Yun Kyongsik, Oh Jihoon, Hong Tae Ho, Kim Eun Young
Computation and Neural Systems, California Institute of Technology, Pasadena, CA, United States.
Department of Psychiatry, College of Medicine, Seoul St. Mary's Hospital, The Catholic University of Korea, Seoul, South Korea.
Front Med (Lausanne). 2021 Mar 31;8:621861. doi: 10.3389/fmed.2021.621861. eCollection 2021.
Predicting prognosis of in-hospital patients is critical. However, it is challenging to accurately predict the life and death of certain patients at certain period. To determine whether machine learning algorithms could predict in-hospital death of critically ill patients with considerable accuracy and identify factors contributing to the prediction power. Using medical data of 1,384 patients admitted to the Surgical Intensive Care Unit (SICU) of our institution, we investigated whether machine learning algorithms could predict in-hospital death using demographic, laboratory, and other disease-related variables, and compared predictions using three different algorithmic methods. The outcome measurement was the incidence of unexpected postoperative mortality which was defined as mortality without pre-existing not-for-resuscitation order that occurred within 30 days of the surgery or within the same hospital stay as the surgery. Machine learning algorithms trained with 43 variables successfully classified dead and live patients with very high accuracy. Most notably, the decision tree showed the higher classification results (Area Under the Receiver Operating Curve, AUC = 0.96) than the neural network classifier (AUC = 0.80). Further analysis provided the insight that serum albumin concentration, total prenatal nutritional intake, and peak dose of dopamine drug played an important role in predicting the mortality of SICU patients. Our results suggest that machine learning algorithms, especially the decision tree method, can provide information on structured and explainable decision flow and accurately predict hospital mortality in SICU hospitalized patients.
预测住院患者的预后至关重要。然而，准确预测某些患者在特定时期内的生死具有挑战性。为了确定机器学习算法是否能够相当准确地预测重症患者的院内死亡，并识别有助于预测能力的因素。我们利用本院外科重症监护病房（SICU）收治的1384例患者的医疗数据，研究机器学习算法能否使用人口统计学、实验室检查及其他疾病相关变量预测院内死亡，并比较三种不同算法方法的预测结果。结局指标是意外术后死亡率，其定义为在手术30天内或与手术在同一住院期间发生的、无预先存在的不予复苏医嘱的死亡。用43个变量训练的机器学习算法成功地以非常高的准确率对死亡和存活患者进行了分类。最值得注意的是，决策树显示出比神经网络分类器更高的分类结果（受试者操作特征曲线下面积，AUC = 0.96）（AUC = 0.80）。进一步分析表明，血清白蛋白浓度、产前总营养摄入量和多巴胺药物峰值剂量在预测SICU患者死亡率方面发挥了重要作用。我们的结果表明，机器学习算法，尤其是决策树方法，可以提供有关结构化且可解释的决策流程的信息，并准确预测SICU住院患者的医院死亡率。
