Prediction of Outcomes After Heart Transplantation in Pediatric Patients Using National Registry Data: Evaluation of Machine Learning Approaches.
Michael O KillianShubo TianAiwen XingDana HughesDipankar GuptaXiaoyu WangJiang BianPublished in: JMIR cardio (2023)
This study demonstrates the comparative utility of ML approaches for modeling posttransplant health outcomes using registry data. ML approaches can identify unique risk factors and their complex relationship with outcomes, thereby identifying patients considered to be at risk and informing the transplant community about the potential of these innovative approaches to improve pediatric care after heart transplantation. Future studies are required to translate the information derived from prediction models to optimize counseling, clinical care, and decision-making within pediatric organ transplant centers.
Keyphrases
- healthcare
- machine learning
- quality improvement
- risk factors
- palliative care
- end stage renal disease
- decision making
- electronic health record
- big data
- newly diagnosed
- chronic kidney disease
- pain management
- mental health
- metabolic syndrome
- peritoneal dialysis
- affordable care act
- health information
- current status
- weight loss
- skeletal muscle
- deep learning
- data analysis
- insulin resistance
- patient reported
- risk assessment
- social media
- hepatitis c virus
- climate change
- antiretroviral therapy