“HEART STROKE PREDICTION”
A predictive analytics approach for heart stroke prediction using machine learning and neural networks
MS. KIRUBADEVI (AP/IT)
ROOBHASRI.S PAVITHRA.S PREETHI.G
BACHELOR OF TECHNOLOGY - 1ST YEAR DEPARTMENT OF ARTIFICIAL INTELLIGENCE AND DATA SCIENCE SRI SHAKTHI INSTITUTE OF ENGINEERING AND TECHNOLOGY
(AUTONOMOUS)
COIMBATORE - 641062
___________________________________________________________________________
ABSTRACT
Stroke is a common ailment that affects many people worldwide. Unfortunately, the statistics reveal that in the current era, about one person dies every minute due to heart stroke. This underscores the significance of utilizing data science in healthcare as it enables professionals to process vast amounts of data that are paramount in conducting research, diagnosis, treatment, and monitoring of stroke patients. In order to develop a predictive model for heart stroke. The proposed model considers various factors such as age, gender, average glucose level, smoking status, body mass index, work type and residence type to predict the likelihood of a person having a heart stroke. Data science algorithms and techniques are used to process and analyze the large amount of healthcare data available. This automated prediction process helps in identifying the risks associated with heart stroke and alerts the patient well in advance. Overall, this study highlights the significance of data science in improving healthcare outcomes and reducing the mortality rate due to heart stroke. Our research aims to develop a model that can accurately predict the risk of heart stroke in patients and classify their risk level. To achieve this goal, we will employ various data mining techniques, including machine learning algorithms like Random Forest, Naïve Bayes, Logistic Regression, K-Nearest Neighbor (KNN), Decision Tree, and Support Vector Machine (SVM). By analysing and processing the data collected from patients, we aim to create a reliable and effective tool that can aid healthcare professionals in identifying patients at high risk of heart stroke and provide timely interventions to prevent or minimize their risk.
Keywords – Machine Learning, Data analysis, Decision Tree, SVM, KNN, Naïve Bayes Heart stroke, Random Forest