Department of Medicine, Division of Hospital Medicine, Thomas Jefferson University, Philadelphia, PA, USA.
Department of Surgery, Thomas Jefferson University, Philadelphia, PA, USA.
Am J Med Sci. 2021 Oct;362(4):355-362. doi: 10.1016/j.amjms.2021.04.001. Epub 2021 May 23.
Coronavirus disease 2019 (COVID-19) carries high morbidity and mortality globally. Identification of patients at risk for clinical deterioration upon presentation would aid in triaging, prognostication, and allocation of resources and experimental treatments.
Can we develop and validate a web-based risk prediction model for identification of patients who may develop severe COVID-19, defined as intensive care unit (ICU) admission, mechanical ventilation, and/or death?
This retrospective cohort study reviewed 415 patients admitted to a large urban academic medical center and community hospitals. Covariates included demographic, clinical, and laboratory data. The independent association of predictors with severe COVID-19 was determined using multivariable logistic regression. A derivation cohort (n=311, 75%) was used to develop the prediction models. The models were tested by a validation cohort (n=104, 25%).
The median age was 66 years (Interquartile range [IQR] 54-77) and the majority were male (55%) and non-White (65.8%). The 14-day severe COVID-19 rate was 39.3%; 31.7% required ICU, 24.6% mechanical ventilation, and 21.2% died. Machine learning algorithms and clinical judgment were used to improve model performance and clinical utility, resulting in the selection of eight predictors: age, sex, dyspnea, diabetes mellitus, troponin, C-reactive protein, D-dimer, and aspartate aminotransferase. The discriminative ability was excellent for both the severe COVID-19 (training area under the curve [AUC]=0.82, validation AUC=0.82) and mortality (training AUC= 0.85, validation AUC=0.81) models. These models were incorporated into a mobile-friendly website.
This web-based risk prediction model can be used at the bedside for prediction of severe COVID-19 using data mostly available at the time of presentation.
2019 年冠状病毒病（COVID-19）在全球范围内具有较高的发病率和死亡率。在就诊时识别出有临床恶化风险的患者，有助于分诊、预后判断以及资源和实验性治疗的分配。
我们能否开发和验证一个基于网络的风险预测模型，以识别可能发展为严重 COVID-19 的患者，严重 COVID-19 的定义为入住重症监护病房（ICU）、需要机械通气和/或死亡？
本回顾性队列研究纳入了一家大型城市学术医疗中心和社区医院的 415 名住院患者。协变量包括人口统计学、临床和实验室数据。使用多变量逻辑回归确定预测因子与严重 COVID-19 的独立关联。使用一个包含 311 名患者（75%）的推导队列来开发预测模型。使用一个包含 104 名患者（25%）的验证队列来检验模型。
中位年龄为 66 岁（四分位距 [IQR] 54-77），大多数患者为男性（55%）和非白人（65.8%）。14 天内严重 COVID-19 的发生率为 39.3%；31.7%需要入住 ICU，24.6%需要机械通气，21.2%死亡。机器学习算法和临床判断被用于提高模型性能和临床实用性，最终选择了 8 个预测因子：年龄、性别、呼吸困难、糖尿病、肌钙蛋白、C 反应蛋白、D-二聚体和天冬氨酸氨基转移酶。严重 COVID-19（训练区的曲线下面积 [AUC] = 0.82，验证 AUC = 0.82）和死亡率（训练 AUC = 0.85，验证 AUC = 0.81）模型的判别能力均非常出色。这些模型被整合到一个便于移动使用的网站中。
该基于网络的风险预测模型可用于床边预测严重 COVID-19，使用的是就诊时大多数可获得的数据。
