• Jocelyn S Zhu, Peilin Ge, Chunguo Jiang, Yong Zhang, Xiaoran Li, Zirun Zhao, Liming Zhang, and Tim Q Duong.
• Departments of Radiology, Renaissance School of Medicine Stony Brook University Stony Brook New York USA.
• J Am Coll Emerg Physicians Open. 2020 Jul 16.

Study ObjectiveThe large number of clinical variables associated with coronavirus disease 2019 (COVID-19) infection makes it challenging for frontline physicians to effectively triage COVID-19 patients during the pandemic. This study aimed to develop an efficient deep-learning artificial intelligence algorithm to identify top clinical variable predictors and derive a risk stratification score system to help clinicians triage COVID-19 patients.MethodsThis retrospective study consisted of 181 hospitalized patients with confirmed COVID-19 infection from January 29, 2020 to March 21, 2020 from a major hospital in Wuhan, China. The primary outcome was mortality. Demographics, comorbidities, vital signs, symptoms, and laboratory tests were collected at initial presentation, totaling 78 clinical variables. A deep-learning algorithm and a risk stratification score system were developed to predict mortality. Data were split into 85% training and 15% testing. Prediction performance were compared with those using COVID-19 severity score, CURB-65 score and pneumonia severity index (PSI).ResultsOf the 181 COVID-19 patients, 39 expired and 142 survived. Five top predictors of mortality were D-dimer, O2 Index, neutrophil:lymphocyte ratio, C-reactive protein, and lactate dehydrogenase. The top 5 predictors and the resultant risk score yielded, respectively, an area under curve (AUC) of 0.968 ([95% CI:0.87-1.0]) and 0.954 ([95% CI:0.80-0.99]) for the testing dataset. Our models outperformed COVID-19 severity score (AUC = 0.756), CURB-65 score (AUC = 0.671), and PSI (AUC = 0.838). The mortality rates for our risk stratification scores (0-5) were 0, 0, 6.7, 18.2, 67.7, and 83.3%, respectively.Conclusions And RelevanceDeep-learning prediction model and the resultant risk stratification score may prove useful in clinical decision-making under time-sensitive and resource-constrained environment.This article is protected by copyright. All rights reserved.This article is protected by copyright. All rights reserved.

5 keywords...

hide…