Key points are not available for this paper at this time.
Artificial intelligence (AI) is increasingly positioned as a transformative force in healthcare. The translation of AI from technical validation to real-world clinical impact remains a critical challenge. This systematic review aims to synthesize the evidence on the AI translational pathway in healthcare, focusing on the systemic barriers and facilitators to integration. Following PRISMA 2020 guidelines, we searched PubMed, Scopus, Web of Science, and IEEE Xplore for studies published between 2000 and 2025. We included peer-reviewed original research, clinical trials, observational studies, and reviews reporting on AI technical validation, clinical deployment, implementation outcomes, or ethical governance. While AI models consistently demonstrate high diagnostic accuracy (92–98% in radiology) and robust predictive performance (AUC 0.76–0.82 in readmission forecasting), clinical adoption remains limited, with only 15–25% of departments integrating AI tools and approximately 60% of projects failing beyond pilot testing. Key barriers include interoperability limitations affecting over half of implementations, lack of clinician trust in unsupervised systems (35%), and regulatory immaturity, with only 27% of countries establishing AI governance frameworks. Moreover, performance disparities exceeding 10% were identified in 28% of models, alongside a pronounced global divide, as 73% of low-resource health systems lack enabling infrastructure. These findings underscore the need for systemic, trustworthy, and equity-driven AI integration strategies.
Medani et al. (Sat,) studied this question.