Patient prioritization for pharmaceutical intervention in the hospital setting: a retrospective cross-sectional study
Bibliographic record
Abstract
OBJECTIVES: Prioritization of patients requiring pharmaceutical intervention is critical given limited resources. Data from pharmacy software could be used to target patients. This retrospective cross-sectional study aimed to describe the method implemented in a hospital care unit to prioritize hospitalized patients and compare the characteristics of those receiving a pharmaceutical intervention and those not. This study also explored the possibility of predicting an intervention using pharmacy software data. METHODS: All patients admitted to a hospital care unit between November 2019 and April 2020 were included. Prioritization with the pharmacy software was based on preselected admission diagnoses and by operating an antimicrobial stewardship programme. Medications and patients' characteristics were extracted from the pharmacy software. Pharmaceutical interventions and drug-related problems were collected from medical records. Two machine learning algorithms were used to produce rule-based models for pharmaceutical intervention prediction. KEY FINDINGS: A total of 850 admissions were included. A medication review following prioritization with the pharmacy software or due to external requests was carried out by clinical pharmacists in 45% of admissions, followed by an intervention in 81% of them. Patients who received an intervention had lower creatinine clearance levels and more regular medications including antibacterials for systemic use, diuretics, and psychoanaleptics. The two resulting interpretable models comprised either 6 or 17 predictors of a pharmaceutical intervention. CONCLUSIONS: Pharmacy software data may be used for more efficient prioritization of patients using specific criteria. Rule-based models are promising avenues to help clinical pharmacists systematically identify patients requiring pharmaceutical intervention, but further work is warranted.
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 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 | 0.003 | 0.006 |
| 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 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".