University of Tennessee, Knoxville, TN, USA.
Center for Biomedical Informatics, Department of Pediatrics, University of Tennessee Health, USA Science Center, Memphis, TN, USA.
Int J Med Inform. 2019 Feb;122:55-62. doi: 10.1016/j.ijmedinf.2018.12.002. Epub 2018 Dec 10.
Sepsis is a life-threatening condition with high mortality rates and expensive treatment costs. To improve short- and long-term outcomes, it is critical to detect at-risk sepsis patients at an early stage.
A data-set consisting of high-frequency physiological data from 1161 critically ill patients was analyzed. 377 patients had developed sepsis, and had data at least 3 h prior to the onset of sepsis. A random forest classifier was trained to discriminate between sepsis and non-sepsis patients in real-time using a total of 132 features extracted from a moving time-window. The model was trained on 80% of the patients and was tested on the remaining 20% of the patients, for two observational periods of lengths 3 and 6 h prior to onset.
The model that used continuous physiological data alone resulted in sensitivity and F1 score of up to 80% and 67% one hour before sepsis onset. On average, these models were able to predict sepsis 294.19 ± 6.50 min (5 h) before the onset.
The use of machine learning algorithms on continuous streams of physiological data can allow for early identification of at-risk patients in real-time with high accuracy.
脓毒症是一种危及生命的疾病，死亡率和治疗费用都很高。为了改善短期和长期预后，早期发现高危脓毒症患者至关重要。
分析了来自 1161 名危重病患者的高频生理数据数据集。377 名患者发生了脓毒症，并且在脓毒症发作前至少有 3 小时的数据。使用从移动时间窗口中提取的总共 132 个特征，使用随机森林分类器实时区分脓毒症患者和非脓毒症患者。该模型在 80%的患者上进行训练，并在其余 20%的患者上进行测试，观察时间为脓毒症发作前 3 小时和 6 小时。
仅使用连续生理数据的模型在脓毒症发作前一小时达到了 80%和 67%的最高敏感性和 F1 评分。这些模型平均能够在发病前 294.19±6.50 分钟（5 小时）预测脓毒症。
使用机器学习算法对连续的生理数据流进行分析，可以实时、高精度地识别高危患者。
