AI-Driven Healthcare System: Transforming Disease Detection and Prevention for a Healthy Future

A rising number of chronic and acute illnesses requires the development of an advanced medical system with early detection and prevention skills. Traditional methods usually need expensive equipment and expert medical knowledge which limits accessibility and delays emergency treatment. In order to address these problems this study proposes an AI- driven healthcare platform that integrates several health parameters utilizing methods from deep learning as well as machine learning and uses data from watches to continuously monitor people's daily health. The ideal number of groups in the system which employs K-Means and Agglomerative Clustering, is ascertained using the Elbow Method. K-Means achieves a silhouette score of 0.85 indicating outstanding clustering effectiveness. Furthermore, the framework classifies illnesses into No Dementia, Very Mild Disease, Mild Dementia and Moderate Dementia using cutting-edge deep learning models like Inception V3, ResNet50, and VGG19 for brain disease detection. These models achieve test accuracies of 90.94%, 79.55% and 93.14% respectively. Similarly, CNN-based models use multiple layers of perception on textual data to detect skin disorders with 95% accuracy lung conditions with 92.15% accuracy during testing, blood-related cancer stages with 95% reliability and cardiovascular conditions with 99.17% accuracy. Additionally, a Decision Tree Classification uses textual data to efficiently classify liver disorders with 98% accuracy. Streamlit UI which offers an easy-to-use interface for disease diagnosis, real-time health monitoring and customized preventive interventions is used to implement the system. This system seeks to transform illness detection and prevention by fusing cutting-edge AI algorithms with actual health data, thereby improving accessibility, health outcomes and individualized healthcare management