Published Paper Details:

ABSTRACT This study explores heart disease prediction using Single-Layer Perceptron (SLP) and Multi-Layer Perceptron (MLP) models. The research begins with Exploratory Data Analysis (EDA) to gain insights into the dataset, including attribute types, data distribution, and identification of missing or duplicate values. The SLP model, with a single hidden layer, classifies patients based on essential clinical attributes, while the MLP model leverages multiple hidden layers for deeper feature extraction. The performance of both models was evaluated and compared based on accuracy. Results indicate that the SLP model outperforms the MLP in this specific context due to the dataset's linear separability. The study emphasizes the importance of selecting appropriate machine learning models based on dataset characteristics. Additionally, it highlights the need for careful handling of challenges and limitations to ensure robust predictions, ultimately supporting better clinical decision-making.