An Empirical Investigation of PU Learning for Predicting Length of Stay
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Reliably predicting the length of stay of patients in a hospital based on their demographic and clinical characteristics as well as the care they received can inform hospital planning, particularly in novel response scenarios such as Covid-19. Positive Unlabelled (PU) learning is a type of semi-supervised learning in which only the positive labels in a dataset are reliable. PU learning can be used when the length of stay prediction is formulated as a classification problem, and the prediction needs to be performed dynamically while the patients are being treated. This paper empirically investigates how unlabeling can negatively affect classification accuracy and show how this effect can be mitigated using different algorithms for PU learning. A large dataset of Covid-19 length of hospital stay was used for the experiments. The results show the potential of utilizing PU learning approaches to predicting the length of hospital stay.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it