Vironix: remote screening, detection, and triage of viral respiratory illness via cloud-enabled, machine-learned APIs

Abstract

<b>Background:</b> Covid-19&nbsp;has delivered a devastating health challenge worldwide with more than 107M confirmed cases and 2.3M deaths (as of February 2021). The need for personalized, remote care tools that facilitate early detection and triage of viral illness has never been greater. To address this gap, we developed an institutional software, Vironix, that uses machine-learned (ML) prediction models to enable real-time risk stratification and decision support for return-to-work initiatives. <b>Objectives:</b> To develop and validate an ML, early detection and triage application that facilitates early intervention on clinically relevant health deterioration among those at-risk of or diagnosed with&nbsp;Covid-19 <b>Methods:</b> ML models were trained and validated using clinical characteristic data from East Asia, Western Europe, and USA. Algorithms take an input of symptom, profile, biometric, and exposure data and return an assessment of disease severity. The Vironix web app was deployed among 11 participants in a small business commercial pilot for member self-screening. Members conducted daily health assessments and received personalized decision support while company managers received work-from-home recommendations and compliant symptom monitoring without&nbsp;seeing&nbsp;member health data. <b>Results:</b> ML predictions showed 87.6% accuracy, 85.5% sensitivity, and 87.8% specificity in identifying severe Covid-19 presentations in an out-of-sample validation set of 5,000 patient cases. After 4-months pilot use, Vironix issued 14 stay-at-home and 10 healthcare escalation recommendations while maintaining 30-day and 7-day user retentions of 66% and 72%, greatly exceeding&nbsp;normal industry adoption rates.