Guidelines for Artificial Intelligence in Medicine: Literature Review and Content Analysis of Frameworks

Abstract

Background Artificial intelligence (AI) is rapidly expanding in medicine despite a lack of consensus on its application and evaluation. Objective We sought to identify current frameworks guiding the application and evaluation of AI for predictive analytics in medicine and to describe the content of these frameworks. We also assessed what stages along the AI translational spectrum (ie, AI development, reporting, evaluation, implementation, and surveillance) the content of each framework has been discussed. Methods We performed a literature review of frameworks regarding the oversight of AI in medicine. The search included key topics such as “artificial intelligence,” “machine learning,” “guidance as topic,” and “translational science,” and spanned the time period 2014-2022. Documents were included if they provided generalizable guidance regarding the use or evaluation of AI in medicine. Included frameworks are summarized descriptively and were subjected to content analysis. A novel evaluation matrix was developed and applied to appraise the frameworks’ coverage of content areas across translational stages. Results Fourteen frameworks are featured in the review, including six frameworks that provide descriptive guidance and eight that provide reporting checklists for medical applications of AI. Content analysis revealed five considerations related to the oversight of AI in medicine across frameworks: transparency, reproducibility, ethics, effectiveness, and engagement. All frameworks include discussions regarding transparency, reproducibility, ethics, and effectiveness, while only half of the frameworks discuss engagement. The evaluation matrix revealed that frameworks were most likely to report AI considerations for the translational stage of development and were least likely to report considerations for the translational stage of surveillance. Conclusions Existing frameworks for the application and evaluation of AI in medicine notably offer less input on the role of engagement in oversight and regarding the translational stage of surveillance. Identifying and optimizing strategies for engagement are essential to ensure that AI can meaningfully benefit patients and other end users.

Multi-omics and machine learning for the prevention and management of female reproductive health

“…These prospective technological advances in remote monitoring of pregnant women would provide conceptual and analytical framework to analyze the complex interplay between various biological modalities that govern preterm birth and other pregnancy-related pathologies. A recent literature review of the use of AI in medicine noted very little identifying and optimizing strategies for engagement, essential for AI to meaningfully benefit patients and other end users (112). In medicine, artificial neural networks (ANNs) (113) are widely used to learn and analyze imprecise pieces of information, and analyze nonlinear data and past examples for the assessment of pregnancy risk and prediction of APOs (114).…”

Evolution of Hybrid Intelligence and Its Application in Evidence-Based Medicine: A Review

“…Some authors suggested that making AI more explainable or “interpretable” may be achieved at the expense of loss of accuracy of these systems, emphasizing that the use of less accurate models carries risks for patient health [ 28 ]. More attention needs to be directed toward how AI clinical support systems will become integrated into the medical decision-making process, so clinicians will be able to understand the outputs of these systems and embed them into their own clinical decision-making procedures [ 28 , 29 , 31 , 32 ]. In this regard, attention is needed also because an algorithmic explanation of AI prediction could be very different from how that prediction has been made [ 31 ].…”

The Clinical Researcher Journey in the Artificial Intelligence Era: The PAC-MAN’s Challenge

“…This could lead reviewers to draw incorrect conclusions [ 22 , 23 ]. Nowadays, there are various types of guidelines available, some of which are an extension of existing ones, to aid researchers in using AI in healthcare ( Table 2 ) [ 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 ]. Adhering to these guidelines is critical for researchers, much like PAC-MAN following the game rules.…”

“… The main guidelines regarding the use of AI in clinical research [ 24 ] (AI = artificial intelligence; ML = Machine Learning). …”