Related Experiment Video
Updated: Jan 10, 2026
Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease
Published on: August 9, 2024
Prioritization of patients at risk of heart attack using a novel full-objective ITARA based on Random Forest and
Niloofar Amini1, Sarfaraz Hashemkhani Zolfani2, Fausto Cavallaro3
1Department of Industrial Engineering and Management Systems, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran.
Insights
This study enhances heart attack risk prediction using machine learning with the ITARA method. It improves early detection and clinical management by objectively prioritizing at-risk individuals based on key predictors like coronary artery disease.
Area of Science:
- Cardiology
- Artificial Intelligence
- Decision Science
Background:
- Heart attacks are a leading cause of death, especially in older adults, often linked to lifestyle factors and inadequate prevention.
- Existing risk prediction models lack comprehensive frameworks for prioritizing patients based on multiple clinical factors.
- Effective early identification and risk stratification are crucial for preventing severe cardiac complications.
Purpose of the Study:
- To adapt the Indifference Threshold Based Attribute Ratio Analysis (ITARA) multi-criteria decision-making method into an objective, machine learning-enhanced framework.
- To improve the accuracy and transparency of heart attack risk prioritization by integrating data-driven insights.
- To address the limitations of traditional ITARA by deriving decision thresholds from machine learning models.
Main Methods:
- Adapted Indifference Threshold Based Attribute Ratio Analysis (ITARA), a multi-criteria decision-making (MCDM) technique.
- Integrated machine learning, specifically Random Forest classification, to generate objective variable importance scores.
- Utilized Random Forest model achieving 97% accuracy to derive feature importance values for refining ITARA thresholds.
Main Results:
- The machine learning-enhanced ITARA framework demonstrated improved accuracy in prioritizing individuals at risk of heart attacks.
- Random Forest classification achieved 97% accuracy, providing crucial feature importance values.
- The number of diseased major vessels (Ca) was identified as the most significant predictor of heart attack risk.
Conclusions:
- The integration of machine learning into the ITARA framework offers a transparent, data-driven approach to heart attack risk assessment.
- This enhanced method improves early detection and clinical management strategies for cardiovascular disease.
- The study highlights the potential of objective, multi-criteria decision-making tools in personalized cardiac care.
Abstract:
Heart attacks remain a major cause of morbidity and mortality, particularly among middle-aged and older adults, often aggravated by unhealthy lifestyles and limited preventive care. Early identification and prioritization of at-risk individuals are essential to avoid severe complications. While prediction models exist, they often lack robust frameworks for prioritization across multiple clinical factors. This study addresses the gap by adapting Indifference Threshold Based Attribute Ratio Analysis (ITARA), a multi-criteria decision-making (MCDM) method, into a fully objective framework enhanced by machine learning. Unlike traditional ITARA, which relies on expert-defined thresholds, the proposed approach derives thresholds from variable importance scores generated by classification models. Among the models tested, Random Forest achieved 97% accuracy and was used to produce feature importance values. These scores refined ITARA, improving prioritization accuracy. Results identified the number of major vessels (Ca) as the most critical predictor. By integrating machine learning, the ITARA framework becomes a transparent, data-driven tool that improveWs both early detection and the clinical management of heart attack risks.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
05:41Left Anterior Descending Coronary Artery Ligation for Ischemia-Reperfusion Research: Model Improvement via Technical Modifications and Quality Control
Published on: December 16, 2022
Related Concept Videos
01:26Coronary Artery Disease IV: Preventive Measures
01:26Atherosclerosis III: Management
01:26Heart Failure Drugs: Inhibitors of Renin-Angiotensin System
01:30Coronary Artery Disease I: Introduction
01:28Acute Coronary Syndrome IV: Interprofessional Care
01:30Heart Failure IV: Classification and Diagnostic Evaluation