Cure8 research brief
People with Crohn’s disease who have had, or will have, intestinal surgery may benefit from better tools to predict early complications and endoscopic recurrence. Predictive models could help tailor follow-up and preventive strategies after surgery.
Clinicians, surgeons, researchers, and post-surgery Crohn’s disease patients
This study developed and internally validated multimodal machine-learning models to predict early postoperative complications and endoscopic recurrence after intestinal resection for Crohn’s disease using clinical, inflammatory, imaging, body-composition, surgical, and pathological features.
Models were trained on a retrospective cohort of 159 patients with 7:3 train/test splitting and evaluated with repeated cross-validation and bootstrap optimism correction.
An SVM model predicting early postoperative complications and a GBM model predicting endoscopic recurrence showed good discrimination (AUCs roughly 0.80–0.87) and acceptable calibration in internal testing.
Important predictors mentioned include sarcopenia, sMaRIA (an imaging index), neutrophil-to-lymphocyte ratio, number of anastomoses, perianal disease, granuloma formation, and disease duration.
The authors conclude these multimodal models may help postoperative risk stratification but state that external multicenter validation is required before clinical use.
Findings come from a retrospective single-cohort study with internal validation only; external multicenter validation is required. The supplied content is an abstract-level summary, not a full peer-reviewed article review.
Review the original publication for the complete reporting, methods, and context.
This Cure8 brief is based on source text from the linked article. Cure8 is informational only and is not a substitute for professional medical advice, diagnosis, or treatment.
Patients with Crohn's who develop intra-abdominal abscesses often face decisions about antibiotics, drainage, or surgery. Predictors like abscess size and imaging appearance may help estimate the chance of needing...
A predictive model for temporary stoma could influence surgical planning for people with Crohn’s disease, helping tailor decisions and expectations around intestinal resection.
Predicting which children with Crohn disease will need surgery — and roughly when — could help families and clinicians plan treatments, monitoring, and discussions about elective bowel resection earlier in the disease...
