Using Natural Language Processing and Machine Learning to Analyze Admission Criteria of a General Internal Medicine Short Stay Unit
Bibliographic record
Abstract
Short Stay Units (SSU) have been created to minimize emergency department overcrowding and aid in the patient flow process of hospitals. The best way to determine admission criteria into such units remains to be a challenge as not all hospitals operate the same. We apply 3 machine learning algorithms to predict the length of stay (LOS) of all General Internal Medicine (GIM) patients at Toronto General Hospital based on patient flow and emergency room triage assessment data from January 2019 to December 2019. Of these patients, 46% of them had a LOS of less than 72 hours and of those patients 51% were GIM patients. To aid in the potential implementation of a GIM SSU, we investigate into the predictors of the best performing model. Performance metric precision was calculated and found to be 0.77 for the best performing model (Random Forest) after hyperparameter tuning and feature selection. The features affecting admission criteria for a potential GIM SSU were found to be the following: age, pulse, blood pressure, respirations, day of admission, and chief complaint. Predictive key words for patients with a LOS of less than 3 days were also identified.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".