An interpretable machine learning model based on a quick pre-screening system enables accurate deterioration risk prediction for COVID-19

• Published in: Scientific reports Vol. 11; no. 1; pp. 23127 - 16
• Main Authors: Jia, Lijing, Wei, Zijian, Zhang, Heng, Wang, Jiaming, Jia, Ruiqi, Zhou, Manhong, Li, Xueyan, Zhang, Hankun, Chen, Xuedong, Yu, Zheyuan, Wang, Zhaohong, Li, Xiucheng, Li, Tingting, Liu, Xiangge, Liu, Pei, Chen, Wei, Li, Jing, He, Kunlun
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 30.11.2021; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1305; 631/114/2413; 692/499; 692/699/255; Adult; Cell number; Coronaviruses; COVID-19; Creatine; Creatine kinase; Globulins; Heart rate; Hematocrit; Humanities and Social Sciences; Humans; L-Lactate dehydrogenase; Lactic acid; Learning algorithms; Lymphocytes; Machine Learning; Magnesium; Middle Aged; multidisciplinary; Patients; Prothrombin; Risk factors; SARS-CoV-2; Science; Science (multidisciplinary); Specific gravity; Thromboplastin
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-021-02370-4

A high-performing interpretable model is proposed to predict the risk of deterioration in coronavirus disease 2019 (COVID-19) patients. The model was developed using a cohort of 3028 patients diagnosed with COVID-19 and exhibiting common clinical symptoms that were internally verified (AUC 0.8517, 95% CI 0.8433, 0.8601). A total of 15 high risk factors for deterioration and their approximate warning ranges were identified. This included prothrombin time (PT), prothrombin activity, lactate dehydrogenase, international normalized ratio, heart rate, body-mass index (BMI), D-dimer, creatine kinase, hematocrit, urine specific gravity, magnesium, globulin, activated partial thromboplastin time, lymphocyte count (L%), and platelet count. Four of these indicators (PT, heart rate, BMI, HCT) and comorbidities were selected for a streamlined combination of indicators to produce faster results. The resulting model showed good predictive performance (AUC 0.7941 95% CI 0.7926, 0.8151). A website for quick pre-screening online was also developed as part of the study.