Machine Learning-Enabled Hypertension Screening Through Acoustical Speech Analysis: Model Development and Validation

Hypertension, referred to as the “silent killer” by the World Health Organization, affects over 35% of the global population. Early diagnosis and behavioural interventions have been shown to mitigate morbidity and mortality associated with this condition. However, conventional methods of measuring blood pressure and accordingly identifying hypertension, such as sphygmomanometry, require technical expertise and may not be readily accessible, particularly in remote or underserved areas. Automatic blood pressure measurement devices offer an alternative but are often inaccessible in certain populations. In this study, we propose a novel framework for detecting hypertension through acoustic analysis of speech. By recording speech across multiple sessions and analyzing its temporal and spectral characteristics, we aim to identify indicators of hypertension. We explore two thresholds for labeling individuals with hypertension: 1) systolic blood pressure (SBP)≥ 135mmHg or diastolic blood pressure (DBP)≥ 85mmHg and 2) SBP≥ 140mmHg or DBP≥ 90mmHg. Our study involved 245 participants, including 91 females. We developed predictive models for each gender and assessed their performance using leave-one-subject-out validation. For the first threshold, the balanced accuracy achieved was 84% for females and 77% for males. For the second threshold, the corresponding balanced accuracies were 63% for females and 86% for males. These results demonstrate the potential of utilizing speech-based representations for non-invasive screening of hypertension.