<![CDATA[Disease is crucial to prevent more serious complications. This study implemented a Feedforward Neural Network (FNN) algorithm to build a cardiovascular disease risk prediction model using patient clinical data. The dataset used was sourced from open sources and underwent preprocessing stages such as one-hot encoding and normalization. The model architecture consists of two hidden layers with ReLU and dropout activation functions, and an output layer with a sigmoid function for binary classification. Training was conducted for 100 epochs with a data split ratio of 80:20. Evaluation was carried out using accuracy, precision, recall, F1-score, and confusion matrix metrics. The evaluation results showed that the model achieved a training accuracy of 92% and a testing accuracy of 88%, with an average F1-score of 87.2%. The Confidence Factor value also indicated a high level of confidence in each prediction. These results indicate that the FNN model is effective for cardiovascular disease risk prediction and has the potential to be used as a tool for rapid and accurate medical decision-making.]]>
Copyrights © 2025
