Audio-based AI classifiers show no evidence of improved COVID-19 screening over simple symptoms checkers

TL;DR

This large-scale study finds that audio-based AI classifiers for COVID-19 detection do not outperform simple symptom checkers when confounding factors are accounted for, questioning their practical utility.

Contribution

The study provides a comprehensive evaluation of audio-based COVID-19 classifiers using a large dataset and highlights their limited effectiveness compared to symptom-based methods.

Findings

Audio classifiers perform well unadjusted but weaken after confounder matching.

Symptom-based scores outperform audio classifiers in practical utility.

Large dataset of 67,842 individuals analyzed for COVID-19 detection.

Abstract

Recent work has reported that AI classifiers trained on audio recordings can accurately predict severe acute respiratory syndrome coronavirus 2 (SARSCoV2) infection status. Here, we undertake a large scale study of audio-based deep learning classifiers, as part of the UK governments pandemic response. We collect and analyse a dataset of audio recordings from 67,842 individuals with linked metadata, including reverse transcription polymerase chain reaction (PCR) test outcomes, of whom 23,514 tested positive for SARS CoV 2. Subjects were recruited via the UK governments National Health Service Test-and-Trace programme and the REal-time Assessment of Community Transmission (REACT) randomised surveillance survey. In an unadjusted analysis of our dataset AI classifiers predict SARS-CoV-2 infection status with high accuracy (Receiver Operating Characteristic Area Under the Curve (ROCAUC) 0.846 [0.838, 0.854]) consistent with the findings of previous studies. However, after matching on measured confounders, such as age, gender, and self reported symptoms, our classifiers performance is much weaker (ROC-AUC 0.619 [0.594, 0.644]). Upon quantifying the utility of audio based classifiers in practical settings, we find them to be outperformed by simple predictive scores based on user reported symptoms.