Department of Healthcare Quality, E-Da Hospital, Kaohsiung 82445, Taiwan.
Department of Healthcare Administration, I-Shou University, Kaohsiung 82445, Taiwan.
J Healthc Eng. 2022 Aug 1;2022:3100618. doi: 10.1155/2022/3100618. eCollection 2022.
An injurious fall is one of the main indicators of care quality in healthcare facilities. Despite several fall screen tools being widely used to evaluate a patient's fall risk, they are frequently unable to reveal the severity level of patient falls. The purpose of this study is to build a practical system useful to predict the severity level of in-hospital falls. This practice is done in order to better allocate limited healthcare resources and to improve overall patient safety.
Four hundred and forty-six patients who experienced fall events at a large Taiwanese hospital were referenced. Eight predictors were used to ascertain the severity of patient falls solely based on the above study population. Multinomial logistic regression, Naïve Bayes, random forest, support vector machine, eXtreme gradient boosting, deep learning, and ensemble learning were adopted to establish predictive models. Accuracy, F1 score, precision, and recall were utilized to assess the models' performance.
Compared to other learners, random forest exhibited satisfying predictive performance in terms of all metrics (accuracy: 0.844, F1 score: 0.850, precision: 0.839, and recall: 0.875 for the test dataset), and it was adopted as the base learner for a severity-level predictive system which is web-based. Furthermore, age, ability of independent activity, patient sources, use of assistive devices, and fall history within the past 12 months were deemed the top five important risk factors for evaluating fall severity.
The application of machine learning techniques for predicting the severity level of patient falls may result in some benefits to monitor fall severity and to better allocate limited healthcare resources.
伤害性跌倒（injurious fall）是医疗保健设施护理质量的主要指标之一。尽管有几种跌倒筛查工具被广泛用于评估患者的跌倒风险，但它们常常无法揭示患者跌倒的严重程度。本研究旨在构建一个实用的系统，用于预测住院患者跌倒的严重程度。这样做是为了更好地分配有限的医疗资源，提高整体患者安全。
参考了一家大型台湾医院发生跌倒事件的 446 名患者。仅基于上述研究人群，使用 8 个预测因素来确定患者跌倒的严重程度。采用多项逻辑回归、朴素贝叶斯、随机森林、支持向量机、极端梯度提升、深度学习和集成学习来建立预测模型。采用准确性、F1 得分、精度和召回率来评估模型的性能。
与其他学习者相比，随机森林在所有指标上（测试数据集的准确性：0.844、F1 得分：0.850、精度：0.839、召回率：0.875）表现出令人满意的预测性能，被选为基于 Web 的严重程度预测系统的基础学习者。此外，年龄、独立活动能力、患者来源、辅助设备使用情况以及过去 12 个月内的跌倒史被认为是评估跌倒严重程度的五个最重要的风险因素。
应用机器学习技术预测患者跌倒的严重程度可能有助于监测跌倒的严重程度，并更好地分配有限的医疗资源。
