Machine learning insights concerning inflammatory and liver-related risk comorbidities in non-communicable and viral diseases

Table 2 Summary of the most repeated inputs of the machine learning models with the most repeated predictor outcomes for the four main inflammatory-related liver conditions

Inflammatory-related liver condition	Inputs	Most repeated predictors
FLD	Age, sex, blood biomarkers, and demographic, anthropometric, and clinical data	BMI, uric acid, TG, and ALT levels
Liver fibrosis	Age, sex, and CT images	Better diagnosis compared to classical methods like APRI and FIB-4 indexes
Virus-induced hepatitis	Age, sex, blood biomarkers, and demographic, anthropometric, and clinical data	AST, PLT levels, APRI index, and age
COVID-19	Age, sex, blood biomarkers, CT images, and demographic, anthropometric, and clinical data	Age, BMI, CT images, oxygen rate, AST, and ALT levels

FLD: Fatty liver disease; CT: Computed tomography; BMI: Body mass index; TG: Triglycerides; ALT: Alanine transaminase; AST: Aspartate transaminase; PLT: Platelet; APRI: Aspartate transaminase/platelet ratio index; COVID-19: Coronavirus disease 2019; FIB-4: Fibrosis-4.