Machine Learning Prediction of Response to Cardiac Resynchronization Therapy: Improvement Versus Current Guidelines
| Autor: | David D. Spragg, Eiran Z. Gorodeski, John Barnard, Divyang Patel, Richard A. Grimm, Mina K. Chung, Niraj Varma, Carolyn J. Park, Mark Niebauer, Anant Madabhushi, Saleem Toro, Michael LaBarbera, Albert Feeny, Sunil Sinha, Xinge Ji, Kevin Trulock, John Rickard |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Male
Time Factors medicine.medical_treatment Clinical Decision-Making Cardiac resynchronization therapy Machine learning computer.software_genre Risk Assessment Ventricular Function Left Article Decision Support Techniques Cardiac Resynchronization Therapy Machine Learning Predictive Value of Tests Risk Factors Physiology (medical) Medicine Humans Aged Ohio Retrospective Studies Heart Failure business.industry Patient Selection Stroke Volume Recovery of Function Middle Aged medicine.disease Progression-Free Survival Echocardiography Heart failure Baltimore Practice Guidelines as Topic Disease Progression Heart Transplantation Female Artificial intelligence Heart-Assist Devices Current (fluid) Cardiology and Cardiovascular Medicine business computer |
| Zdroj: | Circ Arrhythm Electrophysiol |
| ISSN: | 1941-3084 |
| Popis: | Background: Cardiac resynchronization therapy (CRT) has significant nonresponse rates. We assessed whether machine learning (ML) could predict CRT response beyond current guidelines. Methods: We analyzed CRT patients from Cleveland Clinic and Johns Hopkins. A training cohort was created from all Johns Hopkins patients and an equal number of randomly sampled Cleveland Clinic patients. All remaining patients comprised the testing cohort. Response was defined as ≥10% increase in left ventricular ejection fraction. ML models were developed to predict CRT response using different combinations of classification algorithms and clinical variable sets on the training cohort. The model with the highest area under the curve was evaluated on the testing cohort. Probability of response was used to predict survival free from a composite end point of death, heart transplant, or placement of left ventricular assist device. Predictions were compared with current guidelines. Results: Nine hundred twenty-five patients were included. On the training cohort (n=470: 235, Johns Hopkins; 235, Cleveland Clinic), the best ML model was a naive Bayes classifier including 9 variables (QRS morphology, QRS duration, New York Heart Association classification, left ventricular ejection fraction and end-diastolic diameter, sex, ischemic cardiomyopathy, atrial fibrillation, and epicardial left ventricular lead). On the testing cohort (n=455, Cleveland Clinic), ML demonstrated better response prediction than guidelines (area under the curve, 0.70 versus 0.65; P =0.012) and greater discrimination of event-free survival (concordance index, 0.61 versus 0.56; P P Conclusions: ML with 9 variables incrementally improved prediction of echocardiographic CRT response and survival beyond guidelines. Performance was not improved by incorporating more variables. The model offers potential for improved shared decision-making in CRT (online calculator: http://riskcalc.org:3838/CRTResponseScore ). Significant remaining limitations confirm the need to identify better variables to predict CRT response. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|