跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2608.25846 · v2

Why ML-based cough models do not generalize: a systematic cross-dataset evaluation for tuberculosis screening

首次提交 2026-08-26 22:22
版本更新 2026-11-18 00:04
雷达观测 2026-11-18 16:38
arXiv ↗PDF ↗

摘要

Cough acoustics are promising for non-invasive tuberculosis (TB) screening, yet whether machine learning (ML) models capture disease-related acoustics or artifacts of data collection remains unresolved. We evaluated the cross-dataset generalizability of classical ML and deep learning (DL) cough-based TB classifiers across three independent datasets. Despite moderate within-dataset performance (ROC-AUC up to 0.76±0.060.76 \pm 0.06), both pipelines fail to generalize, with external performance frequently below 0.6, indicating a possible limitation of the data. We further observed that audio representations are organized by recording device and dataset rather than TB status, predicted TB probability tracks country-level prevalence in CODA, and device mismatch degrades transfer while device-diverse training improves it. Additionally, a clinical-variable baseline generalizes more consistently (ROC-AUC 0.65−0.710.65-0.71), indicating acquisition-specific variability in acoustics is a stronger driver of poor generalizability. High within-dataset performance is not enough. External validation is essential before cough-based TB models are clinically ready.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-18 00:04 · 最新观测版本

Why ML-based cough models do not generalize: a systematic cross-dataset evaluation for tuberculosis screening

Cough acoustics are promising for non-invasive tuberculosis (TB) screening, yet whether machine learning (ML) models capture disease-related acoustics or artifacts of data collection remains unresolved. We evaluated the cross-dataset generalizability of classical ML and deep learning (DL) cough-based TB classifiers across three independent datasets. Despite moderate within-dataset performance (ROC-AUC up to 0.76±0.060.76 \pm 0.06), both pipelines fail to generalize, with external performance frequently below 0.6, indicating a possible limitation of the data. We further observed that audio representations are organized by recording device and dataset rather than TB status, predicted TB probability tracks country-level prevalence in CODA, and device mismatch degrades transfer while device-diverse training improves it. Additionally, a clinical-variable baseline generalizes more consistently (ROC-AUC 0.65−0.710.65-0.71), indicating acquisition-specific variability in acoustics is a stronger driver of poor generalizability. High within-dataset performance is not enough. External validation is essential before cough-based TB models are clinically ready.

查看此版本解读 →查看此版本原文 ↗