298852240528123911