Value of Laboratory Tests in COVID-19 Hospitalized Patients for Clinical Decision-makers: A Predictive Model, Using Data Mining Approach

Background: Reports, mostly from high-income countries, have shown a wide range of symptoms, clinical profile, and outcomes for patients diagnosed with COVID-19. However, little is known about these issues in developing countries. This research used medical records 15 hospitals Tehran, the capital city Iran, to assess predictors in-hospital mortality Methods: The required information was extracted patients' records, including age, gender, laboratory data (complete blood count, serum electrolytes, liver, renal, muscle injury tests) at admission, outcome (yes/no) 4,542 adult confirmed logistic regression (measured as adjusted odds ratio [aOR]) Chi-square automatic interaction detector classify high-risk different age groups decision tree model. Two models were developed through machine learning approach. Results: Overall, 822 (18.09%) cases passed away hospital. Mortality risk increased 4.33% aged 18-40 years old 40.96% those 80+ old. After adjusting covariates, (aOR 1.62 7.05 vs. old), high aspartate transaminase 1.64 3.21), alkaline phosphatase (aOR=2.17), low sodium (aOR=1.31), level (aOR=5.05), potassium (aOR=2.41), calcium (aOR=2.31), creatine phosphokinase (aOR=2.21 2.24), creatinine (aOR=3.43) significantly associated mortality. Conclusion: Based on results our study, rate among patients, particularly older who had liver renal dysfunctions, injury, electrolyte imbalance admission. Triage special care can improve outcomes.