Breath-Dx:首个用于疾病筛查的电子鼻时间序列分类基准
Breath-Dx: A Time Series Classification Benchmark for Disease Screening with eNose
Breath-Dx 是首个针对基于电子鼻的疾病筛查引入时间序列分类基准,使用 S-O-H 数据集(1,234 名患者、9 类诊断组、17 通道多变量时间序列)评估 10 种方法(特征表模型)。
Published on Nov 11
Authors:
,
,
,
Abstract
A comprehensive benchmark evaluates time-series classification methods on a large clinical breath dataset under realistic temporal splits, showing that sensor drift lowers performance and recurrent models are most consistent across diseases.
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.
View arXiv page View PDF GitHub 2 Add to collection
Get this paper in your agent:
hf papers read 2611.15348
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.15348 in a model README.md to link it from this page.
Datasets citing this paper 1
ivanpodd/S-OH
Viewer • Updated about 1 hour ago • 1.23k • 1.21k • 3
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.15348 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
来源: Hugging Face Daily Papers · huggingface.co