Blood pressure profiling during exercise has been found to predict a future diagnosis of heart-related diseases such as hypertension, hypotension, and coronary heart disease. Non-invasive methods have made it easier to measure blood pressure. Devices like stethoscope and sphygmomanometer are most commonly used in clinics and hospitals to measure blood pressure but these devices provide us with single measurement or partial information about a person’s cardiovascular health. Blood pressure does not remain constant; it changes with every instant considering various parameters such as age and gender. So, there is a need to measure BP through a more improved method such as exercise stress testing. This study describes the implementation of Artificial Neural Network to develop an algorithm to perform cardiovascular health pre-diagnosis of a patient. The decision-making is done through a blood pressure (BP) profile generated by conducting exercise stress testing. The parameters considered for profiling were age, gender, height, weight, blood pressure measurement with the risk factors and BMI. The data generated is imparted as training and testing sets to develop an algorithm, which will be able to accurately pre-diagnose cardiovascular health status of a person. Later an expert system can be developed which will assist medical doctors and practitioners to diagnose a patient with heart-related issues with more accuracy and will be able to spread more awareness in people regarding their cardiovascular health status.