Blog

Abstract

This study aims to create an automated, accessible, and cost-effective diagnostic tool for chronic obstructive pulmonary disease (COPD). Traditional diagnostic methods are expensive, time-consuming, and require specialized equipment. The proposed TriSpectraKAN model leverages audio-based lung sound features to improve early diagnosis. TriSpectraKAN is a hybrid model combining spectral features and the Kolmogorov–Arnold Network (KAN) to analyze lung sounds using Mel-frequency cepstral coefficients (MFCCs), chromagram, and Mel spectrograms. Each sub-model focuses on a different audio feature, capturing unique sonic signatures. These features are merged through a hybrid network for comprehensive analysis. The model, trained on a COPD dataset, was deployed on a Raspberry Pi for real-time use. TriSpectraKAN achieved 93% accuracy, an F1 score of 0.98, precision of 0.97, and recall of 0.98. This multimodal approach captured a broad range of lung sound features, improving diagnosis accuracy compared to traditional methods. The integration of multiple audio features in TriSpectraKAN enhances COPD diagnosis, demonstrating the potential of AI and machine learning to transform respiratory disease diagnosis through accessible tools.

Abstract

This study aims to create an automated, accessible, and cost-effective diagnostic tool for chronic obstructive pulmonary disease (COPD). Traditional diagnostic methods are expensive, time-consuming, and require specialized equipment. The proposed TriSpectraKAN model leverages audio-based lung sound features to improve early diagnosis. TriSpectraKAN is a hybrid model combining spectral features and the Kolmogorov–Arnold Network (KAN) to analyze lung sounds using Mel-frequency cepstral coefficients (MFCCs), chromagram, and Mel spectrograms. Each sub-model focuses on a different audio feature, capturing unique sonic signatures. These features are merged through a hybrid network for comprehensive analysis. The model, trained on a COPD dataset, was deployed on a Raspberry Pi for real-time use. TriSpectraKAN achieved 93% accuracy, an F1 score of 0.98, precision of 0.97, and recall of 0.98. This multimodal approach captured a broad range of lung sound features, improving diagnosis accuracy compared to traditional methods. The integration of multiple audio features in TriSpectraKAN enhances COPD diagnosis, demonstrating the potential of AI and machine learning to transform respiratory disease diagnosis through accessible tools.

Abstract

This study aims to create an automated, accessible, and cost-effective diagnostic tool for chronic obstructive pulmonary disease (COPD). Traditional diagnostic methods are expensive, time-consuming, and require specialized equipment. The proposed TriSpectraKAN model leverages audio-based lung sound features to improve early diagnosis. TriSpectraKAN is a hybrid model combining spectral features and the Kolmogorov–Arnold Network (KAN) to analyze lung sounds using Mel-frequency cepstral coefficients (MFCCs), chromagram, and Mel spectrograms. Each sub-model focuses on a different audio feature, capturing unique sonic signatures. These features are merged through a hybrid network for comprehensive analysis. The model, trained on a COPD dataset, was deployed on a Raspberry Pi for real-time use. TriSpectraKAN achieved 93% accuracy, an F1 score of 0.98, precision of 0.97, and recall of 0.98. This multimodal approach captured a broad range of lung sound features, improving diagnosis accuracy compared to traditional methods. The integration of multiple audio features in TriSpectraKAN enhances COPD diagnosis, demonstrating the potential of AI and machine learning to transform respiratory disease diagnosis through accessible tools.

Most people diagnosed with COPD are middle aged with a history of smoking, but Hanania explains that this is not always the case. About 20% of patients who have COPD are non-smokers, and the illness is caused by second-hand smoke or heavy pollutants used in certain occupations or countries. There also has been evidence that poor or stunted lung growth during childhood could be a risk factor.

“The disease is serious because it can increase the risk of having what we call exacerbations or flare ups, which may increase medical visits or hospital admissions,” Hanania said. “Quality of life will also become affected when individuals cannot complete their usual activities. Some people can even become disabled and need to continue with oxygen therapy.”

Hanania adds there are potential genetic and hereditary factors to COPD as not all smokers get COPD. Research on COPD genes is being conducted to find out if certain individuals who smoke have higher risks than others.

“We don’t have a very quick answer now, but there are potential genetic factors that have been identified that put a smoker at high risk for developing COPD.”

Most people diagnosed with COPD are middle aged with a history of smoking, but Hanania explains that this is not always the case. About 20% of patients who have COPD are non-smokers, and the illness is caused by second-hand smoke or heavy pollutants used in certain occupations or countries. There also has been evidence that poor or stunted lung growth during childhood could be a risk factor.

“The disease is serious because it can increase the risk of having what we call exacerbations or flare ups, which may increase medical visits or hospital admissions,” Hanania said. “Quality of life will also become affected when individuals cannot complete their usual activities. Some people can even become disabled and need to continue with oxygen therapy.”

Hanania adds there are potential genetic and hereditary factors to COPD as not all smokers get COPD. Research on COPD genes is being conducted to find out if certain individuals who smoke have higher risks than others.

“We don’t have a very quick answer now, but there are potential genetic factors that have been identified that put a smoker at high risk for developing COPD.”

Most people diagnosed with COPD are middle aged with a history of smoking, but Hanania explains that this is not always the case. About 20% of patients who have COPD are non-smokers, and the illness is caused by second-hand smoke or heavy pollutants used in certain occupations or countries. There also has been evidence that poor or stunted lung growth during childhood could be a risk factor.

“The disease is serious because it can increase the risk of having what we call exacerbations or flare ups, which may increase medical visits or hospital admissions,” Hanania said. “Quality of life will also become affected when individuals cannot complete their usual activities. Some people can even become disabled and need to continue with oxygen therapy.”

Hanania adds there are potential genetic and hereditary factors to COPD as not all smokers get COPD. Research on COPD genes is being conducted to find out if certain individuals who smoke have higher risks than others.

“We don’t have a very quick answer now, but there are potential genetic factors that have been identified that put a smoker at high risk for developing COPD.”

Abstract

This study aims to create an automated, accessible, and cost-effective diagnostic tool for chronic obstructive pulmonary disease (COPD). Traditional diagnostic methods are expensive, time-consuming, and require specialized equipment. The proposed TriSpectraKAN model leverages audio-based lung sound features to improve early diagnosis. TriSpectraKAN is a hybrid model combining spectral features and the Kolmogorov–Arnold Network (KAN) to analyze lung sounds using Mel-frequency cepstral coefficients (MFCCs), chromagram, and Mel spectrograms. Each sub-model focuses on a different audio feature, capturing unique sonic signatures. These features are merged through a hybrid network for comprehensive analysis. The model, trained on a COPD dataset, was deployed on a Raspberry Pi for real-time use. TriSpectraKAN achieved 93% accuracy, an F1 score of 0.98, precision of 0.97, and recall of 0.98. This multimodal approach captured a broad range of lung sound features, improving diagnosis accuracy compared to traditional methods. The integration of multiple audio features in TriSpectraKAN enhances COPD diagnosis, demonstrating the potential of AI and machine learning to transform respiratory disease diagnosis through accessible tools.

Most people diagnosed with COPD are middle aged with a history of smoking, but Hanania explains that this is not always the case. About 20% of patients who have COPD are non-smokers, and the illness is caused by second-hand smoke or heavy pollutants used in certain occupations or countries. There also has been evidence that poor or stunted lung growth during childhood could be a risk factor.

“The disease is serious because it can increase the risk of having what we call exacerbations or flare ups, which may increase medical visits or hospital admissions,” Hanania said. “Quality of life will also become affected when individuals cannot complete their usual activities. Some people can even become disabled and need to continue with oxygen therapy.”

Hanania adds there are potential genetic and hereditary factors to COPD as not all smokers get COPD. Research on COPD genes is being conducted to find out if certain individuals who smoke have higher risks than others.

“We don’t have a very quick answer now, but there are potential genetic factors that have been identified that put a smoker at high risk for developing COPD.”

Abstract

This study aims to create an automated, accessible, and cost-effective diagnostic tool for chronic obstructive pulmonary disease (COPD). Traditional diagnostic methods are expensive, time-consuming, and require specialized equipment. The proposed TriSpectraKAN model leverages audio-based lung sound features to improve early diagnosis. TriSpectraKAN is a hybrid model combining spectral features and the Kolmogorov–Arnold Network (KAN) to analyze lung sounds using Mel-frequency cepstral coefficients (MFCCs), chromagram, and Mel spectrograms. Each sub-model focuses on a different audio feature, capturing unique sonic signatures. These features are merged through a hybrid network for comprehensive analysis. The model, trained on a COPD dataset, was deployed on a Raspberry Pi for real-time use. TriSpectraKAN achieved 93% accuracy, an F1 score of 0.98, precision of 0.97, and recall of 0.98. This multimodal approach captured a broad range of lung sound features, improving diagnosis accuracy compared to traditional methods. The integration of multiple audio features in TriSpectraKAN enhances COPD diagnosis, demonstrating the potential of AI and machine learning to transform respiratory disease diagnosis through accessible tools.

Most people diagnosed with COPD are middle aged with a history of smoking, but Hanania explains that this is not always the case. About 20% of patients who have COPD are non-smokers, and the illness is caused by second-hand smoke or heavy pollutants used in certain occupations or countries. There also has been evidence that poor or stunted lung growth during childhood could be a risk factor.

“The disease is serious because it can increase the risk of having what we call exacerbations or flare ups, which may increase medical visits or hospital admissions,” Hanania said. “Quality of life will also become affected when individuals cannot complete their usual activities. Some people can even become disabled and need to continue with oxygen therapy.”

Hanania adds there are potential genetic and hereditary factors to COPD as not all smokers get COPD. Research on COPD genes is being conducted to find out if certain individuals who smoke have higher risks than others.

“We don’t have a very quick answer now, but there are potential genetic factors that have been identified that put a smoker at high risk for developing COPD.”