Comparison of five classification systems for interpreting electronic fetal monitoring in predicting neonatal status at birth
Bibliographic record
Abstract
OBJECTIVE: To compare the accuracy of five different classification systems for interpreting electronic fetal monitoring (EFM) when predicting neonatal status at birth, as determined by the umbilical cord arterial pH. METHODS: Ninety-seven cardiotocography traces were retrospectively interpreted according to five classification systems for EFM: Dublin Fetal Heart Rate Monitoring Trial (DFHRMT), Royal College of Obstetricians and Gynecologists (RCOG), Society of Obstetricians and Gynaecologists of Canada (SOGC), National Institute of Child Health and Human Development (NICHD) and Parer & Ikeda's. For each classification system, sensitivity, specificity, positive and negative predictive values were calculated. The capacity of the classifications to predict neonatal pH was also evaluated by receiver-operating characteristic (ROC) curves. Agreement between the five systems was estimated using weighted kappa statistic. RESULTS: Considering pH ≤7.15 as the cutoff for low pH, the sensitivity and specificity values were 100 and 18% (DFHRMT); 100 and 15% (RCOG); 88 and 37% (SOGC); 67 and 92% (NICHD); 55 and 67% (Parer & Ikeda). The ROC curves showed that all classifications analyzed had a low discriminative capacity when predicting umbilical artery pH ≤7.15. An excellent agreement was observed between DFHRMT and RCOG (weighted κ value: 0.860). CONCLUSIONS: Parer & Ikeda and NICHD classifications had the highest specificity in detecting umbilical cord arterial pH ≤7.15. The high specificity of the NICHD classification is hindered by a high percentage of "intermediate" traces (80%). Parer & Ikeda classification is the one that best classify as pathological only the traces of fetuses that are truly at risk of acidemia, thus avoiding unnecessary intervention. It also showed the best trade-off between sensitivity and specificity and the lowest rate of traces considered "intermediate."
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 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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".