通过基于机器学习的方法预测脑卒中后的日常生活活动。
Predicting post-stroke activities of daily living through a machine learning-based approach on initiating rehabilitation.
机构信息
Department of Physical Medicine & Rehabilitation, Chang Gung Memorial Hospital at Linkou, Taoyuan City, Taiwan.
Department of Information Management, Chang Gung University, Taoyuan City, Taiwan; Department of Neurology, Chang Gung Memorial Hospital at Taoyuan, Taoyuan City, Taiwan.
出版信息
Int J Med Inform. 2018 Mar;111:159-164. doi: 10.1016/j.ijmedinf.2018.01.002. Epub 2018 Jan 4.
OBJECTIVES
Prediction of activities of daily living (ADL) is crucial for optimized care of post-stroke patients. However, no suitably-validated and practical models are currently available in clinical practice.
METHODS
Participants of a Post-acute Care-Cerebrovascular Diseases (PAC-CVD) program from a reference hospital in Taiwan between 2014 and 2016 were enrolled in this study. Based on 15 rehabilitation assessments, machine learning (ML) methods, namely logistic regression (LR), support vector machine (SVM), and random forest (RF), were used to predict the Barthel index (BI) status at discharge. Furthermore, SVM and linear regression were used to predict the actual BI scores at discharge.
RESULTS
A total of 313 individuals (men: 208; women: 105) were enrolled in the study. All the classification models outperformed single assessments in predicting the BI statuses of the patients at discharge. The performance of the LR and RF algorithms was higher (area under ROC curve (AUC): 0.79) than that of SVM algorithm (AUC: 0.77). In addition, the mean absolute errors of both SVM and linear regression models in predicting the actual BI score at discharge were 9.86 and 9.95, respectively.
CONCLUSIONS
The proposed ML-based method provides a promising and practical computer-assisted decision making tool for predicting ADL in clinical practice.
目的
预测日常生活活动（ADL）对于优化脑卒中患者的护理至关重要。然而，目前在临床实践中尚无经过充分验证且实用的模型。
方法
本研究纳入了台湾一家参考医院的 2014 年至 2016 年期间参加 Post-acute Care-Cerebrovascular Diseases（PAC-CVD）计划的患者。基于 15 项康复评估，采用机器学习（ML）方法，即逻辑回归（LR）、支持向量机（SVM）和随机森林（RF），预测出院时的巴氏指数（BI）状态。此外，SVM 和线性回归用于预测出院时的实际 BI 评分。
结果
共纳入 313 名患者（男性 208 名，女性 105 名）。所有分类模型在预测患者出院时的 BI 状态方面均优于单项评估。LR 和 RF 算法的性能优于 SVM 算法（AUC：0.79 比 AUC：0.77）。此外，SVM 和线性回归模型预测出院时实际 BI 评分的平均绝对误差分别为 9.86 和 9.95。
结论
所提出的基于 ML 的方法为预测临床实践中的 ADL 提供了一种有前途且实用的计算机辅助决策工具。
Zotero 插件