BCoughBench: Benchmarking Respiratory Acoustic Foundation Models Under Body-Coupled Wearable Sensor Conditions

2026-06-23

AI Summary

This study addresses the lack of reliability validation for existing respiratory acoustic foundation models under body-coupled wearable conditions, as prior evaluations have been limited to smartphone recordings. The authors introduce BCoughBench, the first benchmark specifically designed for this setting, leveraging the EBEN framework to simulate five body-coupled sensor configurations. They systematically evaluate prominent models—including OPERA, HeAR, and M2D+Resp—across nine disease classification and three age regression tasks. Results reveal a consistent performance degradation under body-coupled conditions, with most models failing to meet clinical sensitivity thresholds for disease detection, though age regression remains robust. HeAR excels in demographic tasks, while M2D+Resp demonstrates superior performance in disease classification. This work fills a critical gap in wearable respiratory sound model evaluation and highlights the substantial impact of sensor placement on model efficacy.

Abstract

Respiratory acoustic foundation models (FMs) are benchmarked exclusively on smartphone recordings, yet clinical deployment increasingly targets body-coupled (BC) wearables whose sensors attenuate high-frequency content through tissue and bone, leaving FM reliability uncharacterised. We introduce BCoughBench, evaluating five FMs (OPERA-CT/CE/GT, HeAR, M2D+Resp) on nine classification tasks (AUROC, sensitivity at 95% specificity, Expected Calibration Error) and three age regression tasks (MAE vs. a mean-predictor baseline) across five EBEN-simulated BC sensor conditions on five labeled cough datasets. Mean AUROC declines from 0.785 (smartphone) to 0.689-0.723, degrading most under temple vibration pickup ($Δ$ = -0.096) and least under the soft in-ear ($Δ$ = -0.062). No FM meets the clinical sensitivity threshold (Se@Sp95 $\geq$ 0.20) on most disease tasks under any BC sensor. Sex classification on the CIDRZ cohort collapses (AUROC 0.954 to 0.596-0.628, $Δ$ = -0.341) while COVID detection is nearly unaffected ($Δ$ = -0.004). Age regression is robust, improving under the forehead accelerometer on CoughVID (MAE 9.61 to 8.97 yr); HeAR leads on regression and demographic tasks, M2D+Resp on disease and characteristic tasks. BCoughBench provides a reproducible framework for FM evaluation under wearable conditions.

Problem

• respiratory acoustic foundation models
• body-coupled wearables
• benchmarking
• sensor attenuation
• clinical deployment

Innovation

• body-coupled wearable
• respiratory acoustic foundation models
• benchmarking
• sensor-induced degradation
• BCoughBench