VIRDOCD : A VIRtual DOCtor to predict dengue fatality

Clinicians make routine diagnosis by scrutinizing patients' medical signs and symptoms, a skill popularly referred to as ‘Clinical Eye’. This evolves through trial-and-error improves with time. The success of the therapeutic regime relies largely on accuracy interpretation such sign-symptoms, analysing which clinician assesses severity illness. present study is an attempt propose complementary front mathematically modelling Eye’ VIRtual DOCtor, using statistical machine intelligence tools (SMI), analyse Dengue epidemic infected patients (100 case studies 11 weighted sign-symptoms). SMI in VIRDOCD reads data translates these into vector comprising multiple linear regression (MLR) coefficients predict infection grades dengue that clone clinician's experience-based assessment. Risk managed ANOVA, grade prediction from found higher (ca 75%) than conventional clinical practice 71.4%, mean profile assessed team 10 senior consultants). Free human errors capable deciphering even minute differences almost identical symptoms (to Clinical eye), uniquely individualized its decision-making ability. algorithm has been validated against Random Forest classification (RF, ca 63%), another regression-based classifier similar MLR can be trained supervised learning. We find MLR-based superior RF predicting morbidity. further extended other infections, COVID-19.