Reliable pneumonia detection and wheeze-crackle classification via data balancing and augmentation

2026-03-31

PRE

Seong, Jaewon

Oh, Soo Min *

Ortiz, Bengie L.

Jo Woon Chong

DOI：10.1007/s11760-026-05259-9

Original

Original request for help

Save

Abstract

En 中文

Pneumonia diagnosis based on X-ray imaging can be costly and inaccessible in resource-limited settings. We propose a machine learning framework that classifies respiratory sounds to detect pneumonia and further distinguish wheeze and crackle, which reflect different pathologies. To improve reliability under class imbalance, we apply a hybrid resampling strategy that combines ADASYN and Tomek Link, and incorporate acoustically plausible augmentations through noise injection and volume control to enhance robustness while preserving signal characteristics. Experiments on the ICBHI 2017 dataset show that XGBoost consistently outperforms Random Forest, achieving higher predictive performance and more confident classifications. These results suggest that the proposed approach enables reliable sound-based respiratory disease screening, even with small and imbalanced datasets.

Keywords:

Pneumonia detection

Respiratory sound classification

Wheeze-crackle discrimination

Tree-based learning

Hybrid sampling

Data augmentation

Reliable pneumonia detection and wheeze-crackle classification via data balancing and augmentation

Abstract

Journal

Organization

Cited Papers

Citing Papers