Ardito Vittoria, Cappellaro Giulia, Compagni Amelia, Petracca Francesco, Preti Luigi Maria
Center for Research on Health and Social Care Management (CERGAS), SDA Bocconi School of Management, Milan, Italy.
Department of Social and Political Sciences, Bocconi University, Milan, Italy.
JMIR Res Protoc. 2023 Sep 12;12:e47971. doi: 10.2196/47971.
An increasing interest in machine learning (ML) has been observed among scholars and health care professionals. However, while ML-based applications have been shown to be effective and have the potential to change the delivery of patient care, their implementation in health care organizations is complex. There are several challenges that currently hamper the uptake of ML in daily practice, and there is currently limited knowledge on how these challenges have been addressed in empirical studies on implemented ML-based applications.
The aim of this systematic literature review is twofold: (1) to map the ML-based applications implemented in health care organizations, with a focus on investigating the organizational dimensions that are relevant in the implementation process; and (2) to analyze the processes and strategies adopted to foster a successful uptake of ML.
We developed this protocol following the PRISMA-P (Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols) guidelines. The search was conducted on 3 databases (PubMed, Scopus, and Web of Science), considering a 10-year time frame (2013-2023). The search strategy was built around 4 blocks of keywords (artificial intelligence, implementation, health care, and study type). Based on the detailed inclusion criteria defined, only empirical studies documenting the implementation of ML-based applications used by health care professionals in clinical settings will be considered. The study protocol was registered in PROSPERO (International Prospective Register of Systematic Reviews).
The review is ongoing and is expected to be completed by September 2023. Data analysis is currently underway, and the first results are expected to be submitted for publication in November 2023. The study was funded by the European Union within the Multilayered Urban Sustainability Action (MUSA) project.
ML-based applications involving clinical decision support and automation of clinical tasks present unique traits that add several layers of complexity compared with earlier health technologies. Our review aims at contributing to the existing literature by investigating the implementation of ML from an organizational perspective and by systematizing a conspicuous amount of information on factors influencing implementation.
INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/47971.
学者和医疗保健专业人员对机器学习（ML）的兴趣日益浓厚。然而，虽然基于ML的应用已被证明是有效的，并且有可能改变患者护理的提供方式，但其在医疗保健组织中的实施却很复杂。目前有几个挑战阻碍了ML在日常实践中的应用，而且目前关于这些挑战在已实施的基于ML的应用的实证研究中是如何得到解决的知识有限。
本系统文献综述的目的有两个：（1）梳理医疗保健组织中实施的基于ML的应用，重点调查实施过程中相关的组织维度；（2）分析为促进ML的成功应用而采用的流程和策略。
我们按照PRISMA-P（系统评价和Meta分析方案的首选报告项目）指南制定了本方案。在3个数据库（PubMed、Scopus和Web of Science）上进行检索，时间范围为10年（2013 - 2023年）。检索策略围绕4组关键词（人工智能、实施、医疗保健和研究类型）构建。根据定义的详细纳入标准，仅考虑记录医疗保健专业人员在临床环境中使用的基于ML的应用实施情况的实证研究。该研究方案已在PROSPERO（国际系统评价前瞻性注册库）中注册。
综述正在进行中，预计于2023年9月完成。目前正在进行数据分析，预计第一批结果将于2023年11月提交发表。该研究由欧盟在多层城市可持续发展行动（MUSA）项目中资助。
涉及临床决策支持和临床任务自动化的基于ML的应用具有独特的特点，与早期的医疗技术相比增加了几层复杂性。我们的综述旨在通过从组织角度研究ML的实施并系统化大量关于影响实施的因素的信息，为现有文献做出贡献。
国际注册报告识别号（IRRID）：DERR1-10.2196/47971
