A Clinical Data Analysis Based Diagnostic Systems for Heart Disease Prediction Using Ensemble Method

The correct diagnosis of heart disease can save lives, while the incorrect diagnosis can be lethal. The UCI machine learning heart disease dataset compares the results and analyses of various machine learning approaches, including deep learning. We used a dataset with 13 primary characteristics to c...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Big Data Mining and Analytics Ročník 6; číslo 4; s. 513 - 525
Hlavní autoři: Kumar, Ankit, Singh, Kamred Udham, Kumar, Manish
Médium: Journal Article
Jazyk:angličtina
Vydáno: Beijing Tsinghua University Press 01.12.2023
Témata:
Algorithms
artificial intelligence
Cardiovascular disease
cleveland dataset
Data analysis
Datasets
Deep learning
Diagnostic systems
Heart
Heart diseases
human sensing
logistic regression
Machine learning
Regression analysis
supervised algorithm
support vector machine
Support vector machines
ISSN:2096-0654, 2097-406X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The correct diagnosis of heart disease can save lives, while the incorrect diagnosis can be lethal. The UCI machine learning heart disease dataset compares the results and analyses of various machine learning approaches, including deep learning. We used a dataset with 13 primary characteristics to carry out the research. Support vector machine and logistic regression algorithms are used to process the datasets, and the latter displays the highest accuracy in predicting coronary disease. Python programming is used to process the datasets. Multiple research initiatives have used machine learning to speed up the healthcare sector. We also used conventional machine learning approaches in our investigation to uncover the links between the numerous features available in the dataset and then used them effectively in anticipation of heart infection risks. Using the accuracy and confusion matrix has resulted in some favorable outcomes. To get the best results, the dataset contains certain unnecessary features that are dealt with using isolation logistic regression and Support Vector Machine (SVM) classification.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2096-0654
2097-406X
DOI:10.26599/BDMA.2022.9020052