Department of Health Technology, Technical University of Denmark, Kongens Lyngby, Denmark.
Department of Health Technology, Technical University of Denmark, Kongens Lyngby, Denmark.
Comput Biol Med. 2022 Aug;147:105559. doi: 10.1016/j.compbiomed.2022.105559. Epub 2022 May 18.
Continuous monitoring of high-risk patients and early prediction of severe outcomes is crucial to prevent avoidable deaths. Current clinical monitoring is primarily based on intermittent observation of vital signs and the early warning scores (EWS). The drawback is lack of time series dynamics and correlations among vital signs. This study presents an approach to real-time outcome prediction based on machine learning from continuous recording of vital signs. Systolic blood pressure, diastolic blood pressure, heart rate, pulse rate, respiration rate and peripheral blood oxygen saturation were continuously acquired by wearable devices from 292 post-operative high-risk patients. The outcomes from serious complications were evaluated based on review of patients' medical record. The descriptive statistics of vital signs and patient demographic information were used as features. Four machine learning models K-Nearest-Neighbors (KNN), Decision Trees (DT), Random Forest (RF), and Boosted Ensemble (BE) were trained and tested. In static evaluation, all four models had comparable prediction performance to that of the state of the art. In dynamic evaluation, the models trained from the static evaluation were tested with continuous data. RF and BE obtained the lower false positive rate (FPR) of 0.073 and 0.055 on no-outcome patients respectively. The four models KNN, DT, RF and BE had area under receiver operating characteristic curve (AUROC) of 0.62, 0.64, 0.65 and 0.64 respectively on outcome patients. RF was found to be optimal model with lower FPR on no-outcome patients and a higher AUROC on outcome patients. These findings are encouraging and indicate that additional investigations must focus on validating performance in a clinical setting before deployment of the real-time outcome prediction.
连续监测高危患者并早期预测严重结局对于预防可避免的死亡至关重要。目前的临床监测主要基于对生命体征的间歇性观察和早期预警评分（EWS）。缺点是缺乏时间序列动态和生命体征之间的相关性。本研究提出了一种基于生命体征连续记录的机器学习实时预后预测方法。通过可穿戴设备连续采集 292 例术后高危患者的收缩压、舒张压、心率、脉搏率、呼吸频率和外周血氧饱和度。根据患者病历回顾评估严重并发症的结局。将生命体征和患者人口统计学信息的描述性统计数据用作特征。训练和测试了 K-最近邻（KNN）、决策树（DT）、随机森林（RF）和增强集成（BE）四种机器学习模型。在静态评估中，所有四个模型的预测性能都与最新技术相当。在动态评估中，使用连续数据测试了从静态评估中训练的模型。RF 和 BE 在无结果患者中分别获得了较低的假阳性率（FPR）0.073 和 0.055。KNN、DT、RF 和 BE 这四个模型在有结果的患者中，其受试者工作特征曲线下面积（AUROC）分别为 0.62、0.64、0.65 和 0.64。RF 在无结果患者中具有较低的 FPR 和较高的 AUROC，被认为是最佳模型。这些发现令人鼓舞，表明在部署实时预后预测之前，必须在临床环境中进一步验证性能。
