A Heart Disease Prediction Model using SVM-Decision Trees-Logistic Regression (SDL)

Mythili, T; Mukherji, Dev; Padalia, Nikita; Naidu, A. Naga Bhushan

doi:10.5120/11662-7250

Cited by 51 publications

(20 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LR [9], [17], [30] provides high accurateness plus chart illustration. In this algorithm, facts must be imported primary and then trained.…”

Section: Logistic Regression Classifier (Lr)mentioning

confidence: 99%

See 1 more Smart Citation

A Relative Research of Machine Learning Build Heart Disease Forecast Model

Agrawal¹,

Soni²,

Gupta³

2020

SKIT Research Journal

View full text Add to dashboard Cite

Nowadays, heart disease is the leading cause of death globally, with an estimated 610000 lives each year due to heart condition. One of the most common causes of heart disease is high blood pressure (HBP), fasting blood sugar (FBS), diabetes, cholesterol, Body mass Index (BMI), heart rate (HR). Diagnosis of heart disease is more prevalent nowadays; this involves a lot of accuracy and uncertainty due to the large-scale data decision-based on doctors may fail in some cases. Data mining is an intelligent diagnostic tool in healthcare. Thus, it is imperative to predict that each menace stage depends on age, sex, blood pressure, diabetes symptoms, what we can do for precaution by diagnosing the disease and proper treatment at the right moment. The purpose of the research work is to develop different predictive models using different forecasting measures and perform comparative analysis. In this work, we have used Cleveland and Statlog datasets with Naive Bayes (NB), K-Nearest Neighbors (KNN), and Logistic Regression (LR), Support vector machine (SVM), Decision Tree (DT), and Random Forest (RF) Classifier to develop various predictors. The experiment result shows that the random forest classifier gives better accuracy and results on both datasets when we perform a comparative analysis of them among all other classification models

show abstract

“…LR [9], [17], [30] provides high accurateness plus chart illustration. In this algorithm, facts must be imported primary and then trained.…”

Section: Logistic Regression Classifier (Lr)mentioning

confidence: 99%

“…Six classifiers (e.g., Naive Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Logistic Regression (LR), and Random Forest (RF)) were selected to create the model with the maximum accuracy possible [5], [15]- [17].…”

Section: Problem Definitionmentioning

confidence: 99%

A Relative Research of Machine Learning Build Heart Disease Forecast Model

Agrawal¹,

Soni²,

Gupta³

2020

SKIT Research Journal

View full text Add to dashboard Cite

show abstract

“…SRM in SVM is used to guarantee the upper limit of generalization in the data collection by controlling the capacity (flexibility) of learning outcomes hypothesis [4]. SVM has been used extensively to classify several medical problems, such as diabetes and pre-diabetes classification [5], breast cancer [6] and a heart disease [7] . Based on previous study in liver disease dataset, SVM is known as the classifier compared to naïve bayes.…”

Section: Svm Work Based On the Principle Of Structural Risk Minimizamentioning

confidence: 99%

Effects of Oversampling SMOTE in the Classification of Hypertensive Dataset

Matondang¹,

Surantha²

2020

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Hypertensive or high blood pressure is a medical condition that can be driven by several factors. These factors or variables are needed to build a classification model of the hypertension dataset. In the construction of classification models, class imbalance problems are often found due to oversampling. This research aims to obtain the best classification model by implementing the Support Vector Machine (SVM) method to get the optimal level of accuracy. The dataset consists of 8 features and a label with two classes: hypertensive and non-hypertensive. Overall test result performance is then compared to assess between SVM combined with SMOTE and not. The results show that SMOTE can improve the accuracy of the model for unbalanced data into 98% accuracy compared to 91% accuracy without SMOTE.

show abstract

“…These tools and approaches help analyze and interpret large datasets. Many factors contribute to heart diseases, including age, weight, height, gender, cholesterol, ECG results, blood pressure, chest pain, smoking, obesity, and eating habits [9]. The traditional approaches for heart disease risk diagnosis rely on a physician's study of a patient's medical history, physical examination report, and relevant symptoms, leading to inaccuracies and delays in diagnosis [10], [11].…”

Section: Introductionmentioning

confidence: 99%

Enhanced accuracy for heart disease prediction using artificial neural network

Sarra

Dinar

Mohammed

2022

IJEECS

View full text Add to dashboard Cite

Making an accurate and timely diagnosis of cardiac disease is critical for preventing and treating heart failure. The accuracy of results produced by traditional machine learning (ML) algorithms is satisfactory. On the other hand, deep learning algorithms result in higher prediction accuracy. In this study, we used an artificial neural network (ANN) model to construct a deep learning diagnosis system for heart disease prediction. The developed ANN prediction model achieved 93.44% accuracy, which is 7.5% higher than a traditional ML model support vector machine (SVM). Additionally, using a simpler neural network reduced the time taken for training and classification to less than a minute.

show abstract

A Heart Disease Prediction Model using SVM-Decision Trees-Logistic Regression (SDL)

Cited by 51 publications

References 12 publications

A Relative Research of Machine Learning Build Heart Disease Forecast Model

A Relative Research of Machine Learning Build Heart Disease Forecast Model

Effects of Oversampling SMOTE in the Classification of Hypertensive Dataset

Enhanced accuracy for heart disease prediction using artificial neural network

Contact Info

Product

Resources

About