Comprehensive review on machine learning approach for heart disease prediction: Current status and future prospects

Many lives can be saved if disease can be detected at earlier stage. Heart disease diagnosis using traditional medical history is not reliable as your doctor will perform a series of tests to diagnose heart disease. Invasive methods of diagnosis are time consuming and costly. Medical field can be si...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yewale, Deepali, Vijayragavan, S. P.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Many lives can be saved if disease can be detected at earlier stage. Heart disease diagnosis using traditional medical history is not reliable as your doctor will perform a series of tests to diagnose heart disease. Invasive methods of diagnosis are time consuming and costly. Medical field can be significantly benefited if we provide an accurate diagnosis of diseases using advanced Machine Learning (ML) approach. As per the new survey, from last 20 years heart problem has remained the major cause of mortality worldwide so in today’s era, it is necessary to diagnose it quickly and accurately. The contents of paper intend to bring forth a comprehensive survey of ML techniques in projecting heart disease. We review representable research works that has been carried out in this field using machine learning approach for University of California, Irvin (UCI) database. Comparison is only possible if we have some common benchmark on the dataset. Therefore, we have chosen the studies that have implemented machine learning algorithms on the same dataset namely UCI database. Few unaddressed issues and challenges that comparatively received meager attention are discussed, highlighting the future prospects for heart disease prediction and providing pointers to the future research.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0080363