Artificial Intelligence-Enabled Spirometry for Early Detection of Right Heart Failure

2025-11-17

AI Summary

This study addresses the challenge of early risk prediction for right heart failure in patients with cor pulmonale. To overcome the scarcity of labeled respiratory signals, we propose a self-supervised representation learning framework based on a variational autoencoder (VAE) that automatically extracts robust, low-dimensional features from unlabeled spirometry time-series data and integrates them with demographic and clinical variables. A two-stage predictive model is then constructed by combining CatBoost classification with synthetic data augmentation. Evaluated on 26,617 samples from UK Biobank, the model achieves an AUC of 0.7501. Notably, AUC improves to 0.8194 and 0.8413 in chronic kidney disease and valvular heart disease subgroups, respectively—demonstrating enhanced high-risk population screening capability and cross-subgroup generalizability. The approach delivers an interpretable, deployable AI solution for noninvasive, early warning of right heart failure.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Reasoning under Uncertainty: Relational Probabilistic Models
• Humans and AI: Voting

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Right heart failure (RHF) is a disease characterized by abnormalities in the structure or function of the right ventricle (RV), which is associated with high morbidity and mortality. Lung disease often causes increased right ventricular load, leading to RHF. Therefore, it is very important to screen out patients with cor pulmonale who develop RHF from people with underlying lung diseases. In this work, we propose a self-supervised representation learning method to early detecting RHF from patients with cor pulmonale, which uses spirogram time series to predict patients with RHF at an early stage. The proposed model is divided into two stages. The first stage is the self-supervised representation learning-based spirogram embedding (SLSE) network training process, where the encoder of the Variational autoencoder (VAE-encoder) learns a robust low-dimensional representation of the spirogram time series from the data-augmented unlabeled data. Second, this low-dimensional representation is fused with demographic information and fed into a CatBoost classifier for the downstream RHF prediction task. Trained and tested on a carefully selected subset of 26,617 individuals from the UK Biobank, our model achieved an AUROC of 0.7501 in detecting RHF, demonstrating strong population-level distinction ability. We further evaluated the model on high-risk clinical subgroups, achieving AUROC values of 0.8194 on a test set of 74 patients with chronic kidney disease (CKD) and 0.8413 on a set of 64 patients with valvular heart disease (VHD). These results highlight the model's potential utility in predicting RHF among clinically elevated-risk populations. In conclusion, this study presents a self-supervised representation learning approach combining spirogram time series and demographic data, demonstrating promising potential for early RHF detection in clinical practice.

Problem

• Early detection of right heart failure using AI spirometry
• Screening cor pulmonale patients developing RHF from lung diseases
• Predicting RHF with spirogram time series and demographic data

Innovation

• Self-supervised learning for spirogram embedding
• VAE encoder extracts low-dimensional time series representation
• CatBoost classifier fuses spirogram and demographic data