Validation of the NICHD Bronchopulmonary Dysplasia Outcome Estimator 2022 in a Quaternary Canadian NICU – A Single Centre Observational Study
Bibliographic record
Abstract
Background/Objectives: The numerical risk of bronchopulmonary dysplasia (BPD) and/or death could be estimated using the National Institute of Child Health and Human Development (NICHD) BPD outcome estimator 2022 in extremely low gestational age (ELGA) infants during the first 4 weeks of life to facilitate prognostication, and centre specific targeted improvement interventions. However, 2022 NICHD BPD outcome estimator’s performance in Canadian setting has not been validated. Our objective is to validate the NICHD BPD outcome estimator 2022 in predicting death and or moderate to severe BPD at 36 weeks in less than 29 weeks infants admitted to NICU. Methods: A retrospective observational study (March 2022–August 2023) was conducted on both inborn and outborn preterm infants excluding neonates with major congenital anomalies. Infants were classified into five groups based on the predicted risk of death or moderate-to-severe BPD (<10%, 10-20%, 20-30%, 30-40%, ≥50%) followed by noting observed outcomes from unit’s database. A Receiver Operating Characteristics (ROC) curve was used to assess the accuracy of the NICHD BPD outcome estimator 2022, with an area under curve (AUC) >0.7 defined a priori as an acceptable predictive accuracy for local use. Results: Among 99 infants included, 13 (13.1%) died, and 40 (40.4%) developed BPD. Median gestational age was 26 weeks, and median birth weight was 914 grams. Twenty-three infants (23.2%) received postnatal steroids. The AUC values for death or moderate to severe BPD on days 1, 3, 7, 14, and 28 were 0.803, 0.806, 0.837, 0.832, and 0.843, respectively. The AUC values for moderate to severe BPD alone on those days were 0.766, 0.746, 0.785, 0.807 and 0.818 respectively. Conclusions: The 2022 BPD estimator accurately predicted the death and /or moderate to severe BPD on Days 1, 3, 7, 14 and 28 of life. This tool could serve as a valid adjunct to facilitate discussion between clinicians and families on initiating time-sensitive targeted interventions to prevent or alter the course of BPD.
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 | 0.015 | 0.029 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.003 | 0.002 |
| 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".