Prediction of Heart Disease Based on Robust Artificial Intelligence Techniques

Heart disease (HD) is a concerning health condition that demands immediate attention. This article employs three artificial intelligence classification algorithms: DT, NB, and SGD to address this issue. The primary goal is to determine the most effective algorithm for early-stage prediction of heart disease, using easily accessible patient information. A dataset of 290 simple input variables, including sex, age, ??? blood sugar, fasting blood sugar levels, and maximal heart rate, was collected from a hospital in Armenia. The results reveal that the DT algorithm outperforms NB and SGD in accuracy, with CAtrain of 0.96 and CAtest of 0.93. Accurate early prediction enables timely interventions and support for patients, improving healthcare management. Leveraging artificial intelligence, particularly DT, enables swift identification of potential heart disease cases, aiding healthcare professionals in providing essential care and preventive measures. Furthermore, the pragmatic approach of employing easily accessible patient data for prediction underscores the feasibility and applicability of the proposed methodology. By relying on readily available and cost-effective information, medical practitioners can efficiently screen and diagnose individuals at risk of heart disease, leading to improved healthcare management and better patient outcomes.