Dataset Information

ECG-based prediction algorithm for imminent malignant ventricular arrhythmias using decision tree.

ABSTRACT: Spontaneous prediction of malignant ventricular arrhythmia (MVA) is useful to avoid delay in rescue operations. Recently, researchers have developed several algorithms to predict MVA using various features derived from electrocardiogram (ECG). However, there are several unresolved issues regarding MVA prediction such as the effect of number of ECG features on a prediction remaining unclear, possibility that an alert for occurring MVA may arrive very late and uncertainty in the performance of the algorithm predicting MVA minutes before onset. To overcome the aforementioned problems, this research conducts an in-depth study on the number and types of ECG features that are implemented in a decision tree classifier. In addition, this research also investigates an algorithm's execution time before the occurrence of MVA to minimize delays in warnings for MVA. Lastly, this research aims to study both the sensitivity and specificity of an algorithm to reveal the performance of MVA prediction algorithms from time to time. To strengthen the results of analysis, several classifiers such as support vector machine and naive Bayes are also examined for the purpose of comparison study. There are three phases required to achieve the objectives. The first phase is literature review on existing relevant studies. The second phase deals with design and development of four modules for predicting MVA. Rigorous experiments are performed in the feature selection and classification modules. The results show that eight ECG features with decision tree classifier achieved good prediction performance in terms of execution time and sensitivity. In addition, the results show that the highest percentage for sensitivity and specificity is 95% and 90% respectively, in the fourth 5-minute interval (15.1 minutes-20 minutes) that preceded the onset of an arrhythmia event. Such results imply that the fourth 5-minute interval would be the best time to perform prediction.

SUBMITTER: Mandala S

PROVIDER: S-EPMC7224460 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

ECG-based prediction algorithm for imminent malignant ventricular arrhythmias using decision tree.

Mandala Satria S Cai Di Tham T Sunar Mohd Shahrizal MS Adiwijaya

PloS one 20200514 5

Spontaneous prediction of malignant ventricular arrhythmia (MVA) is useful to avoid delay in rescue operations. Recently, researchers have developed several algorithms to predict MVA using various features derived from electrocardiogram (ECG). However, there are several unresolved issues regarding MVA prediction such as the effect of number of ECG features on a prediction remaining unclear, possibility that an alert for occurring MVA may arrive very late and uncertainty in the performance of the ...[more]

PMID: 32407335

Similar Datasets

Project description:Background Short-term variability of the QT interval (STVQT) has been proposed as a novel electrophysiological marker for the prediction of imminent ventricular arrhythmias in animal models. Our aim is to study whether STVQT can predict imminent ventricular arrhythmias in patients. Methods and Results In 2331 patients with primary prophylactic implantable cardioverter defibrillators, 24-hour ECG Holter recordings were obtained as part of the EU-CERT-ICD (European Comparative Effectiveness Research to Assess the Use of Primary Prophylactic Implantable Cardioverter Defibrillators) study. ECG Holter recordings showing ventricular arrhythmias of >4 consecutive complexes were selected for the arrhythmic groups (n=170), whereas a control group was randomly selected from the remaining Holter recordings (n=37). STVQT was determined from 31 beats with fiducial segment averaging and calculated as [Formula: see text], where Dn represents the QT interval. STVQT was determined before the ventricular arrhythmia or 8:00 am in the control group and between 1:30 and 4:30 am as baseline. STVQT at baseline was 0.84±0.47 ms and increased to 1.18±0.74 ms (P<0.05) before the ventricular arrhythmia, whereas the STVQT in the control group remained unchanged. The arrhythmic patients were divided into three groups based on the severity of the arrhythmia: (1) nonsustained ventricular arrhythmia (n=32), (2) nonsustained ventricular tachycardia (n=134), (3) sustained ventricular tachycardia (n=4). STVQT increased before nonsustained ventricular arrhythmia, nonsustained ventricular tachycardia, and sustained ventricular tachycardia from 0.80±0.43 ms to 1.18±0.78 ms (P<0.05), from 0.90±0.49 ms to 1.14±0.70 ms (P<0.05), and from 1.05±0.22 ms to 2.33±1.25 ms (P<0.05). This rise in STVQT was significantly higher in sustained ventricular tachycardia compared with nonsustained ventricular arrhythmia (+1.28±1.05 ms versus +0.24±0.57 ms [P<0.05]) and compared with nonsustained ventricular arrhythmia (+0.34±0.87 ms [P<0.05]). Conclusions STVQT increases before imminent ventricular arrhythmias in patients, and the extent of the increase is associated with the severity of the ventricular arrhythmia.

Dataset Information

ECG-based prediction algorithm for imminent malignant ventricular arrhythmias using decision tree.

Publications

ECG-based prediction algorithm for imminent malignant ventricular arrhythmias using decision tree.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets