Skip to content

Source paper

Breath-Dx: A Time Series Classification Benchmark for Disease Screening with eNose

Ivan Poddiakov, Ivan Kruzhilov, Galina Zubkova and 3 more

Ivan Poddiakov, Ivan Kruzhilov, Galina Zubkova, Svetlana Erofeeva, Andrey Savchenko, Pavel Blinov

arXiv 2611.15348 · 202633 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

This paper presents Breath-Dx, the first comprehensive benchmark evaluating multivariate time series classification methods for breath-based disease screening on the public Scent of Health (S-OH) dataset comprising 1,234 patients across nine diagnostic conditions. The authors benchmark ten diverse algorithms across tabular, convolutional, graph, and time series families under strict temporal splits that replicate physical sensor degradation over 13 weeks. Their findings demonstrate that temporal sensor drift causes a severe 0.05 to 0.12 drop in ROC AUC compared to standard cross-validation, while also revealing that demographic factors like age act as significant diagnostic confounders.

How it works (AI summary)

The study collects 17-channel metal oxide gas sensor time series data (sampled at 0.4 Hz for 895 seconds per patient) and evaluates one-versus-rest binary classification across nine diagnostic classes using fixed temporal week-based test splits. Ten classification architectures are evaluated: feature-based tabular ensembles (CatBoost, XGBoost, HistGradientBoost, Random Forest) trained on statistical summaries and kinetic growth parameters, 2D convolutional networks (CNN and pre-trained ResNet18) trained on polynomial interaction matrices, Graphormer operating on 8-node complete inter-sensor graphs, and raw time series models (LSTM, InceptionTime, and TS2Vec self-supervised representations).