Predicting Postoperative Hospital Stays Using Nursing Narratives and the Reverse Time Attention (RETAIN) Model: Retrospective Cohort Study
Bibliographic record
Abstract
Background: Nursing narratives are an intriguing feature in the prediction of short-term clinical outcomes. However, it is unclear which nursing narratives significantly impact the prediction of postoperative length of stay (LOS) in deep learning models. Objective: Therefore, we applied the Reverse Time Attention (RETAIN) model to predict LOS, entering nursing narratives as the main input. Methods: A total of 354 patients who underwent ovarian cancer surgery at the Seoul National University Bundang Hospital from 2014 to 2020 were retrospectively enrolled. Nursing narratives collected within 3 postoperative days were used to predict prolonged LOS (≥10 days). The physician's assessment was conducted based on a retrospective review of the physician's note within the same period of the data model used. Results: The model performed better than the physician's assessment (area under the receiver operating curve of 0.81 vs 0.58; P=.02). Nursing narratives entered on the first day were the most influential predictors in prolonged LOS. The likelihood of prolonged LOS increased if the physician had to check the patient often and if the patient received intravenous fluids or intravenous patient-controlled analgesia late. Conclusions: 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".