Predicting Postoperative Hospital Stays Using Nursing Narratives and the Reverse Time Attention (RETAIN) Model: Retrospective Cohort Study.
Sungjoo HanYong-Beom KimJae Hong NoDong Hoon SuhKidong KimSoyeon AhnPublished in: JMIR medical informatics (2023)
The use of the RETAIN model on nursing narratives predicted postoperative LOS effectively for patients who underwent ovarian cancer surgery. These findings suggest that accurate and interpretable deep learning information obtained shortly after surgery may accurately predict prolonged LOS.
Keyphrases
- healthcare
- deep learning
- end stage renal disease
- patients undergoing
- mental health
- ejection fraction
- newly diagnosed
- chronic kidney disease
- quality improvement
- peritoneal dialysis
- prognostic factors
- high resolution
- working memory
- emergency department
- coronary artery bypass
- machine learning
- artificial intelligence
- patient reported outcomes
- coronary artery disease
- health information
- convolutional neural network
- acute care
- percutaneous coronary intervention