AN ADVANCED MACHINE LEARNING (ML) ARCHITECTURE FOR HEART DISEASE DETECTION, PREDICTION AND CLASSIFICATION USING MACHINE LEARNING

Cardiovascular diseases (CD) are the common cause of death worldwide over in developed as well as underdeveloped and developing countries. Early detection and continuous supervision can reduce the mortality rate. Cardiovascular disease diagnosis and accurate diagnosis to enable early treatment. Some of these techniques do not easily diagnose heart diseases at early stages hence, getting treatment late poses a big risk. The present work attempts to better predict this disease from the chest pain symptom, and classify it by designing an efficient machine learning system based on a dataset with 303 patient data made available to the public domain. The four machine learning algorithms that were used for the analysis include Logistic Regression, Random Forest, Support Vector Machines, and Neural Networks to determine which of them is most appropriate for predicting heart diseases. Original data was preprocessed by handling missing values, normalizing features, and using feature extraction techniques. Splitting the dataset into 80% training and 20% testing, cross-validation was performed to validate outcomes on all four models. Although the highest accuracy was reached by the model of the Neural Network by 97%, it was revealed to have tendencies of overfitting. The SVM model achieved the highest accuracy of 97%, and was the most stable and interpretable; therefore, it was considered to be the most suitable for clinical use. Base on the study, there is a promise to champion the use of machine learning models for timely diagnosis of heart diseases by medical practitioners to enhance patient success rates and the overworked health facilities’ performance. The next steps will consist in enlarging a database and implementing these models in supporting clinical practice with real-time diagnostic potential. As a result, the doctors can visualize the patient’s real-time sensor data using the application and start live video streaming if instant medication is required. The proposed system is notified at once through GSM technology.