About this paper
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…
time series classificationmultivariate time seriesfeature-based tabular learnersconvolution-based modelsgraph-based modelstime series architecturesrecurrent architecturestemporal validationrandom cross-validationROC AUC
- Upvotes
- 6
- Authors
- 6
- Published
- Nov 11, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
Breath-Dx: A Time Series Classification Benchmark for Disease Screening with eNose was first seen on Hugging Face · Daily papers on Nov 18, 2026. Since then it has appeared in 13 checks on 2 different days. Its best position was #7 of 30, reached on Nov 18, 11:28 UTC. It dropped off the list after Nov 19, 03:28 UTC.