Narrow Results

There are certain difficulties and unpleasant issues related to conventional diagnostic tools. These factors tilted the researchers toward finding an alternative non-invasive way of diagnosis. This alternate approach usually involves physiological and lifestyle-related data. The non-invasive tools are more convenient for common people as they are user-friendly and have no side effects. At the same time, they are cost-effective as well. The non-invasive diagnosis is also preferred by the people who live in places where medical facilities are not abundant. This study concentrates on detecting a person as hypertensive by analyzing certain parameters in speech using machine learning approaches. We identify some phonemes and features of speech that are more sensitive to capture the distortions in speech due to hypertension. Four different machine learning methods involving both classical and state-of-the-art methods in our study show the effectiveness of both types of machine learning methods in different dimensions. The study shows inspiring results in terms of prediction accuracy ($\sim$95%) as well as identifying a minimal set of hypertension-sensitive features. It is also found that when we combine the predictions of both classical and state-of-the-art methods, the result gives more reliable predictions.

A great increase in the number of cardiovascular cases has been a cause of serious concern for the medical experts all over the world today. In order to achieve valuable risk stratification for patients, early prediction of heart health can benefit specialists to make effective decisions. Heart sound signals help to know about the condition of heart of a patient. Motivated by the success of cepstral features in speech signal classification, authors have used here three different cepstral features, viz. Mel-frequency cepstral coefficients (MFCCs), gammatone frequency cepstral coefficients (GFCCs), and Mel-spectrogram for classifying phonocardiogram into normal and abnormal. Existing research has explored only MFCCs and Mel-feature set extensively for classifying the phonocardiogram. However, in this work, the authors have used a fusion of GFCCs with MFCCs and Mel-spectrogram, and achieved a better accuracy score of 0.96 with sensitivity and specificity scores as 0.91 and 0.98, respectively. The proposed model has been validated on the publicly available benchmark dataset PhysioNet 2016.