Screening swabs surpass traditional risk factors as predictors of MRSA bacteremia
Bibliographic record
Abstract
BACKGROUND: Consideration to add empiric MRSA therapy with vancomycin is a common clinical dilemma. However, vancomycin overuse has important adverse events. MRSA colonization screening is commonly performed for infection control. We hypothesized that in cases of S. aureus bacteremia, a score based on patient level factors and MRSA colonization could predict the risk of MRSA infection and inform the need for empiric coverage. METHODS: Using modern machine learning statistical methods (LASSO regression and random forests), we designed a predictive score for MRSA infection based on patient level characteristics, and MRSA colonization as measured by screening done 30 days before infection (30-Day criteria), or at any time before infection (Ever-Positive criteria). Patient factors (age, sex, number of previous admissions, and other medical comorbidities) were obtained through our electronic records. RESULTS: With random forests, MRSA colonization largely surpassed all other factors in terms of accuracy and discriminatory power. Using LASSO regression, MRSA colonization was the only factor with MRSA infection predictive power with odds ratio of 10.3 (min: 5.99, max: 16.1) and 8.14 (min: 6.01, max: 14.8) for the 30-Day and Ever-Positive criteria, respectively. Further, patient comorbidities were not adequate predictors of MRSA colonization. CONCLUSIONS: In an era of community acquired MRSA, colonization status appears to be the only independent and reliable predictor of MRSA infection in cases of S. aureus bacteremia. A clinical approach based on a patient's known MRSA colonization status and on local susceptibility patterns may be appropriate.
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 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 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".