Machine learning in cardiac surgery: a narrative review.
Travis J MilesRavi K GhantaPublished in: Journal of thoracic disease (2024)
Studies utilizing high volume, multidimensional data such as that derived from electronic health record (EHR) data appear to best demonstrate the advantages of ML methods. Models trained on post cardiac surgery intensive care unit data demonstrate excellent predictive performance and may provide greater clinical utility if incorporated as clinical decision support tools. Further development of ML models and their integration into EHR's may result in dynamic clinical decision support strategies capable of informing clinical care and improving outcomes in cardiac surgery.
Keyphrases
- electronic health record
- clinical decision support
- cardiac surgery
- acute kidney injury
- intensive care unit
- machine learning
- adverse drug
- healthcare
- palliative care
- quality improvement
- big data
- chronic pain
- metabolic syndrome
- adipose tissue
- weight loss
- deep learning
- pain management
- mechanical ventilation
- resistance training
- high intensity
- acute respiratory distress syndrome