← Search

Table · dataset · 2026

Data Sheet 1_Explainable random forest–SHAP framework for Montreal phenotype–stratified prediction of one-year complications in Crohn’s disease.pdf

Listed in figshare

Background<p>Early identification of phenotype-stratified, short-term complication risk remains a critical unmet need in Crohn’s disease (CD).

Description

Existing models focus on single outcomes and lack interpretability, limiting clinical use. We developed a clinically interpretable machine-learning framework to enable Montreal phenotype–stratified prediction of three one-year complication categories: bowel resection (Task 1), perianal complications (Task 2), and abdominal complications (Task 3).</p>Methods<p>Data from 370 patients across two clinical centers were pooled for model development and evaluated using stratified 10-fold cross-validation.

Within each fold, data preprocessing, LASSO feature selection, SMOTE-Tomek resampling, model optimization, calibration, and threshold determination were restricted to the training data. Seven machine-learning algorithms were compared in terms of discrimination, calibration, with decision-curve analysis used to explore potential net benefit. SHapley Additive exPlanations (SHAP) were used for model interpretation, and nomograms, heatmaps, and a web-based calculator were generated as exploratory visualizations of model-derived risk estimates rather than as clinical decision-support tools.

Read the rest (3 more)

Phenotype-stratified and non-linear associations between CDAI and complication risk were further analyzed within the Montreal framework.</p>Results<p>Within one year after discharge, bowel resection, perianal complications, and abdominal complications occurred in 70 (18.9%), 142 (38.4%), and 84 (22.7%) patients, respectively. Random Forest showed the most consistent overall performance, achieving an AUROC of 0.86 (95% CI, 0.82–0.90) for bowel resection, 0.71 (95% CI, 0.64–0.78) for perianal complications, and 0.73 (95% CI, 0.69–0.78) for abdominal complications.

SHAP identified distinct predictors across outcomes: disease behavior, nutritional support therapy, and disease duration for bowel resection; prior perianal complications, extraintestinal manifestations, and CDAI for perianal complications; and prior abdominal complications, nutritional support therapy, and Montreal L3 phenotype for abdominal complications. Receipt of NST was interpreted as a clinical marker of nutritional depletion and greater disease burden rather than as a causal risk factor.

Montreal-based stratification revealed marked heterogeneity, with isolated small-bowel disease associated with higher risks of bowel resection and abdominal complications, and isolated colonic disease with the highest burden of perianal complications.</p>Conclusion<p>The interpretable RF–SHAP framework showed potential for Montreal phenotype–stratified prediction of one-year complication risk in CD and inform future evaluation of risk stratification and phenotype-informed management.</p>

Links

Where it is published

Catalogue records · 1

Topics

Inferred from text
Disease 75%
Provenance · 1 source records, 19 field assertions
SourceKeyLast seenRaw
figshareoai:figshare.com:article/3377095611 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · figshare comconnector:figshare_com@1.0.0
concepts[disease].local:disease:diseaseenrichment · figshare comkeyword-concept-rules@1.0.0title+description (75%)
concepts[field].anzsrc:group:4602mapping · figshare comvocabulary-mapper@1.0.0keywords['artificial intelligence']
concepts[field].anzsrc:group:4611mapping · figshare comvocabulary-mapper@1.0.0keywords['machine learning']
concepts[field].local:field:astronomymapping · figshare comconnector:figshare_com@1.0.0
concepts[field].local:field:chemistrymapping · figshare comconnector:figshare_com@1.0.0
concepts[field].local:field:computer-science-aimapping · figshare comconnector:figshare_com@1.0.0
concepts[field].local:field:earth-environmentalmapping · figshare comconnector:figshare_com@1.0.0
concepts[field].local:field:economics-financemapping · figshare comconnector:figshare_com@1.0.0
concepts[field].local:field:engineeringmapping · figshare comconnector:figshare_com@1.0.0
concepts[field].local:field:humanitiesmapping · figshare comconnector:figshare_com@1.0.0
concepts[field].local:field:life-sciencesmapping · figshare comconnector:figshare_com@1.0.0
concepts[field].local:field:medicine-healthmapping · figshare comconnector:figshare_com@1.0.0
concepts[field].local:field:ocean-atmosphericmapping · figshare comconnector:figshare_com@1.0.0
concepts[field].local:field:social-sciencemapping · figshare comconnector:figshare_com@1.0.0
descriptionsource · figshare comconnector:figshare_com@1.0.0/metadata/dc/description
licensesource · figshare comconnector:figshare_com@1.0.0/metadata/dc/rights
publication_datesource · figshare comconnector:figshare_com@1.0.0
titlesource · figshare comconnector:figshare_com@1.0.0/metadata/dc/title