Department of Health Information Management, School of Health Management and Information Sciences, Iran University of Medical Sciences, Tehran, Iran.
Department of Health Information Management, School of Health Management and Information Sciences, Iran University of Medical Sciences, Tehran, Iran.
Int J Med Inform. 2023 Dec;180:105246. doi: 10.1016/j.ijmedinf.2023.105246. Epub 2023 Oct 9.
Identifying patient safety events using electronic health records (EHRs) and automated machine learning-based detection methods can help improve the efficiency and quality of healthcare service provision.
This study aimed to systematically review machine learning-based methods and techniques, as well as their results for patient safety event management using EHRs.
We reviewed the studies that focused on machine learning techniques, including automatic prediction and detection of patient safety events and medical errors through EHR analysis to manage patient safety events. The data were collected by searching Scopus, PubMed (Medline), Web of Science, EMBASE, and IEEE Xplore databases.
After screening, 41 papers were reviewed. Support vector machine (SVM), random forest, conditional random field (CRF), and bidirectional long short-term memory with conditional random field (BiLSTM-CRF) algorithms were mostly applied to predict, identify, and classify patient safety events using EHRs; however, they had different performances. BiLSTM-CRF was employed in most of the studies to extract and identify concepts, e.g., adverse drug events (ADEs) and adverse drug reactions (ADRs), as well as relationships between drug and severity, drug and ADEs, drug and ADRs. Recurrent neural networks (RNN) and BiLSTM-CRF had the best results in detecting ADEs compared to other patient safety events. Linear classifiers and Naive Bayes (NB) had the highest performance for ADR detection. Logistic regression had the best results in detecting surgical site infections. According to the findings, the quality of articles has non-significantly improved in recent years, but they had low average scores.
Machine learning can be useful in automatic detection and prediction of patient safety events. However, most of these algorithms have not yet been externally validated or prospectively tested. Therefore, further studies are required to improve the performance of these automated systems.
使用电子健康记录（EHR）和基于自动化机器学习的检测方法识别患者安全事件有助于提高医疗保健服务提供的效率和质量。
本研究旨在系统回顾基于机器学习的方法和技术，以及它们在使用 EHR 管理患者安全事件方面的结果。
我们回顾了专注于机器学习技术的研究，包括通过 EHR 分析自动预测和检测患者安全事件和医疗错误，以管理患者安全事件。通过搜索 Scopus、PubMed（Medline）、Web of Science、EMBASE 和 IEEE Xplore 数据库收集数据。
经过筛选，共审查了 41 篇论文。支持向量机（SVM）、随机森林、条件随机场（CRF）和带有条件随机场的双向长短期记忆（BiLSTM-CRF）算法主要用于使用 EHR 预测、识别和分类患者安全事件；然而，它们的性能不同。BiLSTM-CRF 被用于大多数研究中，以提取和识别概念，例如药物不良事件（ADE）和药物不良反应（ADR），以及药物与严重程度、药物与 ADE、药物与 ADR 之间的关系。与其他患者安全事件相比，递归神经网络（RNN）和 BiLSTM-CRF 在检测 ADE 方面具有最佳效果。线性分类器和朴素贝叶斯（NB）在检测 ADR 方面性能最高。逻辑回归在检测手术部位感染方面具有最佳效果。根据研究结果，近年来文章质量有了显著提高，但平均得分仍然较低。
机器学习可用于自动检测和预测患者安全事件。然而，这些算法中的大多数尚未经过外部验证或前瞻性测试。因此，需要进一步研究来提高这些自动化系统的性能。
