IMPLEMENTATION OF EHEALTH FRAMEWORK FOR MEDICAL IMAGE ANALYSIS USING HUMAN-CENTRED ARTIFICIAL INTELLIGENCE FOR CARDIOVASCULAR DISEASES

ABSTRACT

Human-centered artificial intelligence (HCAI) is pivotal for timely diagnosis and prediction of ailments such as hypertension, stroke, and diabetes. This paper explores HCAI's role in early disease detection and immediate treatment solutions for detected diseases. By designing transparent, ethical, and interactive systems, HCAI ensures the best interests of humans are upheld. Leveraging machine learning (ML) techniques, including Decision Tree, Random Forest, and K-Nearest Neighbor. The study attains high predictive accuracy in identifying diseases using ML techniques. The analysisreveals factors influencing healthy living, facilitating early diagnosis. Results indicate a significant improvement of 2% for decision tree and random forest respectively when compared with the baseline studies. Through predictive modeling, HCAI enhances disease analysis efficiency and patient care, offering accurate and timely diagnoses. This underscores the significance of integrating HCAI techniques for improved healthcare outcomes, empowering users with system understanding and control.

Keywords: Medical Imaging, Human-centred, Artificial Intelligence, Machine Learning, Cardiovascular Diseases