Stroke Risk Prediction Using Deep Neural Networks: Empowering Healthcare Services for Early Identification and Prevention

The objective of this study is to develop a predictive model for identifying individuals at risk of stroke in order to support healthcare services. The model incorporates several key characteristics that play a vital role in determining an individual's susceptibility to stroke. By considering inputs such as blood sugar level, glucose level, weight, age, and other relevant parameters, the goal is to accurately predict whether a person is prone to experiencing a stroke. Early detection and prevention can be initiated promptly for individuals identified as high-risk. To achieve this, the model employs Deep Neural Networks (DNN) as the underlying framework for creating the classifier. Prior to feeding the data into the neural network, a preprocessing step is performed to appropriately format and prepare the dataset. The neural network utilizes ReLU and sigmoid activation functions to make predictions based on the input data. Through the research efforts, A predictor has been successfully developed, achieving an impressive accuracy rate of 90% when predicting stroke risk based on user information. By leveraging the power of deep learning techniques and utilizing a comprehensive set of user inputs, the model holds great potential for aiding in the early identification and prevention of stroke cases. This research contributes to the ongoing efforts in healthcare to enhance stroke risk assessment and improve patient outcomes.