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

• URL: http://arxiv.org/abs/2603.15688v1
• Date: Sun, 15 Mar 2026 21:13:47 GMT
• Title: PulmoVec: A Two-Stage Stacking Meta-Learning Architecture Built on the HeAR Foundation Model for Multi-Task Classification of Pediatric Respiratory Sounds
• Abstract summary: PulmoVec is a multi-task framework for classification of pediatric respiratory sounds.<n>It links event-level acoustic phenotyping with patient-level clinical classification.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Trusting Right Predictions for Wrong Reasons: A LIME Based Analysis of Deep Learning Interpretability in Lung Cancer Diagnosis [0.0]
  Lung cancer is the leading cause of cancer-related mortality, with approximately 2.5 million new cases and 1.8 million deaths annually.<n> evaluation has largely focused on predictive accuracy, leaving their decision-making processes insufficiently examined.<n>This study compares three models: a Convolutional Neural Network (CNN), a pretrained ResNet50, and a Vision Transformer (ViT), trained on the IQ-OTH/NCCD lung cancer CT dataset.<n>All three models achieved strong classification performance, with ResNet50 attaining 98.61% accuracy, CNN 97.91%, and ViT 93.75%, while all achieved
  arXiv  Detail & Related papers  (2026-06-14T22:08:31Z)
• Early Detection of Alzheimer's Disease Using Explainable Machine Learning on Clinical Biomarkers: A Multi-Class Classification Study Using the Alzheimer's Disease Neuroimaging Initiative (ADNI) Dataset [0.0]
  Alzheimer's disease affects over 55 million people worldwide.<n>Machine learning model trained on routine clinical assessments achieves near-perfect three-class Alzheimer's detection.
  arXiv  Detail & Related papers  (2026-04-14T10:54:14Z)
• MorphDistill: Distilling Unified Morphological Knowledge from Pathology Foundation Models for Colorectal Cancer Survival Prediction [3.2844015242965927]
  We propose MorphDistill, a framework that distills complementary knowledge from multiple pathology foundation models into a CRC-specific encoder.<n>In Stage I, a student encoder is trained using dimension-agnostic multi-teacher distillation with supervised contrastive regularization on large-scale colorectal datasets.<n>In Stage II, the encoder extracts patch-level features from whole-slide images, which are aggregated via attention-based multiple instance learning to predict five-year survival.
  arXiv  Detail & Related papers  (2026-04-07T19:21:18Z)
• Robust Multicentre Detection and Classification of Colorectal Liver Metastases on CT: Application of Foundation Models [11.274035647041762]
  We developed a foundation model-based AI pipeline for patient-level classification and lesion-level detection of CRLM on CT.<n> UMedPT achieved the best performance and was fine-tuned with a head for classification and an FCOS-based head for lesion detection.
  arXiv  Detail & Related papers  (2026-01-12T14:35:29Z)
• Explainable Admission-Level Predictive Modeling for Prolonged Hospital Stay in Elderly Populations: Challenges in Low- and Middle-Income Countries [65.4286079244589]
  Prolonged length of stay (pLoS) is a significant factor associated with the risk of adverse in-hospital events.<n>We develop and explain a predictive model for pLos using admission-level patient and hospital administrative data.
  arXiv  Detail & Related papers  (2026-01-07T23:35:24Z)
• MeCaMIL: Causality-Aware Multiple Instance Learning for Fair and Interpretable Whole Slide Image Diagnosis [40.3028468133626]
  Multiple instance learning (MIL) has emerged as the dominant paradigm for whole slide image (WSI) analysis in computational pathology.<n>textbfMeCaMIL, a causality-aware MIL framework, explicitly models demographic confounders through structured causal graphs.<n>MeCaMIL achieves superior fairness -- demographic disparity variance drops by over 65% relative reduction on average across attributes.
  arXiv  Detail & Related papers  (2025-11-14T06:47:21Z)
• A SHAP-based explainable multi-level stacking ensemble learning method for predicting the length of stay in acute stroke [3.2906073576204955]
  Existing machine learning models have shown suboptimal predictive performance, limited generalisability, and have overlooked system-level factors.<n>We developed an interpretable multi-level stacking ensemble model for ischaemic and haemorrhagic stroke.<n>An explainable ensemble model effectively predicted the prolonged LOS in ischaemic stroke.<n>Further validation is needed for haemorrhagic stroke.
  arXiv  Detail & Related papers  (2025-05-30T01:08:26Z)
• Predicting Length of Stay in Neurological ICU Patients Using Classical Machine Learning and Neural Network Models: A Benchmark Study on MIMIC-IV [49.1574468325115]
  This study explores multiple ML approaches for predicting LOS in ICU specifically for the patients with neurological diseases based on the MIMIC-IV dataset.<n>The evaluated models include classic ML algorithms (K-Nearest Neighbors, Random Forest, XGBoost and CatBoost) and Neural Networks (LSTM, BERT and Temporal Fusion Transformer)
  arXiv  Detail & Related papers  (2025-05-23T14:06:42Z)
• A multimodal ensemble approach for clear cell renal cell carcinoma treatment outcome prediction [6.199310532720352]
  We developed a multi-modal ensemble model (MMEM) that integrates clinical data, multi-omics data, and histopathology whole slide image (WSI) data.<n>MMEM predicted overall survival (OS) and disease-free survival (DFS) for ccRCC patients.
  arXiv  Detail & Related papers  (2024-12-10T02:51:14Z)
• CIMIL-CRC: a clinically-informed multiple instance learning framework for patient-level colorectal cancer molecular subtypes classification from H\&E stained images [42.771819949806655]
  We introduce CIMIL-CRC', a framework that solves the MSI/MSS MIL problem by efficiently combining a pre-trained feature extraction model with principal component analysis (PCA) to aggregate information from all patches. We assessed our CIMIL-CRC method using the average area under the curve (AUC) from a 5-fold cross-validation experimental setup for model development on the TCGA-CRC-DX cohort.
  arXiv  Detail & Related papers  (2024-01-29T12:56:11Z)
• A Federated Learning Framework for Stenosis Detection [70.27581181445329]
  This study explores the use of Federated Learning (FL) for stenosis detection in coronary angiography images (CA) Two heterogeneous datasets from two institutions were considered: dataset 1 includes 1219 images from 200 patients, which we acquired at the Ospedale Riuniti of Ancona (Italy) dataset 2 includes 7492 sequential images from 90 patients from a previous study available in the literature.
  arXiv  Detail & Related papers  (2023-10-30T11:13:40Z)
• Learning to diagnose cirrhosis from radiological and histological labels with joint self and weakly-supervised pretraining strategies [62.840338941861134]
  We propose to leverage transfer learning from large datasets annotated by radiologists, to predict the histological score available on a small annex dataset. We compare different pretraining methods, namely weakly-supervised and self-supervised ones, to improve the prediction of the cirrhosis. This method outperforms the baseline classification of the METAVIR score, reaching an AUC of 0.84 and a balanced accuracy of 0.75.
  arXiv  Detail & Related papers  (2023-02-16T17:06:23Z)
• Exploring traditional machine learning for identification of pathological auscultations [0.39577682622066246]
  Digital 6-channel auscultations of 45 patients were used in various machine learning scenarios. The aim was to distinguish between normal and anomalous pulmonary sounds. Supervised models showed a consistent advantage over unsupervised ones.
  arXiv  Detail & Related papers  (2022-09-01T18:03:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.