Implementation and evaluation of a Sepsis Best Practice Advisory alert utilizing predictive analytics to improve patient outcomes: An implementation study
Bibliographic record
Abstract
Background: Sepsis increases mortality and is a global healthcare concern. In the United States evidence-based early identification and treatment protocols are required in some states. Predictive analytics is one option to meet this requirement. Objective: The purpose of this system-wide initiative was to develop an interprofessional team to implement, evaluate, and optimize an early alert system for patients at high risk for sepsis utilizing predictive analytics to improve patient outcomes. Methods: The Sepsis Predictive Model and customized Best Practice Advisory (BPA) were evaluated utilizing a phased-rollout and pilot-testing. Regular meetings were conducted to analyze data and strategize iterative changes. End users were educated. Results: Pilot tests established the most effective alert-sepsis trigger scores; scores > 5 resulted in a 54% decrease in alerts. The Concordance Statistic (C-Stat) for the system-wide roll out was 0.765. The proportion of patients who had a BPA alert, had sepsis and an intervention (18.83%) was significantly greater than the proportion of patients who had a BPA alert had sepsis, and did not have an intervention (4.35%, p-value < .001). Similar results were found for the proportion of patients with a final diagnosis of infection who had a BPA alert, and an intervention, compared to those who did not. Early warning of potential sepsis resulted in a reduction in sepsis mortality rates not present on admission. Conclusions: An interprofessional team approach to leveraging established evidence and harnessing predictive analytics, fostered a customized collaborative protocol that improved sepsis care. Predictive analytics, tailored to clinical settings, is a powerful tool for advancing sepsis management.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".