AN ANALYSIS ON SUPERVISED MACHINE LEARNING ALGORITHMS FOR HEALTHCARE PREDICTIVE ANALYTICS

Abstract

Aim: The aim is to develop a Decision Vector Machine (DVM) model for cardiovascular medical record analysis.

Background: Predictive analytics in healthcare industry on patient for the risk identification and intervention facilitation plays a major role in modern healthcare systems.

Methodology: This work assess the patient medical data and effectively uses an algorithm to predicts the heart failure.

Contribution: The dataset is analyzed using the DVM approach and includes medical history, NYHA classification, and demographic data. DVM classifies the data to find the cardio vascular disease.

Findings: The results show how effectively the DVM method forecasts the patient population's heart failure trajectory. Promising performance are achieved by the model in its high accuracy classification. Interpretability of the model also offers information about the important factors influencing the categorization choices. The results show, all things considered, how supervised machine learning—especially the DVM algorithm—can improve patient management and risk classification in healthcare predictive analytics.

Recommendations for Researchers:: To finds how well the DVM algorithm predicts the heart failure rate using classification, medical history, and demographic data. To Work on the findings the features for classification and offer understanding of the fundamental causes of illness.