Detection of Hemorrhagic Brain Arteriovenous Malformations using ML

- The project’s purpose is to develop and improve emergency healthcare services for the rapid and reliable diagnosis of brain bleeding. The conventional approach of manual reviewing of CT and MRI scans is tedious and error-laden. Our method employs Convolutional Neural Networks (CNNs) for feature extraction, combined with Support Vector Machines (SVMs) for classification yielding a 97% average accuracy. To enhance the experience for the users, there is also a chatbot powered by Natural Language Processing (NLP) that aids patients and healthcare professionals in navigating through the diagnosis and the follow-up actions. The efficiency of AI and NLP ensures not only improved diagnostic speed and accuracy, but also assists in real-time scalable solutions for emergency care.