A Novel Algorithm Based on Artificial Intelligence-Assisted Analysis of Lung Sounds Auscultation for Acute Respiratory Illnesses in Noisy Environments

    Inventor

    The Lung Sound Evaluation Management System is a web-based software designed to manage lung sounds, particularly in noisy environments, to prioritize acute respiratory illnesses. It predicts lung disease and provides initial management, enhances clinical decision-making, expedites diagnostic processes, and serves as an educational resource in medical universities. The system uses deep learning to recognize pulmonary diseases from electronically recorded lung sounds, classifying patients based on disease types using CNN + LSTM. The dataset used for training and testing the system is obtained from HUKM Hospital in Malaysia. The study also implements a multiple denoising technique involving Fast Fourier Transform and high-pass filtering to improve diagnostic accuracy. This project lays the groundwork for implementing deep learning models in clinical settings to assist clinicians in recognizing pulmonary diseases.

  • Description of Invention

    Ts. Dr. R. Kanesaraj A/L Ramasamy, Multimedia University

  • Intellectual Property (IP) Status

    • TRL Status: 4

Video