Abstract :

Cardio-respiratory Disorders Remain A Major Public Health Concern, Contributing To A Significant Proportion Of Global Mortality, With A Notably High Burden In Countries Like India. Timely Identification Of Abnormalities In Heart And Lung Function Is Critical, And Auscultation Serves As A Primary Diagnostic Technique. Conventionally, Clinicians Rely On Acoustic Signals Captured Through Stethoscopes And Interpret Them Based On Experience, Which Can Lead To Variability In Diagnosis Due To Subjectivity, Environmental Noise, And Differences In Expertise. To Overcome These Challenges, This Work Introduces An Intelligent, Automated System For Analyzing Cardio-respiratory Sounds Using Advanced Computational Methods. A Specialized Dataset Comprising Cardiac Signals, Pulmonary Sounds, And Combined Recordings Is Acquired Using A Digital Stethoscope In A Controlled Clinical Setup. The Audio Data Is Processed Using Signal Analysis Techniques To Derive Representative Features Such As MFCCs, Chromatic Features, And Spectral Representations. These Extracted Attributes Are Utilized To Train A Range Of Machine Learning Algorithms, Including Quadratic Discriminant Analysis, Gradient Boosting, Gaussian Naive Bayes, And Logistic Regression, Enabling Comparative Evaluation. In Addition, A Newly Designed Deep Learning Architecture, Referred To As HLS-CMDS, Integrates Bi-directional Convolutional Neural Networks With Bi-directional Gated Recurrent Units To Effectively Learn Both Spatial And Temporal Characteristics Of The Signals. The System Is Capable Of Simultaneously Distinguishing Heart And Lung Sounds From Mixed Inputs With Strong Predictive Performance, Achieving Accuracy Levels In The Range Of 92–95%. A Graphical Interface With Access Control Features Further Enhances Usability By Supporting Both Model Training And Real-time Inference. The Proposed Solution Offers A Reliable, Efficient, And Non-invasive Approach For Early Detection Of Cardio-respiratory Conditions, Reducing Reliance On Manual Assessment And Improving Diagnostic Consistency.

Published:

22-6-2026

Issue:

Vol. 26 No. 6 (2026)

Page Nos:

1297-1308

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite