Comparison of National Factor-Based Models for Preeclampsia Screening
Bibliographic record
Abstract
Objective This study aimed to compare the predictive values of the American College of Obstetricians and Gynecologists (ACOG), the National Institute for Health and Care Excellence (NICE), and the Society of Obstetricians and Gynecologists of Canada (SOGC) factor-based models for preeclampsia (PE) screening. Study Design We conducted a secondary analysis of maternal and birth data from 32 hospitals. For each delivery, we calculated the risk of PE according to the ACOG, the NICE, and the SOGC models. Our primary outcomes were PE and preterm PE (PE combined with preterm birth) using the ACOG criteria. We calculated the detection rate (DR or sensitivity), the false positive rate (FPR or 1 − specificity), the positive (PPV) and negative (NPV) predictive values of each model for PE and for preterm PE using receiver operator characteristic (ROC) curves. Results We used 130,939 deliveries including 4,635 (3.5%) cases of PE and 823 (0.6%) cases of preterm PE. The ACOG model had a DR of 43.6% for PE and 50.3% for preterm PE with FPR of 15.6%; the NICE model had a DR of 36.2% for PE and 41.3% for preterm PE with FPR of 12.8%; and the SOGC model had a DR of 49.1% for PE and 51.6% for preterm PE with FPR of 22.2%. The PPV for PE of the ACOG (9.3%) and NICE (9.4%) models were both superior than the SOGC model (7.6%; p < 0.001), with a similar trend for the PPV for preterm PE (1.9 vs. 1.9 vs. 1.4%, respectively; p < 0.01). The area under the ROC curves suggested that the ACOG model is superior to the NICE for the prediction of PE and preterm PE and superior to the SOGC models for the prediction of preterm PE (all with p < 0.001). Conclusion The current ACOG factor-based model for the prediction of PE and preterm PE, without considering race, is superior to the NICE and SOGC models. Key Points
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 | 0.046 | 0.113 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".