paper-with-me

Papers

PulmoVec: A Two-Stage Stacking Meta-Learning Architecture Built on the HeAR Foundation Model for Multi-Task Classification of Pediatric Respiratory Sounds

2026-03-15 · Izzet Turkalp Akbasli, Oguzhan Serin arxiv

Background: Respiratory diseases are a leading cause of childhood morbidity and mortality, yet lung auscultation remains subjective and limited by inter-listener variability, particularly in pediatric populations. Existing AI approaches are further constrained by small datasets and single-task designs. We developed PulmoVec, a multi-task framework built on the Health Acoustic Representations (HeAR) foundation model for classification of pediatric respiratory sounds. Methods: In this retrospective analysis of the SPRSound database, 24,808 event-level annotated segments from 1,652 pediatric patients were analyzed. Three task-specific classifiers were trained for screening, sound-pattern recognition, and disease-group prediction. Their out-of-fold probability outputs were combined with demographic metadata in a LightGBM stacking meta-model, and event-level predictions were aggregated to the patient level using ensemble voting. Results: At the event level, the screening model achieved an ROC-AUC of 0.96 (95% CI, 0.95-0.97), the sound-pattern recognition model a macro ROC-AUC of 0.96 (95% CI, 0.96-0.97), and the disease-group prediction model a macro ROC-AUC of 0.94 (95% CI, 0.93-0.94). At the patient level, disease-group classification yielded an accuracy of 0.74 (95% CI, 0.71-0.77), a weighted F1-score of 0.73, and a macro ROC-AUC of 0.91 (95% CI, 0.90-0.93). Stacking improved performance across all tasks compared with base models alone. Conclusions: PulmoVec links event-level acoustic phenotyping with patient-level clinical classification, supporting the potential of foundation-model-based digital auscultation in pediatric respiratory medicine. Multi-center external validation across devices and real-world conditions remains essential.

📄 PDF Abstract BibTeX arXiv:2603.15688

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Stacking hybrid GARCH models for forecasting Bitcoin volatility

2021-07-15 · Expert Systems with Applications 2021 7 · Serkan Aras

Machine learning techniques have been used frequentlyfor volatility forecasting. However, previous studies have built these hybrid models in a form of a first-order GARCH(1,1) process by following general use for GARCH m…

feature selectionMeta-Learning

Regularized Meta-Learning for Improved Generalization

2026-02-12 · Noor Islam S. Mohammad, Md Muntaqim Meherab arxiv

Deep ensemble methods often improve predictive performance, yet they suffer from three practical limitations: redundancy among base models that inflates computational cost and degrades conditioning, unstable weighting un…

RocketStack: A level-aware deep recursive ensemble learning framework with exploratory feature fusion and model pruning dynamics

2025-06-20 · Çağatay Demirel

Ensemble learning remains a cornerstone of machine learning, with stacking used to integrate predictions from multiple base learners through a meta-model. However, deep stacking remains rare, as most designs prioritize h…

Ensemble Learning

Enhancing binary classification: A new stacking method via leveraging computational geometry

2024-10-30 · Wei Wu, Liang Tang, Zhongjie Zhao, Chung-Piaw Teo

Stacking, a potent ensemble learning method, leverages a meta-model to harness the strengths of multiple base models, thereby enhancing prediction accuracy. Traditional stacking techniques typically utilize established l…

Binary ClassificationEnsemble Learning

Regularized boosting with an increasing coefficient magnitude stop criterion as meta-learner in hyperparameter optimization stacking ensemble

2024-02-02 · Laura Fdez-Díaz, José Ramón Quevedo, Elena Montañés

In Hyperparameter Optimization (HPO), only the hyperparameter configuration with the best performance is chosen after performing several trials, then, discarding the effort of training all the models with every hyperpara…

Ensemble LearningHyperparameter Optimization