โก Quick Summary
This study introduces a deep learning framework for classifying COVID-19 based on cough sounds, utilizing advanced models like ResNet and EfficientNet v2. The results indicate that ResNet achieved an impressive accuracy of 98.5%, showcasing its potential for rapid diagnosis and intervention.
๐ Key Details
- ๐ Dataset: Cough sounds for COVID-19 classification
- ๐งฉ Features used: Normal and cough sounds
- โ๏ธ Technology: ResNet, EfficientNet v2, 1D-CNN, DS-CNN
- ๐ Performance: ResNet: Accuracy 98.5%, Precision 98.99%, Recall 98%
๐ Key Takeaways
- ๐ฆ COVID-19 is highly contagious, necessitating rapid diagnosis.
- ๐ค Deep learning models can effectively classify cough sounds to identify COVID-19.
- ๐ ResNet outperformed other models with an accuracy of 98.5%.
- ๐ Low false positive rate of 0.01 indicates high reliability.
- ๐ก Early intervention can significantly reduce disease transmission.
- ๐ Performance metrics included accuracy, recall, precision, F1_Score, and MCC.
- ๐ Study published in the journal Sci Rep, highlighting its relevance in global health.
๐ Background
The emergence of COVID-19 in late 2019 has posed significant health and economic challenges worldwide. As a respiratory disease, it spreads primarily through respiratory droplets, making rapid diagnosis crucial for controlling its transmission. Traditional diagnostic methods can be time-consuming, thus necessitating innovative approaches to enhance early detection and intervention.
๐๏ธ Study
This study aimed to develop a novel framework for classifying COVID-19 using cough sounds. Researchers employed various deep learning models, including 1D-CNN, DS-CNN, EfficientNet v2, and ResNet, to analyze cough sounds and differentiate between normal and COVID-19 coughs. The performance of these models was rigorously evaluated using multiple metrics.
๐ Results
The findings revealed that the ResNet model significantly outperformed other models, achieving an accuracy of 98.5%, precision of 98.99%, and a recall of 98%. The Matthews Correlation Coefficient (MCC) was calculated at 0.9699, while the false positive rate was remarkably low at 0.01. These results underscore the effectiveness of deep learning in medical diagnostics.
๐ Impact and Implications
The implications of this study are profound, as it highlights the potential of using cough sounds for the early detection of COVID-19. By leveraging advanced deep learning technologies, healthcare providers can achieve high-precision diagnostics, facilitating timely interventions that can help reduce the spread of the virus. This approach could pave the way for similar applications in diagnosing other infectious diseases.
๐ฎ Conclusion
This research showcases the transformative potential of deep learning in the realm of infectious disease diagnostics. The high accuracy and reliability of the ResNet model in classifying cough sounds for COVID-19 detection present a promising avenue for enhancing public health responses. Continued exploration in this field could lead to significant advancements in rapid diagnostic technologies.
๐ฌ Your comments
What are your thoughts on using cough sounds for diagnosing COVID-19? We invite you to share your insights and engage in a discussion! ๐ฌ Leave your comments below or connect with us on social media:
ResNet-EfficientNet powered framework for high-precision cough-based classification of infectious diseases.
Abstract
COVID-19 is a extremely contagious disease triggered by the SARS-CoV-2 virus which mostly affects the human breathing system. Furthermore, the COVID-19 was emerged in late 2019 and escalated rapidly into a global pandemic which impacted health and economic challenges across globe. Similar to other infectious diseases, it transmits through respiratory droplets and the rapid diagnosis is more important in controlling transmission and managing patient health care. In this work, a deep learning framework for COVID-19 classification using cough sounds has been proposed. Furthermore, the various deep learning models such as one-dimensional Convolutional Neural Network (1D-CNN), Depth-wise Convolutional Neural Network (DS-CNN), EfficientNet v2 and ResNet are utilized for the identification of normal and cough sounds produced by COVID-19. Also, the performances of all the deep learning models are analyzed using performance metrics such as accuracy, recall, precision, Matthews Correlation Coefficient (MCC), F1_Score and False Positive Rate (FPR). Results demonstrate that the performance of pre-trained models namely EfficientNet v2 and ResNet is better when compared to existing Deep Learning (DL) models. Additionally, the accuracy, precision, recall, F1_Score, MCC and false positive rate of ResNet is 98.5%, 98.99, 98, 0.9849, 0.9699 and 0.01 respectively shows that the ResNet is superior to the other models. The proposed work focus on the early intervention which helps physicians to isolate or treat patients which reduces transmission.
Author: [‘Johnson DS’, ‘Alagumariappan P’, ‘Sathyamoorthy M’, ‘Sayeed MS’, ‘Kaveri PR’, ‘Sai Kiran Reddy PP’]
Journal: Sci Rep
Citation: Johnson DS, et al. ResNet-EfficientNet powered framework for high-precision cough-based classification of infectious diseases. ResNet-EfficientNet powered framework for high-precision cough-based classification of infectious diseases. 2025; 15:38975. doi: 10.1038/s41598-025-22874-7