arXiv cs.AI· Ivan Poddiakov, Ivan Kruzhilov, Galina Zubkova, Svetlana Erofeeva, Andrey Savchenko, Pavel Blinov·· 3 小时前AI 评分38
Breath-Dx：基于电子鼻呼吸检测疾病筛查的时间序列分类基准
Breath-Dx: A Time Series Classification Benchmark for Disease Screening with eNose
AI 导读
研究者发布 Breath-Dx，首个针对电子鼻呼气疾病筛查的时间序列分类基准，基于迄今最大的公开临床 eNose 数据集 S-OH，涵盖 1,234 名患者、九个诊断组，每人 17 通道多元时间序列。在考虑传感器漂移的时间划分验证下，10 种方法普遍出现 0.05-0.12 AUC 下降，部分肺部疾病最佳 ROC AUC 达 0.74-0.76。数据集、划分协议与代码已开源。
正文 · 原文
Abstract:Electronic nose (eNose) technology offers a portable, non-invasive route for disease screening via exhaled breath analysis. However, progress in the field is hindered by the lack of systematic benchmarks that compare machine learning methods under realistic conditions, particularly sensor drift, a known but rarely quantified failure mode. Most existing studies rely on small, private datasets with inconsistent protocols, rendering results non-comparable and slowing progress. We introduce Breath-Dx, the first comprehensive benchmark of time series classification methods for breath-based disease screening. Our work leverages the Scent of Health (S-OH) dataset, the largest public clinical eNose collection to date, comprising 1,234 patients across nine diagnostic groups, each providing a 17-channel multivariate time series with explicit temporal train/test splits that account for sensor drift. We systematically evaluate 10 methods spanning four families: feature-based tabular learners, convolution-based models, graph-based, and time series architectures. All methods degrade significantly under temporal validation (0.05-0.12 AUC drop compared to random cross-validation), confirming that drift embeds a strong temporal signal. Under this realistic evaluation, the best methods achieve ROC AUC of 0.74-0.76 for some lung conditions, though others remain near chance. Recurrent architectures show the most consistent performance across diseases, while specialized time series methods achieve the highest peak results. Demographic confounders matter: breath signals provide independent diagnostic value for some conditions but add little beyond age for others. We release the S-OH dataset, all temporal splits, evaluation protocols, and code to enable reproducible research and accelerate progress in clinical breathomics.
| Comments: | IEEE ICDM 2026 - Best Paper Runner-Up (Applied Track) |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.15348 [cs.LG] |
| (or arXiv:2611.15348v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.15348 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ivan Kruzhilov [view email]
[v1]
Wed, 11 Nov 2026 11:25:51 UTC (671 KB)
来源：arXiv cs.AI · arxiv.org