A Model for Predicting Significant Hyperbilirubinemia in Neonates From China
Bibliographic record
Abstract
OBJECTIVES: To develop and validate a predischarge risk stratification model by using transcutaneous bilirubin (TcB) values and clinical factors to predict significant postdischarge hyperbilirubinemia in healthy term and late preterm Chinese neonates. METHODS: In a prospective cohort study, 8215 healthy term and late preterm neonates in 8 hospitals in China underwent TcB measurement at <168 hours of age. TcB percentiles were calculated and used to develop an hour-specific nomogram, and 9 empirically weighted items were used to derive a prediction model. A risk stratification model was developed by combining the TcB nomogram with clinical risk scores to predict significant hyperbilirubinemia, defined as a postdischarge bilirubin level that exceeded the hour-specific recommended threshold value for phototherapy. Data from another 13,157 neonates were used to validate the model. RESULTS: A TcB nomogram for every 12 hours of the studied interval was constructed from the development set. Gestational age, male gender, history of previous neonate who received phototherapy, bruising, feeding mode, weight loss, and early discharge were predictors of postdischarge significant hyperbilirubinemia. The combination of the TcB nomogram and clinical risk score provided the best prediction of significant hyperbilirubinemia with an area under the curve of 0.95 (95% confidence interval: 0.94-0.95) in the development data set and 0.94 (95% confidence interval: 0.93-0.94) in the validation data set. A risk stratification model with 6 distinct risk levels was developed and validated. CONCLUSIONS: A risk classification model, combining discharge transcutaneous bilirubin values and clinical risk factors, separated term and late preterm Chinese neonates into 6 risk classes for the timely follow-up of postdischarge hyperbilirubinemia detection.
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 | 0.004 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 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".