Abstract: Aortic stenosis and mitral valve prolapse are examples of valvular dysfunctions usually related with the adult population. Early detection and care in adolescence has yet to be explored, more so with already existing computational approaches currently made easily available. It shall, therefore, present in this paper how basic physiologic data—heart rate, blood pressure, and demographic information—will be used with reduced computational models in trying to foresee the possibility of heart valve malfunction in adolescents. The models are developed with the use of already available computational packages, which make them more useful in educational settings. The models developed are compared in their accuracy with parameters like age, sex, and activity level. Early practices in cardiology are established to help devise tools in the enhancement of education and awareness about heart health in the population. This study serves as the basis for future work and indicates the potential involvement of high school students in activities related to the development of computational thinking. Keywords: Heart Disease, Machine Learning Models, RF Classifier, LR Model, SVM