Machine Learning Approaches to Identify Patient Comorbidities and Symptoms That Increased Risk of Mortality in COVID-19

Background: Providing appropriate care for people suffering from COVID-19, the disease caused by pandemic SARS-CoV-2 virus is a significant global challenge. Many individuals who become infected have pre-existing conditions that may interact with COVID-19 to increase symptom severity and mortality risk. patient comorbidities are likely be informative about individual risk of severe illness mortality. Accurately determining how associated symptoms would thus greatly assist in planning provision. Methods: To assess interaction we performed meta-analysis published literature, machine learning predictive analysis using an aggregated dataset. Results: Our identified chronic obstructive pulmonary (COPD), cerebrovascular (CEVD), cardiovascular (CVD), type 2 diabetes, malignancy, hypertension as most significantly current literature. Machine classification novel cohort data similarly found COPD, CVD, CKD, malignancy hypertension, well asthma, features classifying those deceased versus survived COVID-19. While age gender were predictor mortality, terms symptom-comorbidity combinations, it was observed Pneumonia-Hypertension, Pneumonia-Diabetes Acute Respiratory Distress Syndrome (ARDS)-Hypertension showed effects on Conclusions: These results highlight cohorts at related morbidity which implications prioritization hospital resources.