Eini-Porat Bar, Amir Ofra, Eytan Danny, Shalit Uri
Technion - Israel Institute of Technology, Haifa, Israel.
Technion - Israel Institute of Technology, Haifa, Israel.
J Biomed Inform. 2022 Aug;132:104107. doi: 10.1016/j.jbi.2022.104107. Epub 2022 Jun 7.
In recent years, extensive resources are dedicated to the development of machine learning (ML) based clinical prediction models for intensive care unit (ICU) patients. These models are transforming patient care into a collaborative human-AI task, yet prediction of patient-related events is mostly treated as a standalone goal, without considering clinicians' roles, tasks or workflow in depth. We conducted a mixed methods study aimed at understanding clinicians' needs and expectations from such systems, informing the design of machine learning based prediction models. Our findings identify several areas of focus where clinicians' needs deviate from current practice, including desired prediction targets, timescales stemming from actionability requirements, and concerns regarding the evaluation and trust in these algorithms. Based on our findings, we suggest several design implications for ML-based prediction tools in the ICU.
近年来，大量资源投入到基于机器学习（ML）的重症监护病房（ICU）患者临床预测模型的开发中。这些模型正在将患者护理转变为一项人类与人工智能协作的任务，然而，对患者相关事件的预测大多被视为一个独立的目标，而没有深入考虑临床医生的角色、任务或工作流程。我们开展了一项混合方法研究，旨在了解临床医生对这类系统的需求和期望，为基于机器学习的预测模型设计提供参考。我们的研究结果确定了几个重点领域，临床医生的需求在这些领域与当前实践存在差异，包括期望的预测目标、基于可操作性要求的时间尺度，以及对这些算法的评估和信任方面的担忧。基于我们的研究结果，我们对ICU中基于ML的预测工具提出了几点设计建议。
