Abstract
<title>Abstract</title> <p>Background Hypertension affects approximately 1.28 billion adults worldwide and is a major cause of cardiovascular disease, stroke and premature mortality, particularly in low- and middle-income countries. Validated risk prediction tools integrated with mobile health technologies may support early identification and prevention. This study developed and validated a hypertension risk prediction model for urban adults in Mysuru, India, and translated it into an artificial-intelligence-assisted smartphone application. Methods A community-based cross-sectional study was conducted from September 2022 to March 2024 in the urban field practice area of a tertiary medical college in Mysuru, Karnataka. Using cluster sampling, 517 adults aged ≥ 19 years were enrolled. Socio-demographic characteristics, lifestyle factors, anthropometric measurements and blood pressure were collected using a pretested semi-structured questionnaire. Hypertension was defined as systolic blood pressure ≥ 140 mmHg, diastolic blood pressure ≥ 90 mmHg or current antihypertensive treatment. Independent predictors were identified using multivariable logistic regression. A weighted risk score was derived from regression coefficients and evaluated using receiver operating characteristic analysis. External validation was performed in an independent sample of 100 participants through the smartphone application. Results Hypertension prevalence was 33.1% (n = 171). Ten independent predictors were identified: age 31–50 years, male sex, married status, illiteracy, obesity, inadequate physical activity, excess salt intake, alcohol use, diabetes mellitus and family history of hypertension. The model achieved an area under the curve of 0.72 (95% CI: 0.68–0.77), with 87.2% sensitivity and 63.8% specificity at a cut-off score of 19.5. External validation demonstrated 83% predictive accuracy. Conclusions The ten-factor risk score showed acceptable discrimination and was successfully integrated into a validated mobile application. It may support targeted prevention and community-based hypertension screening in similar urban Indian settings.</p>