High Healthcare Costs in Childhood Inflammatory Bowel Disease: Development of a Prediction Model Using Linked Clinical and Health Administrative Data
Bibliographic record
Abstract
BACKGROUND: The incidence of pediatric-onset inflammatory bowel disease (IBD) and the costs of caring for individuals with IBD are both increasing. We calculated the direct healthcare costs of pediatric IBD in the first year after diagnosis and developed a model to predict children who would have high costs (top 25th percentile). METHODS: Using data from the Canadian Children IBD Network inception cohort (≤16 years of age, diagnosed between 2013 and 2019) deterministically linked to health administrative data from Ontario, Canada, we estimated direct healthcare and medication costs accrued between 31 and 365 days after diagnosis. Candidate predictors included age at diagnosis, sex, rural/urban residence location, distance to pediatric center, neighborhood income quintile, IBD type, initial therapy, disease activity, diagnostic delay, health services utilization or surgery around diagnosis, regular primary care provider, and receipt of mental health care. Logistic regression with stepwise elimination was used for model building; 5-fold nested cross-validation optimized and improved model accuracy while limiting overfitting. RESULTS: The mean cost among 487 children with IBD was CA$15 168 ± 15 305. Initial treatment (anti-tumor necrosis factor therapy, aminosalicylates, or systemic steroids), having a mental health care encounter, undergoing surgery, emergency department visit at diagnosis, sex, and age were predictors of increased costs, while having a regular primary care provider was a predictor of decreased costs. The C-statistic for our model was 0.71. CONCLUSIONS: The cost of caring for children with IBD in the first year after diagnosis is immense and can be predicted based on characteristics at diagnosis. Efforts that mitigate rising costs without compromising quality of care are needed.
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 | 0.006 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".