A survey on AI and decision support systems in psychiatry – Uncovering a dilemma

作者：

Highlights：

• Small sample sizes (median 151.5) in the literature, focus on algorithm development.

• Low DDSS and AI adoption in clinical practice.

• High accuracy rates (mean 82.8%) did not lead to successful AI and DDSS adoption.

• No clear correlation between sample size and accuracy.

• The absence of unified benchmarking makes research difficult to compare.

摘要

•Small sample sizes (median 151.5) in the literature, focus on algorithm development.•Low DDSS and AI adoption in clinical practice.•High accuracy rates (mean 82.8%) did not lead to successful AI and DDSS adoption.•No clear correlation between sample size and accuracy.•The absence of unified benchmarking makes research difficult to compare.

论文关键词：Medical information policy,Medical technology,Digital decision support system (DDSS),Clinical Decision Support Systems (CDSS),Artificial Intelligence (AI),Machine Learning (ML),Psychiatry

论文评审过程：Received 23 January 2021, Revised 19 April 2022, Accepted 28 April 2022, Available online 2 May 2022, Version of Record 5 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117464