EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SpiroLLM: Finetuning pretrained LLMs to understand spirogram time series with clinical validation in COPD reporting

Shuhao Mei iD, Yongchao Long, Xiaoyu Xiao, Shan Cao, Xiaobo Han, Shijia Geng, Jinbo Sun, Yuxi Zhou, Shenda Hong iD

PLOS Digital Health · 24.03.2026 · 5 (3) · e0001300

DOI: 10.1371/journal.pdig.0001300 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 24.03.2026. Verfasst von Shuhao Mei und 8 weiteren Autor:innen. Beteiligte Einrichtung: Guangzhou Institute of Technology, Xidian University, Xi'an, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Tianjin Science and Technology Program, Tianchi Elite Youth Doctoral Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Autor:innen und Institutionen

  • Guangzhou Institute of Technology, Xidian University, Xi'an, China.
  • Department of Computer Science, Tianjin University of Technology, Tianjin, China.
  • National Institute of Health Data Science, Peking University, Beijing, China.
  • Department of Respiratory, The Second Hospital of Tianjin Medical University, Tianjin, China.
  • College of Pulmonary and Critical Care Medicine, Chinese PLA General Hospital, Beijing, China.
  • HeartVoice Medical Technology, Hefei, China.

ORCID-Profile: Shuhao Mei, Shenda Hong

Förderung

  • National Natural Science Foundation of China
  • Tianjin Science and Technology Program
  • Tianchi Elite Youth Doctoral Program
  • CCF-Zhipu Large Model Innovation Fund
  • Xidian University Specially Funded Project for Interdisciplinary Exploration

Zitieren

APA

Mei, S., Long, Y., Xiao, X., Cao, S., Han, X., Geng, S., Sun, J., Zhou, Y., & Hong, S. (2026). SpiroLLM: Finetuning pretrained LLMs to understand spirogram time series with clinical validation in COPD reporting. PLOS Digital Health, 5(3), e0001300. https://doi.org/10.1371/journal.pdig.0001300

Vancouver

Mei S, Long Y, Xiao X, Cao S, Han X, Geng S, et al. SpiroLLM: Finetuning pretrained LLMs to understand spirogram time series with clinical validation in COPD reporting. PLOS Digital Health. 2026;5(3):e0001300. doi:10.1371/journal.pdig.0001300

BibTeX
@article{Mei2026,
  author = {Mei, Shuhao and Long, Yongchao and Xiao, Xiaoyu and Cao, Shan and Han, Xiaobo and Geng, Shijia and Sun, Jinbo and Zhou, Yuxi and Hong, Shenda},
  title = {SpiroLLM: Finetuning pretrained LLMs to understand spirogram time series with clinical validation in COPD reporting},
  journal = {PLOS Digital Health},
  year = {2026},
  volume = {5},
  number = {3},
  pages = {e0001300},
  doi = {10.1371/journal.pdig.0001300}
}
Kostenlos starten →