71: Impact of a Novel Predictive Model for Early-Onset Neonatal Sepsis Evaluation
Bibliographic record
Abstract
The multivariate risk model proposed by Puopolo et al (Pediatrics 2011;128(5):e11655–1163) has been shown to identify 35% fewer asymptomatic infants born at ≥ 36 weeks in a single maternity center as high risk for early onset neonatal sepsis (EOS) when compared with standard algorithms. (Mukhopadhyay et al E-PAS2013:3355.6) To retrospectively examine the number of infants assessed and treated for EOS using local guidelines in a Canadian neonatal unit in comparison with the numbers that would have been assessed by using the quantitative multivariate risk model of Puopolo et al. Retrospective cohort study of infants born at ≥34 weeks gestational age (GA) admitted to a Canadian NICU, between July 2012 and June 2013. The cohort, which includes infants admitted to the NICU for a variety of clinical and child welfare reasons, was first stratified into high- and low-risk groups according to the risk calculated by the model of Puopolo et al. This model uses GA highest maternal intrapartum temperature, duration of rupture of membranes, maternal group B Strep status as well as timing and type of intrapartum antibiotics to calculate a risk. A value of ≥0.5 per 1000 live births was used to define high risk and therefore the threshold for assessment and treatment. The numbers who were investigated (CBC, blood culture, or CSF culture) and/or treated for EOS within each group were then identified. 89.5% (239 of 267) of infants were calculated as being low risk while 10.5% (28 of 267) were high risk, with the mean risk scores being 0.12±0.01 (95% CI 0.0 to 0.47) and 1.68±0.91 (95% CI 0.52 to 13.19), respectively. Within the low risk group, 130 of 239 (54%) were investigated for EOS, while 31 of 239 (13%) received antibiotics. Within the high risk group, 18 of 28 (64%) were investigated with only two of 28 (7%) also being treated for EOS. There were no differences in the mean risk scores in the high risk group between those who were investigated and those who were not. The scores of the two patients in the high risk group who received antibiotics were 13.19 and 0.94, and the mean score of those who did not was 1.26±0.39 (95% CI 0.52 to 4.47). In total, 148 of 267 (55.4%) of infants were investigated for EOS in this cohort based on clinical judgement. No cases of EOS as defined by a positive blood or CSF culture were identified during this period. Use of the Puopolo et al. neonatal sepsis predictive model for evaluation of EOS would have resulted in 81% fewer infants investigated. Costs associated with the investigations and treatment and potential cost savings of using this model are currently being evaluated. Prospective study is needed to further evaluate the practical impact of this predictive instrument on EOS identification and associated cost savings in Canadian NICUs.
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 | 0.010 | 0.022 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".