Enhanced Bayesian Optimized Support Vector Machine (BO-SVM) Classification and Prediction of Heart Disease

Medical data analysis is increasingly used to plan, improve research techniques, and explain diagnoses. The allocation of medical resources is based on the prevalence of specific pathologies. Artificial intelligence (AI) offers robust software solutions to analyze existing data and provide optimal predictions of medical outcomes. The dataset for heart disease prediction consists missing values in important features like cholesterol, ECG results and lifestyle factors. This research focuses to solve the issues in the traditional machine learning algorithm and designing a system model incorporating multiple data processing algorithms to classify heart disease. The classification process allows for the generation of a predictive model from training and testing datasets. These datasets are processed using an algorithm for classification to create a new model that can analyze detailed data, potentially with these same classes, by combining computational techniques with mathematical tools. This study uses optimization strategies to improve this model's performance and maximize prediction outcomes. This study aims to provide a framework to forecast cardiac problems based on significant risk using various classifier techniques, including the Bayesian Optimized SVM, to variables. The UCI repository is the source of the dataset utilized in this investigation. Linear Discriminant Analysis is used for feature extraction to decrease dimensionality and enhance the model's capacity to identify relevant patterns in the data. To generate the results as a precision, Recall, f1 score and accuracy.
Published in: 2025 4th International Conference on Sentiment Analysis and Deep L