The Analytical Framework of Clinical Trials Evaluating Clinical Outcomes of Artificial Intelligence-Based Digital Health Interventions: A Systematic Literature Review

Résumé fourni par la source

Introduction: This systematic literature review (SLR) provides an analytical framework for clinical trials evaluating clinical outcomes of artificial intelligence-based digital health interventions (AI-DHI). Methods: The SLR was conducted in accordance with the PRISMA guidelines. Search was conducted (September 2025) in PubMed and Embase. Population included patients using AI-DHI. Only clinical trials exploring clinical outcomes, written in English, were considered. NICE checklist was used to assess studies’ quality. Results were analyzed descriptively. Results: Final sample had 84 studies, with metabolic (28.6%), musculoskeletal (20.2%), and mental health disorders (19.0%) as the most common indications. Most studies (75.0%) were controlled, parallel-group trials with 2+ arms, mostly comparing AI-DHI with standard-of-care or waitlist. Although type of intervention often precludes blinding (64.3% were open-label), a double-blinding is strongly recommended (only 6.0%). Only 9.5% of studies were conducted at multiple sites across different countries. Dropout rates in the total sample and each study arm should be <20% at all endpoints (64.3%). Statistical tests were used based on the outcome measures. The small sample sizes and limited generalizability of findings were reported as the main limitations. Conclusions: This SLR emphasized current methodological gaps and an urgent need for unified global guidelines. Standard SLR limitations apply to this research.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.