The primary cause of death globally is cardiovascular disease, of which over 80 percent can be prevented with early intervention and lifestyle change. The risk factors for CVD start in adolescence, and identifying the same using Machine learning models driven by Artificial Intelligence is a promising approach. To explore cardiovascular health risk factors among adolescents and develop a nursing algorithm by best machine learning model to mitigate cardiovascular risk among adolescents, our crosssectional prospective design study covered adolescents aged between 17 and 19 years, recruited through the multi-stage random cluster sampling technique at higher educational institutions in the Northern Kerala. Out of 1240 participants, 915 (73.8%) were aged 19 years, and 646 (52.1%) were female. The study found that odds ratio of a family history of CVD - 2.219; physical activity - 1.374; dietary habits -1.357 and stress - 2.421 times more likely to exhibit CVD than those having no risk. The Nursing algorithm was developed based on Random Forest classifier model, which was outperformed in prediction with 93 percent accuracy. Random Forest Classifier model was identified as the most suitable Machine learning model in artificial intelligence for predicting cardiovascular health risk data sets specific to adolescents in the Kerala, Indian context.