Dataset Information

Optimal Length of Heart Rate Variability Data and Forecasting Time for Ventricular Fibrillation Prediction Using Machine Learning.

ABSTRACT: Ventricular fibrillation (VF) is a cardiovascular disease that is one of the major causes of mortality worldwide, according to the World Health Organization. Heart rate variability (HRV) is a biomarker that is used for detecting and predicting life-threatening arrhythmias. Predicting the occurrence of VF in advance is important for saving patients from sudden death. We extracted features from seven HRV data lengths to predict the onset of VF before nine different forecast times and observed the prediction accuracies. By using only five features, an artificial neural network classifier was trained and validated based on 10-fold cross-validation. Maximum prediction accuracies of 88.18% and 88.64% were observed at HRV data lengths of 10 and 20 s, respectively, at a forecast time of 0 s. The worst prediction accuracy was recorded at an HRV data length of 70 s and a forecast time of 80 s. Our results showed that features extracted from HRV signals near the VF onset could yield relatively high VF prediction accuracies.

SUBMITTER: Jeong DU

PROVIDER: S-EPMC10435312 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Optimal Length of Heart Rate Variability Data and Forecasting Time for Ventricular Fibrillation Prediction Using Machine Learning.

Jeong Da Un DU Taye Getu Tadele GT Hwang Han-Jeong HJ Lim Ki Moo KM

Computational and mathematical methods in medicine 20210316

Ventricular fibrillation (VF) is a cardiovascular disease that is one of the major causes of mortality worldwide, according to the World Health Organization. Heart rate variability (HRV) is a biomarker that is used for detecting and predicting life-threatening arrhythmias. Predicting the occurrence of VF in advance is important for saving patients from sudden death. We extracted features from seven HRV data lengths to predict the onset of VF before nine different forecast times and observed the ...[more]

PMID: 37601811

Similar Datasets

Project description:Hypertrophic cardiomyopathy (HCM) is frequently associated with sudden cardiac death, presumably due to the development of malignant arrhythmias. The risk of sudden cardiac death due to HCM has been reported to be predicted by assessing electrocardiographic (ECG) changes including frequencies and complexities of arrhythmias as well as heart rate variability (HRV) as an assessment of autonomic balance. Sudden cardiac death in association with naturally-occurring left ventricular hypertrophy (LVH) has been reported in a colony of rhesus macaques and is under investigation as a potential non-human primate model of human HCM. In the present study, 10 rhesus macaques with LVH and 10 without the signs of LVH confirmed by an echocardiographic examination were recruited for assessing ECG and HRV parameters. ECG morphology on 10-s, 6-lead ECG analysis, and the frequency and complexity of arrhythmias as well as HRV on 20-h ambulatory ECG Holter analyses were assessed. On the standard 10-s 6-lead ECG analysis, P wave and QRS complex duration as well as the QRS complex amplitude were significantly increased in the LVH-affected rhesus macaques compared to control rhesus macaques. Analysis of 20-h Holter monitoring revealed no statistically significant differences in the frequency or the complexity of arrhythmias between the LVH and the control groups. Several HRV parameters were smaller in the LVH group than the control group throughout the majority of Holter recordings showing periods of reduced variability, however, no statistically significant differences were achieved across groups and/or time points. These findings indicate that ECG analysis and Holter monitoring of rhesus macaques are feasible and that ECG morphological changes in association with LVH could be used as a possible component of an antemortem screening tool. The rhesus macaques of this study did not reveal clear indications of risk for sudden cardiac death. Further studies are necessary to determine the etiology of sudden cardiac death due in LVH affected rhesus macaques and identify if any parameters of arrhythmia assessment or HRV can be used to predict the development of sudden cardiac death.

Dataset Information

Optimal Length of Heart Rate Variability Data and Forecasting Time for Ventricular Fibrillation Prediction Using Machine Learning.

Publications

Optimal Length of Heart Rate Variability Data and Forecasting Time for Ventricular Fibrillation Prediction Using Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets