Automated detection of methicillin-resistant <i>Staphylococcus aureus</i> with the MRSA CHROM imaging application on BD Kiestra Total Lab Automation System
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
(MRSA) and its potentially fatal outcome necessitate rapid and accurate detection of patients colonized with MRSA in healthcare settings. Using the BD Kiestra Total Lab Automation (TLA) System in conjunction with the MRSA Application (MRSA App), an imaging application that uses artificial intelligence to interpret colorimetric information (mauve-colored colonies) indicative of MRSA pathogen presence on CHROMagar chromogenic media, anterior nares specimens from three sites were evaluated for the presence of mauve-colored colonies. Results obtained with the MRSA App were compared to manual reading of agar plate images by proficient laboratory technologists. Of 1,593 specimens evaluated, 1,545 (96.98%) were concordant between MRSA App and laboratory technologist reading for the detection of MRSA growth [sensitivity 98.15% (95% CI, 96.03, 99.32) and specificity 96.69% (95% CI, 95.55, 97.60)]. This multi-site study is the first evaluation of the MRSA App in conjunction with the BD Kiestra TLA System. Using the MRSA App, our results showed 98.15% sensitivity and 96.69% specificity for the detection of MRSA from anterior nares specimens. The MRSA App, used in conjunction with laboratory automation, provides an opportunity to improve laboratory efficiency by reducing laboratory technologists' labor associated with the review and interpretation of cultures.
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.
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 | 0.002 | 0.000 |
| 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 | 0.000 |
| 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 it