JMIR Publications

ABSTRACT

Studies on the combined use of artificial intelligence (AI) and electronic healthcare records (EHRs) in hospitals have been becoming more frequent and there is now a significant number of peer-reviewed journal papers. Through a literature review, this study reflects on the effects of the combined use of AI and EHRs on the work of hospitals, aiming to provide an overview of the published literature on this topic. We conducted a systematic literature review focused on empirical research on the combined effect of AI and EHRs in a hospital setting. The following criteria were applied during the selection of the articles: 1) were published in a peer-reviewed journal, 2) were written in English, 3) the full text was accessible to the researchers, 4) include primary empirical data, 5) studied a form of AI technology that was linked to an EHR, 6) either directly or indirectly showed the combined effect on the work of hospitals, and 7) satisfied the standards established for quality research. The initial search resulted in a dataset of 717 articles that were considered in the selection process. In total, 30 relevant articles were selected for inclusion in the final review. The results indicate that AI and EHRs are combined in patient care during risk prediction and decision-making. Healthcare professionals are also affected, and the studies suggest some resistance to the new technology and that professionals must train themselves to use and adopt new work processes. Finally, we have identified additional indirect effects, which show mixed outcomes related to both increased and decreased efficiency and also positive effects on usability and privacy. The review provides an overview of the effects of combining AI and EHRs on hospitals. In particular, the usability of complex data increases efficiency but also has costs within hospitals. However, efficiency only increases when the resistance of healthcare professionals is understood and addressed in depth.