Predicting electrical storms by remote monitoring of implantable cardioverter-defibrillator patients using machine learning
- Resource Type
- Authors
- Saeed Shakibfar; Alfonso Aranda; Helen Høgh Petersen; Jonas Moll; Tariq Osman Andersen; Jesper Hastrup Svendsen; Casper Lund-Andersen; Oswin Krause; Christian Igel
- Source
- EP Europace. 21:268-274
- Subject
- Time Factors
Databases, Factual
medicine.medical_treatment
Electric Countershock
030204 cardiovascular system & hematology
Machine learning
computer.software_genre
Logistic regression
Risk Assessment
Implantable defibrillators
Machine Learning
03 medical and health sciences
0302 clinical medicine
Heart Rate
Predictive Value of Tests
Risk Factors
Physiology (medical)
Clinical information
Humans
Medicine
Model development
030212 general & internal medicine
Heart Failure
business.industry
Area under the curve
Reproducibility of Results
Signal Processing, Computer-Assisted
Ventricular pacing
Implantable cardioverter-defibrillator
Defibrillators, Implantable
Random forest
Treatment Outcome
Remote Sensing Technology
Ventricular Fibrillation
Tachycardia, Ventricular
Artificial intelligence
Cardiology and Cardiovascular Medicine
business
computer
- Language
- ISSN
- 1532-2092
1099-5129
Aims Electrical storm (ES) is a serious arrhythmic syndrome that is characterized by recurrent episodes of ventricular arrhythmias. Electrical storm is associated with increased mortality and morbidity despite the use of implantable cardioverter-defibrillators (ICDs). Predicting ES could be essential; however, models for predicting this event have never been developed. The goal of this study was to construct and validate machine learning models to predict ES based on daily ICD remote monitoring summaries. Methods and results Daily ICD summaries from 19 935 patients were used to construct and evaluate two models [logistic regression (LR) and random forest (RF)] for predicting the short-term risk of ES. The models were evaluated on the parts of the data not used for model development. Random forest performed significantly better than LR (P