Clinical impact of accepting or rejecting a recommendation from a clinical decision support system–assisted antibiotic stewardship program
Bibliographic record
Abstract
Background: Outcomes associated with physician responses to recommendations from an antimicrobial stewardship program (ASP) at an individual patient level have not yet been assessed. We aimed to compare clinical characteristics and mortality risk among patients for whom recommendations from an ASP were accepted or refused. Methods: A prospective cohort study was performed with hospitalized adults who received intravenous or oral antimicrobials at a 677-bed academic centre in Canada in 2014–2017. We included patients with an alert produced by a clinical decision support system (CDSS) for whom a recommendation was made by the pharmacist to the attending physician. The outcome was 90-day in-hospital all-cause mortality. Results: We identified 3,197 recommendations throughout the study period, of which 2,885 (90.2%) were accepted. The median length of antimicrobial treatment was significantly shorter when a recommendation was accepted (0.26 versus 1.78 d; p < 0.001). Refusal of a recommendation was not associated with mortality (odds ratio 1.32; 95% confidence interval, 0.93 to 1.89; p = 0.12). The independent risk factors associated with in-hospital mortality were age, Charlson Comorbidity Index score, admission to a critical care unit, duration between admission and recommendation, and issuance of a recommendation on a carbapenem. Conclusions: The duration of antimicrobial treatment was significantly shorter when a recommendation originating from a CDSS-assisted ASP program was accepted. Future prospective studies including potential residual confounding variables, such as the source of infection or physiological derangement, might help in understanding whether CDSS-assisted ASP will have a direct impact on patient mortality.
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 | 0.004 | 0.034 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 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".