SpiroLLM: Finetuning Pretrained LLMs to Understand Spirogram Time Series with Clinical Validation in COPD Reporting

TL;DR

This paper introduces SpiroLLM, a multimodal large language model that understands respiratory spirogram time series to improve COPD diagnosis and reporting, demonstrating high accuracy and robustness in clinical validation.

Contribution

It is the first model to integrate spirogram analysis with LLMs, enabling interpretable and reliable clinical decision support for COPD using a large UK Biobank cohort.

Findings

Achieved a diagnostic AUROC of 0.8977 for COPD.

Maintained 100% valid responses with missing data, outperforming text-only models.

Demonstrated the potential of multimodal fusion of physiological signals and LLMs.

Abstract

Chronic Obstructive Pulmonary Disease (COPD), a major chronic respiratory disease with persistent airflow limitation, is a leading global cause of disability and mortality. Respiratory spirogram time series, routinely collected during pulmonary function tests (PFTs), play a critical role in the early detection of respiratory diseases and in monitoring lung function over time. However, most current AI models for COPD diagnosis are limited to outputting classification results without providing a rationale for their diagnostic process, while current Large Language Models (LLMs) cannot understand spirograms yet, which severely limits their clinical trust and adoption. To tackle this challenge, we leverage a cohort of 234,028 individuals from the UK Biobank (UKB) to propose SpiroLLM, the first multimodal large language model that can understand spirogram. The model extracts morphological features from respiratory curves via a SpiroEncoder and aligns them with PFT numerical values in a unified latent space using a SpiroProjector, ultimately empowering a large language model to generate a comprehensive diagnostic report. Experimental results confirm that SpiroLLM achieved a diagnostic AUROC of 0.8977 (95% CI: 0.88-0.91). In a robustness test with missing core data, it maintained a 100% valid response rate, far surpassing the 13.4% of a text-only model and showcasing the superiority of its multimodal design. This work demonstrates the substantial potential of deeply fusing physiological signals with large language models, establishing a new paradigm for the next generation of interpretable and reliable clinical decision support tools.