Reducing Risk and Uncertainty of Deep Neural Networks on Diagnosing COVID-19 Infection

Abstract

Effective and reliable screening of patients via Computer-Aided Diagnosis can play a crucial part in the battle against COVID-19. Most of the existing works focus on developing sophisticated methods yielding high detection performance, yet not addressing the issue of predictive uncertainty. In this work, we introduce uncertainty estimation to detect confusing cases for expert referral to address the unreliability of stateof-the-art (SOTA) DNNs on COVID-19 detection. To the best of our knowledge, we are the first to address this issue on the COVID-19 detection problem. In this work, we investigate a number of SOTA uncertainty estimation methods on publicly available COVID dataset and present our experimental findings. In collaboration with medical professionals, we further validate the results to ensure the viability of the best performing method in clinical practice.

Individual Factors Associated With COVID-19 Infection: A Machine Learning Study

“…In particular, feature selection approaches to risk assessment of infectious diseases have been successfully applied in the case of tuberculosis ( 120 ), zika ( 121 ), dengue ( 122 ), clostridium difficile ( 123 ), HIV ( 124 ), and even COVID-19 ( 125 , 126 ). These previous efforts have shown the advantages of these approaches as reliable tools for epidemic outbreak prevention and containment.…”