Objective: Hypertension is a prevalent cardiovascular condition associated with significant morbidity and mortality. While various prognostic models exist for predicting hypertension, incorporating artificial intelligence (AI) algorithms may enhance diagnostic accuracy and prognostication. However, the value of such AI-based prognostic models in hypertension diagnosis and risk stratification remains to be fully elucidated. This study aimed to evaluate the value of a prognostic model for the diagnosis of hypertension using AI algorithms by assessing biomarkers, predictors for worse prognosis, and clinical outcomes with Kaplan-Meier analysis and Cox regression models. Design and method: A retrospective cohort study was conducted on 256 smoker individulas with a mean age of 56.2 ± 12.8 years. Participants were followed up for a median duration of 6.5±2.6 years. Clinical and laboratory data, including cardiovascular biomarkers and predictors of hypertension, were collected at baseline. An AI-based prognostic model was developed using machine learning algorithms to predict hypertension diagnosis and prognosis. Kaplan-Meier analysis was performed to evaluate the cumulative incidence of hypertension, while Cox regression models were utilized to assess predictors of worse prognosis. Results: During the follow-up period, 42% of patients developed hypertension. The AI-based prognostic model demonstrated excellent diagnostic accuracy in predicting hypertension development, with 78% sensitivity and 75% specificity. Additionally, several predictors were identified for worse prognosis in hypertensive patients, including abdominal obesity, glucose intolerance, dyslipidemia. Cox regression models confirmed the independent association between high-risk classification by the prognostic model and cumulative incidence of hypertension (hazard ratio [HR], [1.15]; 95% confidence interval [CI], [1.05-1.26]; p < 0.05). Conclusions: Our findings suggest that an AI-based prognostic model holds promise for the diagnosis of hypertension and risk stratification. Incorporating AI algorithms into prognostic models may enhance diagnostic accuracy and improve outcomes in patients with hypertension. Further research is warranted to validate these findings in larger cohorts and optimize the AI-based prognostic model for clinical implementation.