P0730 DESIGN OF PREDICTIVE MODELS FOR POSITIVE OUTCOMES OF UPPER AND LOWER GASTROINTESTINAL ENDOSCOPIES IN CHILDREN AND ADOLESCENTS
Bibliographic record
Abstract
Introduction: Predictive models for gastrointestinal endoscopy outcomes have been designed in adult populations to try to optimize the use of these procedures(1.). Similar data regarding the predictive value of different clinical signs and symptoms found in the pediatric population is limited. We aim to determine if predictive models exist for positive findings of upper and lower endoscopies in children seen by pediatric gastroenterologists in a tertiary care center. Methods: Retrospective review of all endoscopies performed in children and adolescents from Jan.1 to Dec. 31, 2000 at the St. Justine Hospital (Montreal, Quebec). Inclusion criteria were age less than 19 years and absence of foreign body or caustic ingestion, known gastrointestinal disease, or previous upper gastrointestinal surgery. Variables of interest for the models were age, presenting symptoms, and laboratory investigations. Inter-rater reliability of the data was determined and only variables with a Kappa or Intra-class correlation coefficient of greater than 0.5 were included in the analysis. Predictive models for a positive outcome on endoscopy were constructed for upper and lower endoscopies by multiple logistic regression (SAS 8.0). The significance of the model was tested at a p <0.05 level. Results: Positive findings on endoscopy, including pathology reports, were found in 288 of 438 and 153 of 232 upper and lower endoscopies respectively. Hematemesis, epigastric tenderness, and hypoalbuminemia were significant predictors of positive upper endoscopies while age and anemia improved the precision of the model. Male sex, age, rectal bleeding, and elevated ESR were significant predictors of positive lower endoscopies while anemia, thrombocytosis, and hypoalbuminemia improved the precision of the model (Table 1). Both models were significant at p<0.0001. Conclusion: In our population of children, a number of predictive variables were found for upper and lower endoscopies and our predictive models were statistically significant. Prospective studies are needed to determine the clinical significance and validity of these variables and models.
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 | 0.069 | 0.103 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.004 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.001 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.008 | 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".