COVID-19 Outcome Prediction by Integrating Clinical and Metabolic Data using Machine Learning Algorithms.

Background: The coronavirus disease (COVID-19) is an infectious disease caused by the SARS-CoV-2 virus and is responsible for nearly 6 million deaths worldwide in the past 2 years. Machine learning (ML) models could help physicians in identifying high-risk individuals. Objectives: To study the use of ML models for COVID-19 prediction outcomes using clinical data and a combination of clinical and metabolic data, measured in a metabolomics facility from a public university. Methods: A total of 154 patients were included in the study. "Basic profile" was considered with clinical and demographic variables (33 variables), whereas in the "extended profile," metabolomic and immunological variables were also considered (156 characteristics). A selection of features was carried out for each of the profiles with a genetic algorithm (GA) and random forest models were trained and tested to predict each of the stages of COVID-19. Results: The model based on extended profile was more useful in early stages of the disease. Models based on clinical data were preferred for predicting severe and critical illness and death. ML detected trimethylamine N-oxide, lipid mediators, and neutrophil/lymphocyte ratio as important variables. Conclusions: ML and GAs provided adequate models to predict COVID-19 outcomes in patients with different severity grades.

COVID-19 Outcome Prediction by Integrating Clinical and Metabolic Data using Machine Learning Algorithms

ABSTRACT Background: The coronavirus disease (COVID-19) is an infectious disease caused by the SARS-CoV-2 virus and is responsible for nearly 6 million deaths worldwide in the past 2 years. Machine learning (ML) models could help physicians in identifying high-risk individuals. Objectives: To study the use of ML models for COVID-19 prediction outcomes using clinical data and a combination of clinical and metabolic data, measured in a metabolomics facility from a public university. Methods: A total of 154 patients were included in the study. "Basic profile" was considered with clinical and demographic variables (33 variables), whereas in the "extended profile," metabolomic and immunological variables were also considered (156 characteristics). A selection of features was carried out for each of the profiles with a genetic algorithm (GA) and random forest models were trained and tested to predict each of the stages of COVID-19. Results: The model based on extended profile was more useful in early stages of the disease. Models based on clinical data were preferred for predicting severe and critical illness and death. ML detected trimethylamine N-oxide, lipid mediators, and neutrophil/lymphocyte ratio as important variables. Conclusion: ML and GAs provided adequate models to predict COVID-19 outcomes in patients with different severity grades.

Glycerophospholipid Metabolism Alterations in Patients with Type 2 Diabetes Mellitus and Tuberculosis Comorbidity.

Type-2 Diabetes (T2D) is a predisposing cause for developing tuberculosis (TB) in low- and middle-income countries. TB-T2D comorbidity worsens clinical control and prognosis of the affected individuals. The underlying metabolic alterations for this infectious-metabolic disease are still largely unknown. Possible mediators of the increased susceptibility to TB in diabetic patients are lipids levels, which are altered in individuals with T2D. To evaluate the modulation of glycerophospholipids in patients with TB-T2D, an untargeted lipidomic approach was developed by means of ultra-performance liquid chromatography (UPLC) coupled to electrospray ionization/quadrupole time-of-flight mass spectrometry (ESI-QToF). In addition, tandem mass spectrometry was performed to determine the identity of the differentially expressed metabolites. We found that TB infected individuals with or without T2D share a common glycerophospholipid profile characterized by a decrease in phosphatidylcholines. A total of 14 glycerophospholipids were differentially deregulated in TB and TB-T2D patients and could potentially be considered biomarkers. It is necessary to further validate these identified lipids as biomarkers, focusing on the anticipate diagnosis for TB development in T2D predisposed individuals.