Published on February 2019 | Machine Learning
Heart failure is long-lasting, progressive that is life threatening and leads to death. The patients with Heart Failure (HF) subjected to medical observation for their remaining days. In this paper, we have presented a Medical Decision Support System (MDSS) for the examination of Heart Failure patients for providing various outputs such as HF Criticality Assessment, HF type prediction and a management interface that compares with different patients reports. The proposed system composed of a portion of Intelligent Core and one HF special purpose management tool. The management tool offers the function to act as an interface the usage of Artificial Intelligence and its training. We followed a Machine Learning (ML) method to implement smart intelligent roles. Here we have related the performance of a system with fuzzy rules that are produced inherently, a neural networks, Random Forest algorithm, and Support Vector Machine (SVM) for analyzing our database. Comparison of HF Criticality Assessment and Type predictions are evaluated by using Random Forest Algorithm. The management tool permits the cardiologist to reside on a supervised database that is appropriate for Machine Learning during his daily consultation. The Machine Learning system automatically provides the readable output based on the condition of the patient that can be understandable by other doctors and even nurses.