Comparative Analysis of Machine Learning Models for Chronic Disease Indicator Classification Using U.S. Chronic Disease Indicators Dataset - Research Report

Aug 6, 2026

Upload by Ivy

The prevalence of chronic diseases creates major strain on public health systems, requiring more accurate and efficient prediction methods for disease indicators. This study compares four machine learning classifiers—Gradient Boosting Classifier, Support Vector Machine, Logistic Regression, and Random Forest—using the U.S. Chronic Disease Indicators (CDI) dataset. Models are evaluated with accuracy, precision, recall, F1 score, classification reports, and confusion matrices. Gradient Boosting achieves the best results, while SVM and Random Forest remain moderate and Logistic Regression serves as a baseline.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Introduction

Importance of chronic disease prediction

Role of machine learning in healthcare analytics

Key challenges and research motivation

Method and Evaluation (overview)

Comparative Analysis of Machine Learning Models for Chronic Disease Indicator Classification Using U.S. Chronic Disease Indicators Dataset Gregorius Airlangga Information System Study Program, Atma Jaya Catholic University of Indonesia, Indonesia E-Mail: [gregorius.airlangga@atmajaya.ac.id](gregorius.airlangga@atmajaya.ac.id) Received May 14th 2024; Revised Jun 18th 2024; Accepted Jun 23th 2024 Corresponding Author: Gregorius Airlangga Abstract The prevalence of chronic diseases poses significant challenges to public health systems worldwide. This study evaluates the performance of four machine learning models—Gradient Boosting Classifier, Support Vector Machine (SVM), Logistic Regression, and Random Forest—in classifying chronic disease indicators using the U.S. Chronic Disease Indicators (CDI) dataset. The models were assessed based on accuracy, precision, recall, F1 score, classification report, and confusion matrix to determine their effectiveness. The Gradient Boosting Classifier outperformed other models with an accuracy of 64.36%, precision of 63. 72%, recall of 64.36%, and F1 score of 63.88%. While SVM and Random Forest demonstrated moderate performance, Logistic Regression served as a baseline for comparison. The study highlights the Gradient Boosting Classifier's superiority in handling the complexities of the CDI dataset, suggesting its potential for improving chronic disease prediction and management. Future research should focus on refining these models, addressing class imbalances, and incorporating domain knowledge to enhance interpretability and applicability in real-world scenarios. Keyword: Chronic Disease Classification, Chronic Disease Indicators, Gradient Boosting, Machine Learning, Support Vector Machine. 1. INTRODUCTION Chronic diseases, also known as non-communicable diseases (NCDs), have emerged as a leading cause of morbidity and mortality globally, placing immense pressure on healthcare systems and economies [1]–[3] . In the United States, chronic diseases such as heart disease, cancer, and diabetes are responsible for approximately 70% of all deaths, underscoring the urgent need for effective prevention, management, and treatment strategies [4]–[6] . These diseases not only diminish the quality of life for individuals but also contribute significantly to healthcare costs and lost productivity [7] . The growing prevalence of chronic diseases has spurred extensive research efforts aimed at understanding their etiology, risk factors, and optimal intervention approaches [8] . In this context, the application of machine learning (ML) techniques offers promising avenues for enhancing the accuracy and efficiency of chronic disease prediction and management [9] . The integration of machine learning into healthcare analytics has the potential to revolutionize the early detection and diagnosis of chronic diseases [10] . By leveraging vast amounts of health-related data, ML algorithms can identify patterns and correlations that may elude traditional statistical methods [11] . This capability is particularly valuable given the multifactorial nature of chronic diseases, which often involve complex interactions between genetic, environmental, and lifestyle factors [12] . The literature on machine learning in healthcare is extensive, encompassing a wide range of approaches and methodologies. Studies have demonstrated the efficacy of various ML models, including decision trees, support vector machines, neural networks, and ensemble methods, in predicting the onset and progression of chronic diseases [13] . One of the critical challenges in chronic disease research is the accurate classification of disease indicators from large and heterogeneous datasets [14] . Traditional statistical methods, while valuable, often fall short in handling the complexity and high dimensionality of such data. Machine learning techniques, on the other hand, can effectively manage and analyze large-scale datasets, u

FAQs

Which machine learning models are compared for chronic disease indicator classification?

The study evaluates Gradient Boosting Classifier, Support Vector Machine (SVM), Logistic Regression, and Random Forest using the U.S. CDI dataset.

How are the models evaluated in the study?

Performance is assessed using accuracy, precision, recall, F1 score, classification reports, and confusion matrices.

What is the top-performing model and what does the result indicate?

The Gradient Boosting Classifier outperforms the others, indicating stronger capability for capturing complexities within the CDI dataset and supporting improved chronic disease prediction and management.

Aug 6, 2026

Upload by Ivy