Impact of an Innovative Smartphone “App” on Intensive Care Unit (ICU) Antimicrobial Utilization Across a Large Metropolitan Health Region in Canada: An Interrupted Time Series Analysis
Bibliographic record
Abstract
Background. Spectrum MD is a customizable stewardship smartphone app that offers algorithmic decision support based on clinical guidelines and local microbiology data. The app was introduced to all ICU prescribers across a large metropolitan health region followed by an interrupted time series analysis (ITSA) to evaluate the impact on ICU antimicrobial utilization (AMU). Methods. Spectrum MD was launched 11 January 2013 to ICU prescribers with monthly educational sessions. Penetration of the app was tracked with Flurry Analytics, a post-intervention survey, and via session attendance. An uncontrolled before-after intervention ITSA (SPSS v19.0) was performed to compare AMU in the 12 months pre- and post-intervention (allowing a 3 month wash-in period) using daily defined doses/100 patient days. Patient demographics, central line associated bloodstream infection (CLABSI) and influenza rates were analyzed for both time periods. Student's t-test was used for continuous variables and two-tailed χ2 or Fishers exact as appropriate for categorical variables. Results. Patient characteristics were similar between the pre- (n = 2867) and post-intervention (n = 2717) groups, including age (x 56.9 versus 56.3 years), admission APACHE (19.7 versus 19.6), and immunosuppression (15% versus 16%), as were rates of CLABSI and influenza. Post wash-in there were 634 active Spectrum MD users within the health region, which increased to 1145 during the post-intervention period, and 76% (54/71; response rate 34%) of survey respondents reported using the app during their ICU rotation. There was no statistically significant change in overall AMU between the time periods. Agent-specific analysis revealed a trend toward decreased anti-pseudomonal utilization (slope change parameter −0.983; p = 0.07). Of 64 respondents, 70% agreed this app changed their antimicrobial prescribing practices while 89% would recommend it to colleagues. Conclusion. Spectrum MD was a widely accepted intervention that yielded positive user feedback. Though there was no significant reduction in overall AMU, a trend toward decreased anti-pseudomonal agent use may represent more appropriate antimicrobial prescribing. Further longitudinal analysis is required to assess the impact of this promising app. Disclosures. J. Conly, Alberta Health Services (AHS): Employee, John Conly receives a stipend from AHS for his medical role in antimicrobial stewardship; B. Dalton, Alberta Health Services (AHS): Employee, Bruce Dalton had roles in both implementation and evaluation of this program and receives remuneration for antimicrobial stewardship activities. Potential risk of bias exists in this evaluation as positive results could also be career advancing.
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 | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.003 |
| 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".