Author Affiliations: College of Information Science & Electronic Engineering (Messrs Lin, Lu, and Ma and Dr Cheng), Department of Neurology, Second Affiliated Hospital, School of Medicine (Ms Tian), and Department of Surgery, Zhejiang University Hospital (Ms Wu), and Department of Orthopedic Surgery, Second Affiliated Hospital, School of Medicine (Mr Hong and Drs Yan and Feng), Zhejiang University, Hangzhou, China.
Comput Inform Nurs. 2021 May 25;40(4):251-257. doi: 10.1097/CIN.0000000000000765.
Being bedridden is a frequent comorbid condition that leads to a series of complications in clinical practice. The present study aimed to predict bedridden duration of hospitalized patients based on EMR at admission by machine learning. The medical data of 4345 hospitalized patients who were bedridden for at least 24 hours after admission were retrospectively collected. After preprocessing of the data, features for modeling were selected by support vector machine recursive feature elimination. Thereafter, logistic regression, support vector machine, and extreme gradient boosting algorithms were adopted to predict the bedridden duration. The feasibility and efficacy of above models were evaluated by performance indicators. Our results demonstrated that the most important features related to bedridden duration were Charlson Comorbidity Index, age, bedridden duration before admission, mobility capability, and perceptual ability. The extreme gradient boosting algorithm showed the best performance (accuracy, 0.797; area under the curve, 0.841) when compared with support vector machine (accuracy, 0.771; area under the curve, 0.803) and logistic regression (accuracy, 0.765; area under the curve, 0.809) algorithms. Meanwhile, the extreme gradient boosting algorithm had a higher sensitivity (0.856), specificity (0.650), and F1 score (0.858) than that of support vector machine algorithm (0.843, 0.589, and 0.841) and logistic regression (0.852, 0.545, and 0.839), respectively. These findings indicate that machine learning based on EMRs at admission is a feasible avenue to predict the bedridden duration. The extreme gradient boosting algorithm shows great potential for further clinical application.
卧床是一种常见的合并症，会导致临床实践中的一系列并发症。本研究旨在通过机器学习，根据入院时的电子病历预测住院患者的卧床时间。回顾性收集了 4345 名卧床至少 24 小时的住院患者的医疗数据。对数据进行预处理后，通过支持向量机递归特征消除选择建模特征。然后，采用逻辑回归、支持向量机和极端梯度提升算法来预测卧床时间。通过性能指标评估上述模型的可行性和疗效。我们的研究结果表明，与卧床时间相关的最重要特征是 Charlson 合并症指数、年龄、入院前卧床时间、活动能力和感知能力。与支持向量机（准确率 0.771，曲线下面积 0.803）和逻辑回归（准确率 0.765，曲线下面积 0.809）算法相比，极端梯度提升算法表现出最佳性能（准确率 0.797，曲线下面积 0.841）。同时，极端梯度提升算法的敏感性（0.856）、特异性（0.650）和 F1 评分（0.858）均高于支持向量机算法（0.843、0.589 和 0.841）和逻辑回归算法（0.852、0.545 和 0.839）。这些发现表明，基于入院时电子病历的机器学习是预测卧床时间的一种可行方法。极端梯度提升算法在进一步的临床应用中具有很大的潜力。
