Predictive Modeling of Heart Failure Using Health Parameters and Machine Learning Techniques - Clinical decision support model evaluation

Aug 3, 2026

Upload by Maeve

Machine learning models are evaluated for predicting heart failure using a dataset compiled from multiple sources across different locations. The workflow includes data preprocessing and statistical analysis to detect significant correlations between lifestyle characteristics and heart failure incidence. Multiple algorithms—Logistic Regression, Support Vector Machine, Random Forest, k-nearest neighbors, Extra Trees, Gradient Boosting, and CatBoost—are trained and assessed with accuracy, feature importance, confusion matrix, and ROC curve metrics. Random Forest delivers the strongest performance, supporting more accurate prediction for clinical decision support systems.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages21

Reading Time53 min

AccessFree to download

Introduction

Research objectives and study structure

Related Work

Methodology

Data analysis and model development

Evaluation metrics

Results Obtained

Data analysis and model interpretation

Performance assessment

Conclusions

Predictive Modeling of Heart Failure Using Health Parameters and Machine Learning Techniques Victor Moisés Silveira Santos1* Erika Carlos Medeiros 1 Patrícia Cristina Moser 1 Jorge Cavalcanti Barbosa Fonsêca 1 Rômulo César Dias de Andrade 1 Fernando Ferreira de Carvalho 1,2,3 Fernando Pontual de Souza Leão Junior 1 Marco Antônio de Oliveira Domingues2 1. Universidade de Pernambuco, Caruaru, PE, Brazil 2. Instituto Federal de Ciência e Tecnologia de Pernambuco, Recife, PE, Brazil 3. Cesar School, Recife, PE, Brasil *E-mail do autor correspondente: [erika.medeiros@upe.br](erika.medeiros@upe.br) Abstract This study conducts a comprehensive analysis of machine learning models' potential in predicting heart failure using a dataset compiled from multiple sources across various locations. Through data preprocessing and analysis, significant correlations were identified between lifestyle characteristics and heart failure incidence. Several machine learning models, including Logistic Regression, Support Vector Machine, Random Forest, Knearest neighbors, Extra trees, Gradient Boosting, and CatBoost, were developed, trained, and evaluated using performance metrics such as accuracy, feature importance, confusion matrix, and the ROC curve. The Random Forest model exhibited superior performance, emphasizing its robustness and effectiveness in heart failure prediction. This research underscores the significance of applying machine learning to enhance predictive accuracy and provides key insights for future applications in clinical decision support systems, suggesting directions for further research in expanding the models to encompass a broader range of cardiovascular conditions according to individual lifestyle. Keywords: Heart Failure Prediction, Machine Learning Models, Lifestyle Characteristics, Clinical Decision Support Systems. DOI: 10.7176/RHSS/14-6-01 Publication date: June 30th 2024 1. Introdution Amidst the continuous evolution of the global health landscape, the ongoing rise in concerns related to heart disease and heart failure stands out as a pressing demand within the medical community (Groenewegen et al., 2020) . Heart Failure, a condition that significantly affects the heart's ability to pump blood effectively throughout the body, poses a substantial challenge for both healthcare systems and patients' quality of life. Data reveals a growing prevalence of these conditions, underscoring the urgent need for effective prediction methods to enable early diagnoses and informed medical decisions. In 2019, heart failure alongside other cardiovascular diseases led as the primary cause of mortality worldwide, comprising approximately 85%(Who, 2019) . The application of artificial intelligence (AI) in the context of heart failure prediction emerges as a promising approach (Yu et al., 2018), leveraging significant technological advances and the availability of extensive medical datasets. Recent statistics indicate a sharp increase in the quantity of available clinical information, allowing advanced machine learning algorithms to thoroughly analyze these data for relevant patterns. Furthermore, with the continuous application of artificial intelligence in various health-related studies, specifically in disease prediction, proposing its use for heart failure prediction becomes a promising and relevant proposition. However, it is crucial to recognize that this advancement is not without challenges, and ethical issues such as algorithmic bias and data privacy protection require careful consideration and heightened reliability, as we are dealing with the prediction of a disease. This scenario highlights the pressing need to understand the capabilities and limitations (Hickman et al., 2021) of AI tools, adapting them insightfully to clinical needs. The effective integration of these technologies will not only provide tangible benefits for heart failure prediction but also substantially contribute to advancemen

FAQs

What is the main goal of this study on heart failure prediction?

To develop and evaluate machine learning models that predict heart failure probability using lifestyle-related characteristics and health parameters.

Which machine learning models are trained and compared?

Logistic Regression, Support Vector Machine, Random Forest, k-nearest neighbors, Extra Trees, Gradient Boosting, and CatBoost are developed, trained, and compared.

Why is Random Forest highlighted in the results?

It achieves superior performance based on evaluation metrics such as accuracy, confusion matrix, feature importance, and the ROC curve.

Aug 3, 2026

Upload by Maeve