Cheligeer Cheligeer, Wu Guosong, Lee Seungwon, Pan Jie, Southern Danielle A, Martin Elliot A, Sapiro Natalie, Eastwood Cathy A, Quan Hude, Xu Yuan
Centre for Health Informatics, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada.
Provincial Research Data Services, Alberta Health Services, Calgary, AB, Canada.
JMIR Med Inform. 2024 Jan 30;12:e48995. doi: 10.2196/48995.
Inpatient falls are a substantial concern for health care providers and are associated with negative outcomes for patients. Automated detection of falls using machine learning (ML) algorithms may aid in improving patient safety and reducing the occurrence of falls.
This study aims to develop and evaluate an ML algorithm for inpatient fall detection using multidisciplinary progress record notes and a pretrained Bidirectional Encoder Representation from Transformers (BERT) language model.
A cohort of 4323 adult patients admitted to 3 acute care hospitals in Calgary, Alberta, Canada from 2016 to 2021 were randomly sampled. Trained reviewers determined falls from patient charts, which were linked to electronic medical records and administrative data. The BERT-based language model was pretrained on clinical notes, and a fall detection algorithm was developed based on a neural network binary classification architecture.
To address various use scenarios, we developed 3 different Alberta hospital notes-specific BERT models: a high sensitivity model (sensitivity 97.7, IQR 87.7-99.9), a high positive predictive value model (positive predictive value 85.7, IQR 57.2-98.2), and the high F-score model (F=64.4). Our proposed method outperformed 3 classical ML algorithms and an International Classification of Diseases code-based algorithm for fall detection, showing its potential for improved performance in diverse clinical settings.
The developed algorithm provides an automated and accurate method for inpatient fall detection using multidisciplinary progress record notes and a pretrained BERT language model. This method could be implemented in clinical practice to improve patient safety and reduce the occurrence of falls in hospitals.
住院患者跌倒问题是医疗服务提供者极为关注的问题，且与患者的不良后果相关。使用机器学习（ML）算法自动检测跌倒可能有助于提高患者安全并减少跌倒的发生。
本研究旨在开发并评估一种使用多学科病程记录和预训练的来自变换器的双向编码器表征（BERT）语言模型进行住院患者跌倒检测的ML算法。
对2016年至2021年期间入住加拿大艾伯塔省卡尔加里市3家急性护理医院的4323名成年患者进行随机抽样。经过培训的评审人员根据与电子病历和管理数据相关联的患者病历确定跌倒情况。基于BERT的语言模型在临床笔记上进行预训练，并基于神经网络二分类架构开发跌倒检测算法。
为满足各种使用场景，我们开发了3种不同的针对艾伯塔省医院笔记的特定BERT模型：一种高灵敏度模型（灵敏度97.7，四分位距87.7 - 99.9）、一种高阳性预测值模型（阳性预测值85.7，四分位距57.2 - 98.2）和高F值模型（F = 64.4）。我们提出的方法在跌倒检测方面优于3种经典ML算法和一种基于国际疾病分类代码的算法，显示出其在不同临床环境中提高性能的潜力。
所开发的算法提供了一种使用多学科病程记录和预训练的BERT语言模型进行住院患者跌倒检测的自动化且准确的方法。该方法可在临床实践中实施，以提高患者安全并减少医院内跌倒的发生。
