Integrated Machine Learning for Accurate Detection of Heart Stroke Diseases

• Published in: 2024 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI) pp. 1 - 8
• Main Authors: A, Kavinilavu, Revathy, Ravi, Parthiban, M, Vishali, R, Malathi, G.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 09.05.2024
• Subjects: Accuracy; classification methods; enhancing prediction precision; Ensemble methods; feature manipulation methods; Heart; Logistic regression; machine learning techniques; Medical diagnostic imaging; predicting heart disease; Predictive models; regression modeling; Subject matter experts; Support vector machines; SVM; the random forest algorithm
• ISBN: 9798350389432
• DOI: 10.1109/ACCAI61061.2024.10602262

Diseases such as CVD (Cardiovascular Diseases) are a major world's health concern that have recently resulted in high mortality rates in India and around the world. As a result, there is an urgent need for an accurate, trustworthy, and useful diagnostic system that can quickly detect these illnesses and enable prompt treatment. In response, scientists are using machine learning techniques to examine intricate medical data sets. Because the heart is so important to circulation, it is critical to accurately predict when cardiac illness will emerge in the medical field. This innovative method aims to automate the analysis of extensive patient data, supporting medical professionals in accurately diagnosing heart-related disorders. This data reservoir is regularly used to gather and store large volumes of patient data, which could one day be applied to forecast when new diseases will manifest. Several data mining and machine learning techniques have been combined in a synergistic way to improve the accuracy of heart illness diagnosis and simulation. These techniques include Logistic Regression, Random Forest Classifier (which is renowned for its exceptional accuracy), Decision Trees, and Support Vector Machines (SVM). The model's predictive performance has increased dramatically as a result of this integration.