Mittermaier Mirja, Raza Marium, Kvedar Joseph C
Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Department of Infectious Diseases, Respiratory Medicine and Critical Care, Berlin, Germany.
Berlin Institute of Health at Charité-Universitätsmedizin Berlin, Charitéplatz 1, 10117, Berlin, Germany.
NPJ Digit Med. 2023 Aug 5;6(1):137. doi: 10.1038/s41746-023-00889-6.
AI-based prediction models demonstrate equal or surpassing performance compared to experienced physicians in various research settings. However, only a few have made it into clinical practice. Further, there is no standardized protocol for integrating AI-based physician support systems into the daily clinical routine to improve healthcare delivery. Generally, AI/physician collaboration strategies have not been extensively investigated. A recent study compared four potential strategies for AI model deployment and physician collaboration to investigate the performance of an AI model trained to identify signs of acute respiratory distress syndrome (ARDS) on chest X-ray images. Here we discuss strategies and challenges with AI/physician collaboration when AI-based decision support systems are implemented in the clinical routine.
在各种研究环境中,基于人工智能的预测模型表现出与经验丰富的医生相当或更优的性能。然而,只有少数模型进入了临床实践。此外,目前还没有将基于人工智能的医生支持系统整合到日常临床工作中以改善医疗服务的标准化方案。总体而言,人工智能与医生的协作策略尚未得到广泛研究。最近一项研究比较了人工智能模型部署和医生协作的四种潜在策略,以调查一个经过训练用于识别胸部X光图像上急性呼吸窘迫综合征(ARDS)迹象的人工智能模型的性能。在此,我们将讨论在临床常规中实施基于人工智能的决策支持系统时,人工智能与医生协作的策略和挑战。