Background: Multidisciplinary Tumor Councils (MDTs) are vital platforms that provide tailored treatment plans for cancer patients by combining expertise from various medical disciplines. Recently, Artificial Intelligence (AI) tools have been investigated as decision-support systems within these councils. Methods: In this prospective study, the compatibility of AI (ChatGPT-4.0) with MDT decisions was evaluated in 100 cancer patients presented to the tumor council between November 2024 and January 2025. AI-generated treatment recommendations based on anonymized, detailed clinical summaries were compared with real-time MDT decisions. Cohen’s Kappa and Spearman correlation tests were used for statistical analysis. Results: Neoadjuvant treatment (45%) and surgery (36%) were the most frequent MDT decisions. AI recommended surgery (39%) and neoadjuvant treatment (37%) most frequently. A high concordance rate of 76.4% was observed between AI and MDT decisions (κ = 0.764 [95% CI; 0.658–0.870] p < 0.001, ρ = 0.810 [95% CI; 0.729–0.868], p < 0.001). Most inconsistencies arose in cases requiring individualized decisions, indicating AI’s current limitations in incorporating contextual clinical judgment. Conclusion: AI demonstrates substantial agreement with MDT decisions, particularly in cases adhering to standardized oncological guidelines. However, for AI integration into clinical workflows, it must evolve to interpret real-time patient data and function transparently within ethical and legal frameworks.

The ability to predict the presence of lymph node metastasis has gained significant importance in recent years due to changes in treatment strategies. Ensuring the absence of lymph node metastasis is crucial in the management of early gastric cancer. This consideration can help avoid radical treatments and facilitate organ-sparing approaches. This study aimed to retrospectively evaluate early gastric adenocarcinoma (T1a-b) cases treated with radical surgery and identify the factors that affect lymph node metastasis. A retrospective analysis was performed on 360 patients who underwent surgery for gastric adenocarcinoma were reviewed, and 41 patients diagnosed with early gastric cancer were included in the study. The relationship between patient age, gender, tumor stage, tumor size, tumor location, histological subtype, lymphovascular invasion, perineural invasion, ulceration, tumor-infiltrating lymphocytes, and lymph node metastases was analyzed. A cumulative risk score was developed using significant predictors to stratify patients into risk groups. The study cohort consisted of 41 patients, with a mean age of 63 years and 66% male. Notably, none of the 14 patients with T1a exhibited lymph node metastasis, whereas 10 of 27 (37%) patients with T1b presented with lymph node metastasis. Univariate analysis revealed that tumor stage (p = 0.009), tumor differentiation (p = 0.043), and lymphovascular invasion (p = 0.006) were significant predictors of lymph node metastasis. Multivariate analysis identified a significant association between lymphovascular invasion (p = 0.024) and tumor size (p = 0.05) with lymph node metastasis. The proposed risk scoring system effectively stratified patients into low, intermediate, and high-risk groups. Examination of radical surgical specimens suggests that organ-preserving methods based on expanded ESD criteria could be a viable option for our population. Tumor stage, histological subtype, tumor size, and lymphovascular invasion were identified as factors influencing the incidence of lymph node metastasis, with tumor stage and lymphovascular invasion emerging as primary determinants. The exploratory scoring model may aid in risk-based clinical decision-making, particularly in selecting candidates for non-surgical treatment.

Foreign body ingestion (FBI) in adults represents a clinically relevant emergency requiring endoscopic management in selected cases. Predictors of procedur

Cystobiliary communication (CBC) is a common complication of hepatic hydatid cysts, increasing surgical complexity and postoperative morbidity. Reliable preoperative prediction and intraoperative detection of occult CBC remain challenging. We retrospectively analyzed 106 patients undergoing surgery for hepatic hydatid disease. Patients were classified as CBC or non-CBC based on intraoperative findings. Clinical, laboratory, radiologic, and operative variables were evaluated. Multivariate logistic regression identified independent predictors, and Receiver Operating Characteristic (ROC) analysis determined optimal cut-offs. Subgroup analysis compared occult and frank CBC. CBC occurred in 42% of patients (16% frank, 26% occult). Multivariate analysis revealed cyst size (OR 1.29; 95% CI 1.07-1.56; p = 0.007) and direct bilirubin (OR 16.35; 95% CI 2.60-102.3; p = 0.003) as independent predictors. ROC analysis suggested thresholds of ≥ 8.85 cm for cyst size and ≥ 0.7 mg/dL for direct bilirubin. Occult CBC accounted for 26% of cases; despite intraoperative provocation tests and saline/dye injection, 25% developed high-output postoperative bile fistula, some requiring ERCP. Subgroup analysis indicated that frank CBC was associated with larger cysts, higher cholangitis rates, and more frequent intrahepatic bile duct dilatation, but postoperative outcomes were comparable. Cyst size and direct bilirubin are independently associated with CBC. Intraoperative provocation tests cannot fully exclude occult communication; vigilant postoperative monitoring and proactive biliary management are essential for high-risk patients.

The accurate preoperative differentiation of early-stage pancreatic ductal adenocarcinoma (PDAC) from benign/premalignant masses remains a clinical challen