AI-enabled clinical decision support tools for mental healthcare: A product review

• Published in: Artificial intelligence in medicine 2024-12, Vol.160, p.103052
• Main Authors: Kleine, Anne-Kathrin, Kokje, Eesha, Hummelsberger, Pia, Lermer, Eva, Schaffernak, Insa, Gaube, Susanne
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Clinical decision support; Medical device regulation; Mental healthcare
• ISSN: 0933-3657; 1873-2860; 1873-2860
• DOI: 10.1016/j.artmed.2024.103052

The review seeks to promote transparency in the availability of regulated AI-enabled Clinical Decision Support Systems (AI-CDSS) for mental healthcare. From 84 potential products, seven fulfilled the inclusion criteria. The products can be categorized into three major areas: diagnosis of autism spectrum disorder (ASD) based on clinical history, behavioral, and eye-tracking data; diagnosis of multiple disorders based on conversational data; and medication selection based on clinical history and genetic data. We found five scientific articles evaluating the devices' performance and external validity. The average completeness of reporting, indicated by 52 % adherence to the Consolidated Standards of Reporting Trials Artificial Intelligence (CONSORT-AI) checklist, was modest, signaling room for improvement in reporting quality. Our findings stress the importance of obtaining regulatory approval, adhering to scientific standards, and staying up-to-date with the latest changes in the regulatory landscape. Refining regulatory guidelines and implementing effective tracking systems for AI-CDSS could enhance transparency and oversight in the field. •Only seven of 84 AI-CDSS for mental healthcare were included as regulated products.•Products addressed ASD and other psychiatric diagnosis and medication selection.•Research quality and reporting were subpar based on CONSORT-AI criteria.•Limited transparency in reporting details questions AI-CDSS real-world applicability.