Automatic classification of normal and sick patients with crackles using wavelet packet decomposition and support vector machine

Auscultation of the respiratory system ? a key system in a human body ? is a complicated procedure and it requires a doctor to have good perception skills and profound experience. During auscultation, specific sounds are identified by the doctor who then associates the acoustic phenomena heard with pathological processes. This article is an attempt at developing a classification system, using wavelet packets, a genetic algorithm, and a Support Vector Machine (SVM), which distinguishes between healthy patients and patients with crackles caused by pneumonia, pulmonary fibrosis, Heart Failure (HF) or Chronic Obstructive Pulmonary Disease (COPD). The system is elaborated and tested over a dataset consisting of 62 healthy (166 recordings) and 58 sick patients (187 recordings). A reliable system is described, consisting of 5 wavelet classifiers, featuring approx. 95 % sensitivity and 91 % specificity, applying 10-fold cross-validation.

Automated summary

The auscultation of the respiratory system, a key element in the human body, is a complex procedure that requires doctors with good perception skills and extensive experience. This article attempts to develop a classification system using wavelet packets, a genetic algorithm, and a Support Vector Machine to differentiate between healthy patients and those with crackles caused by pneumonia, pulmonary fibrosis, HF, or COPD. The system, tested on a dataset of 62 healthy and 58 sick patients, showed promising results with high sensitivity and specificity.