Hidden Markov Models for early detection of cardiovascular diseases
Open Access
- 20 December 2023
- journal article
- research article
- Published by Universidad Cooperativa de Colombia - UCC in Ingenieria Solidaria
- Vol. 20 (1) , 1-31
Abstract
Introduction: This article, developed between 2022 and 2023 within the framework of Applied Stochastic Processes by the SciBas group at the Universidad Distrital Francisco José de Caldas, focuses on the role of Hidden Markov Models (HMM) in predicting cardiovascular diseases. Problem: The addressed issue is the need to enhance the early detection of heart diseases, emphasizing how HMM can address uncertainty in clinical data and detect complex patterns. Objective: To evaluate the use of Hidden Markov Models (HMM) in the analysis of electrocardiograms (ECG) for the early detection of cardiovascular diseases. Methodology: The methodology comprises a literature review concerning the relationship between HMM and cardiovascular diseases, followed by the application of HMM to prevent heart attacks and address uncertainty in clinical data. Results: The findings indicate that HMM is effective in preventing heart diseases, yet its effectiveness is contingent upon data quality. These results are promising but not universally applicable. Conclusions: In summary, this study underscores the utility of HMM in early infarction detection and its statistical approach in medicine. It is emphasized that HMM is not infallible and should be complemented with other clinical options and assessment methods in real-world situations. Originality: This work stands out for its statistical and probabilistic approach in the application of Hidden Markov Models (HMM) in medical analysis, offering an innovative perspective and enhancing the understanding of their utility in the field of medicine. Limitations: It is recognized that there are limitations, such as dependence on data quality and variable applicability in clinical cases. These limitations should be considered in the context of their implementation in medical practice.Keywords
This publication has 42 references indexed in Scilit:
- Detection of Apnea Bradycardia from ECG Signals of Preterm Infants Using Layered Hidden Markov ModelAnnals of Biomedical Engineering, 2021
- Apnea bradycardia detection based on new coupled hidden semi Markov modelMedical & Biological Engineering & Computing, 2020
- An intelligent learning approach for improving ECG signal classification and arrhythmia analysisArtificial Intelligence in Medicine, 2020
- Detection of atrial fibrillation using discrete-state Markov models and Random ForestsComputers in Biology and Medicine, 2019
- Hidden Markov Models2019
- Multiclass classification of myocardial infarction with convolutional and recurrent neural networks for portable ECG devicesInformatics in Medicine Unlocked, 2018
- Online apnea–bradycardia detection based on hidden semi-Markov modelsMedical & Biological Engineering & Computing, 2014
- Myocardial infarction classification with multi-lead ECG using hidden Markov models and Gaussian mixture modelsApplied Soft Computing, 2012
- Combining recurrent neural networks with eigenvector methods for classification of ECG beatsDigital Signal Processing, 2009
- PVC detection by the heart-beat interval data—Markov chain approachComputers and Biomedical Research, 1975