Keywords: Cardio Data
Cardiovascular diseases (CVD) are a leading cause of mortality and morbidity worldwide. For predicting the occurrence of cardiovascular diseases based on a comprehensive dataset containing various risk factors and medical indicators, the author uses ANN. The dataset includes features such as age, gender, blood pressure, cholesterol levels, glucose levels, smoking habits, and alcohol habits. The cardio dataset is preprocessed to standardize the numerical features, to bring them into a single scale. After that, the data was split into 75:25 ratio, 75 percent is of training data, and 25 percent is of test data. Later, an ANN model was built upon them with multiple layers, including input layer, hidden layers and output layer. The appropriate activation functions used for input layer is ReLu, while output layer ran with sigmoid activation function. During training, the model adjusted its weights and biases using backpropagation and optimization algorithms, such as Adam optimizer, to minimize the binary cross-entropy loss function. The binary cross-entropy loss measures the difference between predicted and actual binary labels (presence or absence of CVD). To avoid overfitting, Batch Normalization technique was applied at each of the layers in the ANN model. The performance of the trained and test model is evaluated using metrics called accuracy to assess its ability to correctly classify individuals as having or not having cardiovascular disease. And finally the accuracy of the cardio disease model came to be 72 percent.
Aim
To Predict the Cardio Data Using DL Techniques
Objective
ANN Technique used
Jupyter, Google Collab
— Preview truncated. The complete document (full chapters, references, diagrams, and appendices) is shared with clients as part of project delivery. —
Scan the QR code below and pay via any UPI app, then enter your transaction ID and upload a screenshot so we can confirm it.
UPI ID: yourupi@okhdfcbank