Identifying proactive ICU patient admission, transfer and diversion policies in a public-private hospital network
Bibliographic record
Abstract
Management of hospital beds is a high-impact issue for two-tier healthcare systems, due principally to their critical importance and high costs. Bed capacity in the public sector is generally insufficient to provide immediate care to all critical patients and thus a significant proportion of public expenditure is assigned to the diversion of patients for treatment in the private sector. We formulate and approximately solve a discounted infinite-horizon Markov Decision Process (MDP) that seeks to identify cost-effective policies for transferring ICU patients between hospitals or diverting them to private clinics. The solution approach employs an affine architecture for approximating the value function of the MDP model and solves the equivalent linear programming model using column generation. The approach can handle a high level of dimensionality, enabling it to consider the arriving patients’ many different diagnostic groups and their corresponding lengths of stay. The decisions generated through this approach often differ from the intuitive ones produced in a typical day-by-day decision process, that does not consider the impact of the current day’s decisions on the future performance of the system. In particular, the resulting policies will in many cases proactively transfer patients to a different public facility or divert them to a private one even though the hospital they first arrived at had beds available. The performance of the proposed method was evaluated by simulating a case study based on data from a hospital network in Santiago, Chile, producing savings of almost 49% due mostly to reduced usage of private services.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".