Machine learning vs. conventional statistical models for predicting heart failure readmission and mortality.
Sheojung ShinPeter C AustinHeather Joan RossHusam Abdel-QadirCassandra FreitasGeorge TomlinsonDavide ChiccoMeera MahendiranPatrick R LawlerFilio BilliaAnthony O GramoliniSlava EpelmanBo WangDouglas S LeePublished in: ESC heart failure (2020)
ML algorithms had better discrimination than CSMs in most studies aiming to predict risk of readmission and mortality in HF patients. Based on our review, there is a need for external validation of ML-based studies of prediction modelling. We suggest that ML-based studies should also be evaluated using clinical quality standards for prognosis research. Registration: PROSPERO CRD42020134867.
Keyphrases
- machine learning
- heart failure
- end stage renal disease
- case control
- cardiovascular events
- chronic kidney disease
- ejection fraction
- newly diagnosed
- deep learning
- peritoneal dialysis
- risk factors
- artificial intelligence
- patient reported outcomes
- coronary artery disease
- acute heart failure
- atrial fibrillation
- cardiovascular disease
- quality improvement
- patient reported
- cardiac resynchronization therapy