P243 Complications of newly diagnosed Crohn's disease can be predicted by mathematical modeling of serologic responses
Bibliographic record
Abstract
Background: Crohn's disease (CD) is a heterogeneous progressive disorder. Predicting factors for complicated disease are scarce. We aimed to predict the natural history of a prospective inception cohort using biomarkers. Methods: A longitudinal, prospective, observational inception cohort, in a tertiary referral center. Adults suspected of CD, or diagnosed with CD during the preceding six months prior to enrollment were recruited. Clinical and biological markers were obtained. Three common NOD2 gene variants, and the ATG16L1variant were analyzed in blood DNA by TaqMan chemistry. Complicated outcome was defined as the first CD-related hospitalization or surgery. Data integration and analysis was performed using mathematical models. Results: A total of 297 patients were enrolled. Of these, 154 attained a definite diagnosis of CD. Mean age at diagnosis 31.9±13.1 years. Males: 79 (51.2%). Average follow-up: 18±11.8 months. At enrolment median CRP was 10.5 (3–22) gr%, and median fecal calprotectin was 424 (181–913) μg/gr stool. Median time between first symptoms and diagnosis was 4 (2–10) months. Montreal classification: L1- 47.9%, L2- 19.9%, L3–32.2%, B1–83.5%, B2–6.3%, B3–10.2%, and perianal involvement in 17.6%. Sixty-two patients (40%) had a complication, almost half (28/62) already at diagnosis, and the rest in the first 10 months since diagnosis. Complications after 10 months from diagnosis were rare. The NOD2 variant carriage rates were 19.6%, and the ATG16L1 variant 47.4%, comparable in complicated and non-complicated patients. The complicated group had lower rates of B1 phenotype, higher rates of B3 phenotype (69.3% vs. 83.6%, p=0.002, and 21% vs 2.1%, p<0.001, respectively) and higher rates of absolute ASCA levels (51.6±46 vs. 26.08±29.1 IU, p=0.001). Complicated patients had expedited exposure to medications: antibiotics HR=2.07 (p=0.005), steroids HR=4.29 (p<0.001), immunomodulators HR=2.66 (p<0.001), and biologics HR=1.89 (p=0.01), compared with non-complicated patients. Multivariate logistic regression utilizing the most discriminatory variables complemented by a decision tree algorithm revealed that integrating the absolute serology levels (IU) at diagnosis impact the probability for an early complication: ALCA (OR 0.944, 95% CI 0.908–0.981), ASCA (OR 1.025, 95% CI 1.009–1.041), and ACCA (OR 1.020, 95% CI 0.999–1.042). Conclusions: In a prospective inception cohort of CD patients early complications were noticed in 40% of patients within 10 months from diagnosis. Clinical data were not sufficient to stratify risk of complication. A decision tree based on serologic responses is reliable in detecting patients at risk for complication, enabling better decision making and patients' care.
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 | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".