Search

Background/aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC., Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines., Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845)., Conclusions: AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Introduction: Anti-tumor necrosis factor (anti-TNF) therapy may improve insulin sensitivity, and its impact during pregnancy remains unclear. We aimed to assess the risk of gestational diabetes mellitus (GDM) associated with anti-TNF treatment among pregnant women with inflammatory bowel disease (IBD)., Methods: This nationwide cohort study included patients with IBD in Korea from 2010 to 2021. Anti-TNF exposure was identified from the last menstrual period (LMP) to LMP + 140 days. The development of GDM was assessed from LMP + 141 days to delivery. We performed overlap weighting to balance the covariates and used a generalized linear mixed model to measure the risk ratio (RR) and 95% confidence intervals (CIs). The anti-TNF group was compared with the unexposed group, as well as with the immunosuppressant, 5-aminosalicylate, and untreated groups., Results: A total of 3,695 pregnancies in women with IBD were identified, of which 338 (9.2%) were exposed to anti-TNFs. GDM was found in 7.1% of the pregnancies exposed to anti-TNFs as compared with 11.0% of those unexposed. The crude and weighted RRs for GDM risk were 0.64 (95% CI 0.43-0.96) and 0.68 (95% CI 0.55-0.84), respectively. The weighted RR when compared with the immunosuppressant, 5-aminosalicylate, and untreated groups was 0.70 (95% CI 0.41-1.18), 0.71 (95% CI 0.52-0.95), and 0.85 (95% CI 0.59-1.24), respectively., Discussion: This nationwide cohort reported a decreased risk of GDM among patients who used anti-TNFs during early pregnancy compared with those unexposed. GDM risk may become a consideration in the decision-making process when choosing treatment options for pregnant women with a risk factor for GDM., (Copyright © 2024 by The American College of Gastroenterology.)