INTRODUCTION: Endoscopic ultrasound (EUS) allows for characterization and biopsy of pancreatic lesions. Pancreatic cystic neoplasms (PCN) include mucinous (M-PCN) and nonmucinous lesions (NM-PCN). Pancreatic ductal adenocarcinoma (P-DAC) is the commonest pancreatic solid lesion (PSL), followed by pancreatic neuroendocrine tumor (P-NET). Although EUS is preferred for pancreatic lesion evaluation, its diagnostic accuracy is suboptimal. This multicentric study aims to develop a convolutional neural network (CNN) for detecting and distinguishing PCN (namely M-PCN and NM-PCN) and PSL (particularly P-DAC and P-NET). METHODS: A CNN was developed with 378 EUS examinations from 4 international reference centers (Centro Hospitalar Universitário São João, Hospital Universitario Puerta de Hierro Majadahonda, New York University Hospitals, Hospital das Clínicas Faculdade de Medicina da Universidade de São Paulo). About 126.000 images were obtained—19.528 M-PCN, 8.175 NM-PCN, 64.286 P-DAC, 29.153 P-NET, and 4.858 normal pancreas images. A trinary CNN differentiated normal pancreas tissue from M-PCN and NM-PCN. A binary CNN distinguished P-DAC from P-NET. The total data set was divided into a training and testing data set (used for model's evaluation) in a 90/10% ratio. The model was evaluated through its sensitivity, specificity, positive and negative predictive values, and accuracy. RESULTS: The CNN had 99.1% accuracy for identifying normal pancreatic tissue, 99.0% and 99.8% for M-PCN and NM-PCN, respectively. P-DAC and P-NET were distinguished with 94.0% accuracy. DISCUSSION: Our group developed the first worldwide CNN capable of detecting and differentiating the commonest PCN and PSL in EUS images, using examinations from 4 centers in 2 continents, minimizing the impact of the demographic bias. Larger multicentric studies are needed for technology implementation.

Background: Several artificial intelligence systems based on large language models (LLMs) have been commercially developed, with recent interest in integrating them for clinical questions. Recent versions now include image analysis capacity, but their performance in gastroenterology remains untested. This study assesses ChatGPT-4’s performance in interpreting gastroenterology images. Methods: A total of 740 images from five procedures—capsule endoscopy (CE), device-assisted enteroscopy (DAE), endoscopic ultrasound (EUS), digital single-operator cholangioscopy (DSOC), and high-resolution anoscopy (HRA)—were included and analyzed by ChatGPT-4 using a predefined prompt for each. ChatGPT-4 predictions were compared to gold standard diagnoses. Statistical analyses included accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the curve (AUC). Results: For CE, ChatGPT-4 demonstrated accuracies ranging from 50.0% to 90.0%, with AUCs of 0.50–0.90. For DAE, the model demonstrated an accuracy of 67.0% (AUC 0.670). For EUS, the system showed AUCs of 0.488 and 0.550 for the differentiation between pancreatic cystic and solid lesions, respectively. The LLM differentiated benign from malignant biliary strictures with an AUC of 0.550. For HRA, ChatGPT-4 showed an overall accuracy between 47.5% and 67.5%. Conclusions: ChatGPT-4 demonstrated suboptimal diagnostic accuracies for image interpretation across several gastroenterology techniques, highlighting the need for continuous improvement before clinical adoption.

Background/Objectives: Colorectal anastomotic leak (CAL) is one of the most severe postoperative complications in colorectal surgery, impacting patient morbidity and mortality. Current risk assessment methods rely on clinical and intraoperative factors, but no real-time predictive tool exists. This study aimed to develop an artificial intelligence model based on intraoperative laparoscopic recording of the anastomosis for CAL prediction. Methods: A convolutional neural network (CNN) was trained with annotated frames from colorectal surgery videos across three international high-volume centers (Instituto Português de Oncologia de Lisboa, Hospital das Clínicas de Ribeirão Preto, and Royal Liverpool University Hospital). The dataset included a total of 5356 frames from 26 patients, 2007 with CAL and 3349 showing normal anastomosis. Four CNN architectures (EfficientNetB0, EfficientNetB7, ResNet50, and MobileNetV2) were tested. The models’ performance was evaluated using their sensitivity, specificity, accuracy, and area under the receiver operating characteristic (AUROC) curve. Heatmaps were generated to identify key image regions influencing predictions. Results: The best-performing model achieved an accuracy of 99.6%, AUROC of 99.6%, sensitivity of 99.2%, specificity of 100.0%, PPV of 100.0%, and NPV of 98.9%. The model reliably identified CAL-positive frames and provided visual explanations through heatmaps. Conclusions: To our knowledge, this is the first AI model developed to predict CAL using intraoperative video analysis. Its accuracy suggests the potential to redefine surgical decision-making by providing real-time risk assessment. Further refinement with a larger dataset and diverse surgical techniques could enable intraoperative interventions to prevent CAL before it occurs, marking a paradigm shift in colorectal surgery.

Background/Objectives: Endoscopic ultrasound (EUS) is crucial for lymph node (LN) characterization, playing a key role in oncological staging and treatment guidance. EUS criteria for predicting malignancy are imprecise, and histologic diagnosis may have limitations. This multicenter study aimed to evaluate the effectiveness of a novel artificial intelligence (AI)–based system in predicting LN malignancy from EUS images. Methods: This multicenter study included EUS images from nine centers. Lesions were labeled (“malignant” or “benign”) and delimited with bounding boxes. Definitive diagnoses were based on cytology/biopsy or surgical specimens and, if negative, a minimum six-month clinical follow-up. A convolutional neural network (CNN) was developed using the YOLO (You Only Look Once) architecture, incorporating both detection and classification modules. Results: A total of 59,992 images from 82 EUS procedures were analyzed. The CNN distinguished malignant from benign lymph nodes with a sensitivity of 98.8% (95% CI: 98.5–99.2%), specificity of 99.0% (95% CI: 98.3–99.7%), and precision of 99.0% (95% CI: 98.4–99.7%). The negative and positive predictive values for malignancy were 98.8% and 99.0%, respectively. Overall diagnostic accuracy was 98.3% (95% CI: 97.6–99.1%). Conclusions: This is the first study evaluating the performance of deep learning systems for LN assessment using EUS imaging. Our AI-powered imaging model shows excellent detection and classification capabilities, emphasizing its potential to provide a valuable tool to refine LN evaluation with EUS, ultimately supporting more tailored, efficient patient care.

Background/Objectives: Functional lumen imaging probe (FLIP) panometry allows real-time assessment of the esophagogastric junction opening and esophageal body contractile activity during an endoscopic procedure. Despite the development of the Dallas Consensus, FLIP panometry analysis remains complex. Artificial intelligence (AI) models have proven their benefit in high-resolution esophageal manometry; however, data on their role in FLIP panometry are scarce. This study aims to develop an AI model for automatic classification of motility patterns during a FLIP panometry exam. Methods: A total of 105 exams from five centers from both the European and American continents were included. Several machine learning models were trained and evaluated for detection of FLIP panometry patterns. Each exam was classified with an expert consensus-based decision according to the Dallas Consensus, with division into a training and testing dataset in a patient-split design. Models’ performance was evaluated through their accuracy and area under the receiver-operating characteristic curve (AUC-ROC). Results: Pathological planimetry patterns were identified by an AdaBoost Classifier with 84.9% accuracy and a mean AUC-ROC of 0.92. Random Forest identified disorders of the esophagogastric junction opening with 86.7% accuracy and an AUC-ROC of 0.973. The Gradient Boosting Classifier identified disorders of the contractile response with 86.0% accuracy and an AUC-ROC of 0.933. Conclusions: In this study, integrating exams with different probe sizes and demographic contexts, a machine learning model accurately classified FLIP panometry exams according to the Dallas Consensus. AI-driven FLIP panometry could revolutionize the approach to this exam during an endoscopic procedure, optimizing exam accuracy, standardization, and accessibility, and transforming patient management.

Background/Objectives: Accurate mediastinal and hilar lymph node (LN) assessment is central to lung cancer staging and treatment selection. Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) has become the standard minimally invasive procedure for mediastinal staging, enabling real-time identification, characterization and sampling of LNs. Although effective, this technique remains operator dependent, and subject to interobserver variability. This study aims to report the development of a Vision Transformer-based AI model for automatic LN detection and classification on EBUS images. Methods: A multicenter, multidevice, retrospective study, using EBUS images of three referral centers (Spain and Brazil). The dataset included images of patients with benign and malignant LNs. Bounding-box annotations were applied for LN localization, and LNs were classified as benign or malignant according to histopathologic reference standards. Detection performance was evaluated with mean average precision, at an intersection over union threshold of 0.5 (mAP50). Characterization performance was assessed using accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). Results: The dataset included 6492 images from 27 patients, of whom 16 had malignant LNs. In the test set, the model achieved a mAP50 of 0.79 for LN detection. For malignant characterization, the model achieved an accuracy of 90.6%, sensitivity of 85.4%, and an AUROC of 0.938. Conclusions: The results of this study support the feasibility of AI-assisted EBUS interpretation for nodal staging workflows and raise the possibility that AI-assisted EBUS could enhance diagnostic performance, while reducing operator variability. Larger prospective studies are needed before clinical implementation.