机器学习咳嗽模型难泛化，跨数据集表现差，需外部验证才可临床使用。
Why ML-based cough models do not generalize: a systematic cross-dataset evaluation for tuberculosis screening
- 用三组独立数据集测试咳嗽分类模型，发现跨域性能普遍低于0.6。
- 音频特征按设备和数据集分组，而非疾病状态，暗示模型学的是采集偏差。
- 设备多样性训练能提升泛化能力，临床变量基线更稳定，适合实际应用。
咳嗽声学有望用于无创结核病（TB）筛查，但机器学习模型是否捕捉到疾病相关声学特征，还是仅学习了数据采集的噪声尚不明确。本研究在三个独立数据集上评估了经典机器学习与深度学习咳嗽基TB分类器的跨数据集泛化能力。尽管在单个数据集上表现中等（ROC-AUC最高达0.755±0.056），但外部数据集表现通常低于0.6，表明可能存在数据局限性。进一步发现，音频表征按录音设备和数据集组织，而非TB状态；预测的TB概率与CODA数据集中国家水平的患病率相关；设备不匹配会降低迁移性能，而设备多样化的训练则可提升泛化能力。此外，仅使用临床变量的基线模型泛化更稳定（ROC-AUC 0.655–0.711），说明采集特定变异比人群差异是导致泛化失败的主要原因。高内部性能不足以保证临床可用性，外部验证必不可少。
原文摘要 · Abstract (English)
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 $0.755 \pm 0.056$), both pipelines fail to generalize, with external performance frequently below 0.6, indicating a possible limitation of the data. We further observed 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 $0.655 - 0.711$), indicating acquisition-specific variability is a stronger driver of poor generalizability than population shift. High within-dataset performance is not enough. External validation is essential before cough-based TB models are clinically ready.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。