Year: 2025
Type: article
Abstract: Pneumonia is a leading global cause of morbidity and mortality, particularly in children and the elderly. Traditional diagnostics often rely on imaging and laboratory tests, which can delay treatment in resource-limited settings. This study proposes an AI-based system for pneumonia prediction using respiratory sounds recorded through digital stethoscopes. Acoustic features, including MFCCs and spectral patterns, were extracted and analyzed using deep learning models (CNNs and RNNs). The system achieved over 93% accuracy, demonstrating performance comparable to experienced clinicians. This portable, cost-effective approach has strong potential for early detection and integration into telemedicine platforms
Author: Amit Singh
Language: English
Subfield: Pulmonary and Respiratory Medicine
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W4414292352
FWCI:
Cites:
Cited by:
Related to: