An Early Warning Tool for Predicting Mortality Risk of COVID-19 Patients Using Machine Learning

COVID-19 pandemic has created an extreme pressure on the global healthcare services. Fast, reliable and early clinical assessment of the severity of the disease can help in allocating and prioritizing resources to reduce mortality. In order to study the important blood biomarkers for predicting disease mortality, a retrospective study was conducted on 375 COVID-19 positive patients admitted to Tongji Hospital (China) from January 10 to February 18, 2020. Demographic and clinical characteristics, and patient outcomes were investigated using machine learning tools to identify key biomarkers to predict the mortality of individual patient. A nomogram was developed for predicting the mortality risk among COVID-19 patients. Lactate dehydrogenase, neutrophils (%), lymphocyte (%), high sensitive C-reactive protein, and age - acquired at hospital admission were identified as key predictors of death by multi-tree XGBoost model. The area under curve (AUC) of the nomogram for the derivation and validation cohort were 0.961 and 0.991, respectively. An integrated score (LNLCA) was calculated with the corresponding death probability. COVID-19 patients were divided into three subgroups: low-, moderate- and high-risk groups using LNLCA cut-off values of 10.4 and 12.65 with the death probability less than 5%, 5% to 50%, and above 50%, respectively. The prognostic model, nomogram and LNLCA score can help in early detection of high mortality risk of COVID-19 patients, which will help doctors to improve the management of patient stratification.

[1]  ACP Risk Grade: A Simple Mortality Index for Patients with Confirmed or Suspected Severe Acute Respiratory Syndrome Coronavirus 2 Disease (COVID-19) During the Early Stage of Outbreak in Wuhan, China , 2020 .

[2]  Q. Fan,et al.  D‐dimer levels on admission to predict in‐hospital mortality in patients with Covid‐19 , 2020, Journal of Thrombosis and Haemostasis.

[3]  Rui Song,et al.  Neutrophil-to-Lymphocyte Ratio Predicts Severe Illness Patients with 2019 Novel Coronavirus in the Early Stage , 2020, medRxiv.

[4]  W. Liang,et al.  Risk Factors of Fatal Outcome in Hospitalized Subjects With Coronavirus Disease 2019 From a Nationwide Analysis in China , 2020, Chest.

[5]  Ghee Chee Phua,et al.  Rapid Progression to Acute Respiratory Distress Syndrome: Review of Current Understanding of Critical Illness from COVID-19 Infection. , 2020, Annals of the Academy of Medicine, Singapore.

[6]  S. Doi,et al.  Validation of the Kuwait Progression Indicator Score for predicting progression of severity in COVID19 , 2020, medRxiv.

[7]  Jian Sun,et al.  ACP risk grade: a simple mortality index for patients with confirmed or suspected severe acute respiratory syndrome coronavirus 2 disease (COVID-19) during the early stage of outbreak in Wuhan, China , 2020, medRxiv.

[8]  Eva L. H. Tsui,et al.  Prognostication in severe acute respiratory syndrome: A retrospective time‐course analysis of 1312 laboratory‐confirmed patients in Hong Kong , 2007, Respirology.

[9]  T. Kishaba,et al.  Staging of Acute Exacerbation in Patients with Idiopathic Pulmonary Fibrosis , 2014, Lung.

[10]  Arun Ross,et al.  Score normalization in multimodal biometric systems , 2005, Pattern Recognit..

[11]  S. Cessie,et al.  Ridge Estimators in Logistic Regression , 1992 .

[12]  Zunyou Wu,et al.  Characteristics of and Important Lessons From the Coronavirus Disease 2019 (COVID-19) Outbreak in China: Summary of a Report of 72 314 Cases From the Chinese Center for Disease Control and Prevention. , 2020, JAMA.

[13]  Li Yan,et al.  A machine learning-based model for survival prediction in patients with severe COVID-19 infection , 2020, medRxiv.

[14]  Centers for Disease Control and Prevention CDC COVID-19 Response Team.  Severe Outcomes Among Patients with Coronavirus Disease 2019 (COVID-19) — United States, February 12–March 16, 2020 , 2020, MMWR. Morbidity and mortality weekly report.

[15]  L. Mombaerts,et al.  An interpretable mortality prediction model for COVID-19 patients , 2020, Nature Machine Intelligence.

[16]  Wei Wang,et al.  Comorbidity and its impact on 1590 patients with COVID-19 in China: a nationwide analysis , 2020, European Respiratory Journal.

[17]  C. Ki,et al.  Predictive factors for pneumonia development and progression to respiratory failure in MERS-CoV infected patients , 2016, Journal of Infection.

[18]  G. Grunkemeier,et al.  Understanding logistic regression analysis in clinical reports: an introduction. , 2003, The Annals of thoracic surgery.

[19]  ANDC: an early warning score to predict mortality risk for patients with Coronavirus Disease 2019 , 2020, Journal of translational medicine.

[20]  Jeffrey D Sachs,et al.  Projecting hospital utilization during the COVID-19 outbreaks in the United States , 2020, Proceedings of the National Academy of Sciences.

[21]  O. Çolak,et al.  High sensitive C-reactive protein: a new marker for urinary tract infection, VUR and renal scar. , 2013, European review for medical and pharmacological sciences.

[22]  Jian-feng Xie,et al.  Development and external validation of a prognostic multivariable model on admission for hospitalized patients with COVID-19 , 2020, medRxiv.

[23]  G. Chowell,et al.  Estimating the asymptomatic proportion of coronavirus disease 2019 (COVID-19) cases on board the Diamond Princess cruise ship, Yokohama, Japan, 2020 , 2020, Euro surveillance : bulletin Europeen sur les maladies transmissibles = European communicable disease bulletin.

[24]  S. Roush.  National Center for Immunization and Respiratory Diseases (NCIRD) Support of CDC Surveillance Strategy and NNDSS Modernization Initiative (NMI): Data Harmonization , 2017 .

[25]  K. Yuen,et al.  Clinical Characteristics of Coronavirus Disease 2019 in China , 2020, The New England journal of medicine.

[26]  Stef van Buuren,et al.  MICE: Multivariate Imputation by Chained Equations in R , 2011 .

[27]  J. Xiang,et al.  Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study , 2020, The Lancet.

[28]  Nan-shan Zhong,et al.  Cardiovascular comorbidity and its impact on patients with COVID-19 , 2020, European Respiratory Journal.

[29]  Marcela Perrone-Bertolotti,et al.  Machine learning–XGBoost analysis of language networks to classify patients with epilepsy , 2017, Brain Informatics.

[30]  Amit Acharya,et al.  MICE vs PPCA: Missing data imputation in healthcare , 2019, Informatics in Medicine Unlocked.

[31]  S. Kalimuddin,et al.  Rapid Progression to Acute Respiratory Distress Syndrome: Review of Current Understanding of Critical Illness from Coronavirus Disease 2019 (COVID-19) Infection , 2020 .

[32]  Mengji Lu,et al.  ANDC: an early warning score to predict mortality risk for patients with Coronavirus Disease 2019 , 2020, Journal of translational medicine.

[33]  Hengcheng Zhu,et al.  Clinical characteristics of 82 death cases with COVID-19 , 2020, medRxiv.

[34]  Giacomo Grasselli,et al.  Critical Care Utilization for the COVID-19 Outbreak in Lombardy, Italy: Early Experience and Forecast During an Emergency Response. , 2020, JAMA.

[35]  Alexander Zlotnik,et al.  A General-purpose Nomogram Generator for Predictive Logistic Regression Models , 2015 .

[36]  Xueyuan Li,et al.  Dynamic changes and diagnostic and prognostic significance of serum PCT, hs-CRP and s-100 protein in central nervous system infection , 2018, Experimental and therapeutic medicine.

[37]  R. Pranata,et al.  Lymphopenia in severe coronavirus disease-2019 (COVID-19): systematic review and meta-analysis , 2020, Journal of Intensive Care.

[38]  Yuxiao Song,et al.  Clinical characteristics of 82 cases of death from COVID-19 , 2020, PloS one.

[39]  J. McDevitt,et al.  Clinical Decision Support Tool and Rapid Point-of-Care Platform for Determining Disease Severity in Patients with COVID-19 , 2020, medRxiv.

[40]  Y. Hu,et al.  Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China , 2020, The Lancet.

[41]  A. Westendorf,et al.  An increased alveolar CD4 + CD25 + Foxp3 + T-regulatory cell ratio in acute respiratory distress syndrome is associated with increased 30-day mortality , 2013, Intensive Care Medicine.

[42]  Yan Zhao,et al.  Clinical Characteristics of 138 Hospitalized Patients With 2019 Novel Coronavirus-Infected Pneumonia in Wuhan, China. , 2020, JAMA.

[43]  Han Zhang,et al.  Gene Expression Value Prediction Based on XGBoost Algorithm , 2019, Front. Genet..

[44]  Z. Memish,et al.  Epidemiological, demographic, and clinical characteristics of 47 cases of Middle East respiratory syndrome coronavirus disease from Saudi Arabia: a descriptive study , 2013, The Lancet Infectious Diseases.

[45]  Zhaofeng Chen,et al.  Prevalence of comorbidities and its effects in patients infected with SARS-CoV-2: a systematic review and meta-analysis , 2020, International Journal of Infectious Diseases.