Predictive modeling of morbidity and mortality in COVID-19 hospitalized patients and its clinical implications.
Predictive modeling of morbidity and mortality in COVID-19 hospitalized patients and its clinical implications.
复制标题
DOI：
10.1101/2020.12.02.20235879
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Joshua M Wang;Wenke Liu;Xiaoshan Chen;M. McRae;J. McDevitt;D. Fenyö
中科院分区：
文献类型：
--
作者：
Joshua M Wang;Wenke Liu;Xiaoshan Chen;M. McRae;J. McDevitt;D. Fenyö
目的：对纽约大学朗格尼医院治疗的新冠肺炎阳性患者进行回顾性研究，以确定预测疾病严重程度的临床标志物，以帮助临床决策分诊，并提供更多关于疾病进展的生物学见解。材料和方法：从2020年1月到8月，在NYULH的3740名身份不明的患者的临床活动。模型在他们住院的不同部分根据临床数据进行培训，以预测三种临床结果：死亡、呼吸机或住进ICU。结果：根据最后24小时的临床数据训练的XGBoost模型在预测死亡率方面表现出色(AUC=0.92，特异度=86%，敏感度=85%)。呼吸频率是最重要的指标，其次是血氧饱和度和75岁以上。该模型预测死亡结局的效果在5天前延长，AUC=0.81，特异度=70%，敏感度=75%。当仅使用前24小时的临床数据时，死亡、呼吸机或ICU入院的AUC值分别为0.79、0.80和0.77。虽然呼吸频率和SpO2水平提供了最高的特征重要性，但包括糖尿病病史、年龄和体温在内的其他典型指标提供的收益最小。当结合实验室数据时，对死亡率的预测受益于血尿素氮(BUN)和乳酸脱氢酶(LDH)。预测发病率的特征包括乳酸脱氢酶、钙、血糖和C反应蛋白(CRP)。结论：这项工作总结了系统检查不同终点结局和不同住院时间点的各种特征的重要性的努力。
Objective: Retrospective study of COVID-19 positive patients treated at NYU Langone Health (NYULH) to identify clinical markers predictive of disease severity to assist in clinical decision triage and provide additional biological insights into disease progression. Materials and Methods: Clinical activity of 3740 de-identified patients at NYULH between January and August 2020. Models were trained on clinical data during different parts of their hospital stay to predict three clinical outcomes: deceased, ventilated, or admitted to ICU. Results: XGBoost model trained on clinical data from the final 24 hours excelled at predicting mortality (AUC=0.92, specificity=86% and sensitivity=85%). Respiration rate was the most important feature, followed by SpO2 and age 75+. Performance of this model to predict the deceased outcome extended 5 days prior with AUC=0.81, specificity=70%, sensitivity=75%. When only using clinical data from the first 24 hours, AUCs of 0.79, 0.80, and 0.77 were obtained for deceased, ventilated, or ICU admitted, respectively. Although respiration rate and SpO2 levels offered the highest feature importance, other canonical markers including diabetic history, age and temperature offered minimal gain. When lab values were incorporated, prediction of mortality benefited the most from blood urea nitrogen (BUN) and lactate dehydrogenase (LDH). Features predictive of morbidity included LDH, calcium, glucose, and C-reactive protein (CRP). Conclusion: Together this work summarizes efforts to systematically examine the importance of a wide range of features across different endpoint outcomes and at different hospitalization time points.