Heart Disease Prediction with Machine Learning-Based Approaches

Ayhan Küçükmanisa; Zeynep Hilal Kilimci

Makale detayları

Heart Disease Prediction with Machine Learning-Based Approaches

Yazarlar:

Ayhan Küçükmanisa | Zeynep Hilal Kilimci

Yayıncı:

Sakarya University

Ana Başlıklar:

Machine Learning (Other)

Dergi:

Sakarya University Journal of Science Vol.28 Issue 1, pp.101-107

Belge Tipi:

Makale

Yayın Tarihi:

2/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001312274

pISSN:

2147-835X

Anahtar kelimeler:

Özet:

 Heart disease, a global ailment with substantial mortality rates, poses a significant health concern. The prevalence of heart disease has escalated due to the demanding nature of contemporary occupations and inherent genetic predispositions. Hence, timely detection of cardiac disorders is paramount to preserving lives. However, the analysis of routine clinical data presents a formidable challenge in identifying cardiovascular ailments. Leveraging machine learning approaches to scrutinize clinical data can furnish effective solutions for informed decision-making and precise prognostications. This research endeavors to predict heart disease by examining the data of 303 individuals encompassing 14 distinct categories. Several machine learning methodologies, namely K-Nearest Neighbor, Gaussian Naive Bayes, Logistic Regression, Random Forest, Gradient Boosting, and Artificial Neural Networks, are proposed as potential remedies to address the problem. The experimental findings unveil that Gradient Boosting attains a remarkable accuracy of 95 and Artificial Neural Networks exhibit a commendable accuracy of 90.1, establishing them as the most successful models in this study. These results underscore the superior performance of the proposed techniques vis-à-vis the existing literature.

 Heart disease, a global ailment with substantial mortality rates, poses a significant health concern. The prevalence of heart disease has escalated due to the demanding nature of contemporary occupations and inherent genetic predispositions. Hence, timely detection of cardiac disorders is paramount to preserving lives. However, the analysis of routine clinical data presents a formidable challenge in identifying cardiovascular ailments. Leveraging machine learning approaches to scrutinize clinical data can furnish effective solutions for informed decision-making and precise prognostications. This research endeavors to predict heart disease by examining the data of 303 individuals encompassing 14 distinct categories. Several machine learning methodologies, namely K-Nearest Neighbor, Gaussian Naive Bayes, Logistic Regression, Random Forest, Gradient Boosting, and Artificial Neural Networks, are proposed as potential remedies to address the problem. The experimental findings unveil that Gradient Boosting attains a remarkable accuracy of 95 and Artificial Neural Networks exhibit a commendable accuracy of 90.1, establishing them as the most successful models in this study. These results underscore the superior performance of the proposed techniques vis-à-vis the existing literature.

 Heart disease, a global ailment with substantial mortality rates, poses a significant health concern. The prevalence of heart disease has escalated due to the demanding nature of contemporary occupations and inherent genetic predispositions. Hence, timely detection of cardiac disorders is paramount to preserving lives. However, the analysis of routine clinical data presents a formidable challenge in identifying cardiovascular ailments. Leveraging machine learning approaches to scrutinize clinical data can furnish effective solutions for informed decision-making and precise prognostications. This research endeavors to predict heart disease by examining the data of 303 individuals encompassing 14 distinct categories. Several machine learning methodologies, namely K-Nearest Neighbor, Gaussian Naive Bayes, Logistic Regression, Random Forest, Gradient Boosting, and Artificial Neural Networks, are proposed as potential remedies to address the problem. The experimental findings unveil that Gradient Boosting attains a remarkable accuracy of 95 and Artificial Neural Networks exhibit a commendable accuracy of 90.1, establishing them as the most successful models in this study. These results underscore the superior performance of the proposed techniques vis-à-vis the existing literature.

 Heart disease, a global ailment with substantial mortality rates, poses a significant health concern. The prevalence of heart disease has escalated due to the demanding nature of contemporary occupations and inherent genetic predispositions. Hence, timely detection of cardiac disorders is paramount to preserving lives. However, the analysis of routine clinical data presents a formidable challenge in identifying cardiovascular ailments. Leveraging machine learning approaches to scrutinize clinical data can furnish effective solutions for informed decision-making and precise prognostications. This research endeavors to predict heart disease by examining the data of 303 individuals encompassing 14 distinct categories. Several machine learning methodologies, namely K-Nearest Neighbor, Gaussian Naive Bayes, Logistic Regression, Random Forest, Gradient Boosting, and Artificial Neural Networks, are proposed as potential remedies to address the problem. The experimental findings unveil that Gradient Boosting attains a remarkable accuracy of 95 and Artificial Neural Networks exhibit a commendable accuracy of 90.1, establishing them as the most successful models in this study. These results underscore the superior performance of the proposed techniques vis-à-vis the existing literature.

Makale detayları

Heart Disease Prediction with Machine Learning-Based Approaches

Yazarlar: Ayhan Küçükmanisa | Zeynep Hilal Kilimci

Yayıncı: Sakarya University

Ana Başlıklar: Machine Learning (Other)

Dergi: Sakarya University Journal of Science Vol.28 Issue 1, pp.101-107

Belge Tipi: Makale

Yayın Tarihi: 2/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001312274

pISSN: 2147-835X

Heart Disease Prediction

Machine Learning

Artificial Neural Networks

Gradient Boosting

Sayı

Yazarlar:

Ayhan Küçükmanisa | Zeynep Hilal Kilimci

Yayıncı:

Sakarya University

Ana Başlıklar:

Machine Learning (Other)

Dergi:

Sakarya University Journal of Science Vol.28 Issue 1, pp.101-107

Belge Tipi:

Makale

Yayın Tarihi:

2/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001312274

pISSN:

2147-835X