A Novel Approach to the Diagnosis of Heart Disease using Machine\n Learning and Deep Neural Networks

2020/07/25 by Sahithi Ankireddy, Ankireddy, Sahithi
Health Professions · #Artificial Intelligence in Healthcare #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.2007.12998

openalex publication_date 2020/07/25 · openalex created_date 2022/09/10 · openalex updated_date 2026/07/28

Abstract

Heart disease is the leading cause of death worldwide. Currently, 33% of\ncases are misdiagnosed, and approximately half of myocardial infarctions occur\nin people who are not predicted to be at risk. The use of Artificial\nIntelligence could reduce the chance of error, leading to possible earlier\ndiagnoses, which could be the difference between life and death for some. The\nobjective of this project was to develop an application for assisted heart\ndisease diagnosis using Machine Learning (ML) and Deep Neural Network (DNN)\nalgorithms. The dataset was provided from the Cleveland Clinic Foundation, and\nthe models were built based on various optimization and hyper parametrization\ntechniques including a Grid Search algorithm. The application, running on\nFlask, and utilizing Bootstrap was developed using the DNN, as it performed\nhigher than the Random Forest ML model with a total accuracy rate of 92%.\n

Related

• On Deep Neural Networks for Detecting Heart Disease
• Predicting Coronary Heart Disease Using a Suite of Machine Learning Models
• Machine Learning and Ensemble Approach Onto Predicting Heart Disease
• Machine Learning-Based Heart Disease Diagnosis: A Systematic Literature Review
• Prediction of Heart Disease Using a Combination of Machine Learning and Deep Learning