Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.11851/11429
Title: Applications of Machine Learning for Predicting Heart Failure
Authors: Boughorbel, Sabri
Himeur, Yassine
Salman, Hüseyin Enes
Bensaali, Faycal
Farooq, Faisal
Yalçın, Hüseyin Çağatay
Publisher: John Wiley & Sons Ltd.
Source: Boughorbel, S., Himeur, Y., Salman, H. E., Bensaali, F., Farooq, F., & Yalcin, H. C. (2022). Applications of Machine Learning for Predicting Heart Failure. Predicting Heart Failure: Invasive, Non‐Invasive, Machine Learning and Artificial Intelligence Based Methods, 171-188.
Abstract: This chapter provides an introduction to the use of machine learning (ML) for the diagnosis of heart failure (HF). ML is the field responsible for developing methods and tools that can learn and make decisions based on data. The growing number of HF patients and increasing healthcare costs indicate the importance of the early diagnosis of HF for efficient treatment planning. The chapter considers the example of HF diagnosis using electrocardiogram (ECG) data. ECGs are performed in addition to physical examination and disease history investigation of the patient. ML has gained a growing importance in cardiovascular medicine, especially for the detection and diagnosis of HF. Based on the nature of the ML algorithms used for detection and diagnosis of HF, four classes can be identified: supervised learning models, unsupervised learning models, semi-supervised learning models, and reinforcement learning models. The use of electronic health record is an important research direction for predicting HF.
URI: https://doi.org/10.1002/9781119813040.ch8
https://hdl.handle.net/20.500.11851/11429
ISBN: 9781119813040
Appears in Collections:Makine Mühendisliği Bölümü / Department of Mechanical Engineering

Show full item record



CORE Recommender

Page view(s)

90
checked on Nov 4, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.