From prediction to decision: Optimizing long‐term care placements among older delayed discharge patients
Bibliographic record
Abstract
This study examines long‐term care (LTC) discharge planning among older delayed discharge patients. While awaiting placements in alternate care such as LTC, these patients occupy hospital beds despite not requiring an intensive level of care. This study proposes a novel discharge decision model based on the Markov decision process (MDP) framework, which incorporates predictions regarding the patients' health trajectory and the associated hospital costs. Our machine learning (ML)‐based predictive analytics allow for considering heterogeneous health transitions, hence personalized decision making, leading to valuable information for reducing hospital costs. We also develop data‐driven cost functions using patient characteristics to estimate the person‐level costs associated with the decisions in the optimization model, that is, whether or not to discharge a patient to LTC. The data analyses and cost estimations are based on large historical data collected over 13 years in Ontario, Canada. To solve the resulting high‐dimensional MDP models, we develop an index policy, where each patient's index value is calculated using their health complexity (comorbidity), sex, age, and acute length of stay in the hospital. Using extensive numerical experiments, we illustrate the superior performance of the proposed index policy against some benchmarking policies and demonstrate the significance of predictive information in optimizing discharge decisions. Our results also indicate that the value of predictive information increases with LTC bed availability and decreases with hospital capacity. We also demonstrate that with the anticipated exacerbating mismatch between supply and demand, targeted prediction‐driven discharge policies, such as the proposed index policy, become even more critical.
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 | 0.001 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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".