Transformer-based Time-Series Biomarker Discovery for COPD Diagnosis

TL;DR

This paper introduces a transformer-based deep learning approach that leverages raw spirogram data and demographic info to improve COPD diagnosis, offering better performance and interpretability over traditional summary measures.

Contribution

The study presents a novel transformer model for raw spirogram analysis, enhancing COPD prediction accuracy and interpretability compared to existing methods.

Findings

Outperforms prior COPD prediction models

Provides interpretable insights aligned with medical knowledge

Achieves higher accuracy using raw data rather than summary measures

Abstract

Chronic Obstructive Pulmonary Disorder (COPD) is an irreversible and progressive disease which is highly heritable. Clinically, COPD is defined using the summary measures derived from a spirometry test but these are not always adequate. Here we show that using the high-dimensional raw spirogram can provide a richer signal compared to just using the summary measures. We design a transformer-based deep learning technique to process the raw spirogram values along with demographic information and predict clinically-relevant endpoints related to COPD. Our method is able to perform better than prior works while being more computationally efficient. Using the weights learned by the model, we make the framework more interpretable by identifying parts of the spirogram that are important for the model predictions. Pairing up with a board-certified pulmonologist, we also provide clinical insights into the different aspects of the spirogram and show that the explanations obtained from the model align with underlying medical knowledge.