Chronic Obstructive Pulmonary Disease Prediction Using Deep Convolutional Network

2024-11-03

medRxiv

AI Summary

To address the clinical need for non-invasive, early, and severity-stratified diagnosis of chronic obstructive pulmonary disease (COPD), this work proposes a deep convolutional neural network (CNN) that jointly learns from multi-dimensional acoustic features—MFCCs, Mel-spectrograms, Chroma, and CENS—directly from respiratory sound signals to automatically classify COPD severity into mild, moderate, and severe grades. Features are extracted using Librosa, and model generalizability is enhanced via 10-fold stratified cross-validation. Evaluated on the public ICBHI dataset, the method achieves 96% classification accuracy—6 percentage points higher than non-cross-validated baselines—and outperforms existing state-of-the-art approaches. Key contributions include: (i) the first end-to-end CNN architecture integrating heterogeneous acoustic features for fine-grained clinical severity grading; and (ii) empirical validation of its robustness and deployability in resource-constrained settings, offering a practical technical pathway to alleviate shortages of respiratory specialists.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

AI and deep learning are two recent innovations that have made a big difference in helping to solve problems in the clinical space. Using clinical imaging and sound examination, they also work on improving their vision so that they can spot diseases early and correctly. Because there aren't enough trained HR, clinical professionals are asking for help with innovation because it helps them adapt to more patients. Aside from serious health problems like cancer and diabetes, the effects of respiratory infections are also slowly getting worse and becoming dangerous for society. Respiratory diseases need to be found early and treated quickly, so listening to the sounds of the lungs is proving to be a very helpful tool along with chest X-rays. The presented research hopes to use deep learning ideas based on Convolutional Brain Organization to help clinical specialists by giving a detailed and thorough analysis of clinical respiratory sound data for Ongoing Obstructive Pneumonic identification. We used MFCC, Mel-Spectrogram, Chroma, Chroma (Steady Q), and Chroma CENS from the Librosa AI library in the tests we ran. The new system could also figure out how serious the infection was, whether it was mild, moderate, or severe. The test results agree with the outcome of the deep learning approach that was proposed. The accuracy of the framework arrangement has been raised to a score of 96% on the ICBHI. Also, in the led tests, we used K-Crisp Cross-Approval with ten parts to make the presentation of the new deep learning approach easier to understand. With a 96 percent accuracy rate, the suggested network is better than the rest. If you don't use cross-validation, the model is 90% accurate.

Problem

• Detecting Chronic Obstructive Pulmonary Disease using respiratory sound analysis
• Classifying COPD severity levels as mild, moderate, or severe
• Automating diagnosis to support clinicians with limited trained personnel

Innovation

• Deep CNN analyzes respiratory sound data for COPD detection
• Uses Librosa-extracted acoustic features like MFCCs and Mel-Spectrogram
• Classifies COPD severity levels with 96% cross-validation accuracy