Risk Prediction and Intracranial Hemorrhage Detection of Brain using AIML Techniques

Abstract - Intracranial Brain Hemorrhage (IBH) is a critical neurological condition requiring swift diagnosis and treatment. This paper proposes a dual-pipeline AIML-based solution that integrates risk prediction and hemorrhage detection. Patient vitals such as blood pressure, age, heart rate, and oxygen saturation are processed through a Random Forest classifier to predict IBH risk. Simultaneously, CT scan images are analyzed using a CNN to detect and classify three major hemorrhage types: Epidural, Subdural, and Intraparenchymal. The proposed model achieved an accuracy of 94.7% for prediction and 86.2% for detection. A GUI interface was developed for ease of use by medical professionals. The proposed system improves diagnostic accuracy and supports clinical decision-making. Key Words: Intracranial Hemorrhage, Deep Learning, Random Forest, CNN, CT Scan, Patient Vitals, GUI, Prediction, Classification.