An artificial intelligence model developed for marking detection and incision guidance during esophageal endoscopic submucosal dissection (ESD) demonstrated promising performance. Compared to junior endoscopists, the AI achieved a notable accuracy of 63.21%, precision rates of up to 85.76%, and an average distance error of 0.096, significantly outperforming junior practitioners while matching senior endoscopists. These results […]
Category: Digital Surgery and Telemedicine
Digital tools enhance postoperative pain management at home
A scoping review of 26 studies reveals digital and telemedicine tools significantly improve postoperative pain management at home. These technologies, including mobile apps and wearable sensors, facilitate patient monitoring and communication with healthcare professionals, leading to better pain control, reduced opioid use, and high patient satisfaction. However, challenges such as low digital literacy among some […]
AI-assisted system effectively aids esophageal lesion resections
The implementation of an artificial intelligence (AI) lesion-labeling system significantly improved the complete resection rate during endoscopic submucosal dissection (ESD) in low-volume centers. In a study involving 174 patients, 90% achieved negative lateral margins, while the en bloc resection rate stood at 98.5%. Comparatively, no significant difference was found in the lateral resection rates between […]
AI Revolutionizes Surgical Video Analysis in Cholecystectomy
AI algorithms were utilized to analyze 481 laparoscopic cholecystectomy videos, revealing that operative time elongated with case complexity. The study found that consultants had a longer duration of anatomy visualization compared to trainees, particularly in complex cases, with the cystic duct often identified before the cystic artery. By correlating AI-derived analytics with clinical variables, the […]
Machine-learning model accurately predicts gallbladder polyp malignancy
A novel machine-learning model, particularly the random forest algorithm, distinguishes between benign and malignant gallbladder polyps, utilizing clinical and ultrasound data from 1,050 patients. Key predictive factors identified include polyp size, age, fibrinogen levels, and presence of stones. The model achieved impressive performance metrics with area under the curve values ranging from 0.940 to 0.963 […]
A machine learning model predicts anastomotic leakage after surgery
An advanced interpretable machine learning model, based on the XGBoost algorithm, shows promising results in predicting anastomotic leakage (AL) following rectal cancer resection. Utilizing data from multiple centers, the model achieved an AUC of 0.984 in the test set, with high accuracy, sensitivity, and specificity. Serum calcium ion levels emerged as a critical predictor. This […]
AI model enhances diagnosis of anal injuries
A novel convolutional neural network (CNN) algorithm for endoanal ultrasound (EUS) efficiently distinguishes between benign anal injuries, notably achieving 100% accuracy for fissures. In assessing external and internal lacerations, the model demonstrated 82.5% sensitivity and 93.5% specificity, alongside 91.7% sensitivity and 85.9% specificity, respectively. This groundbreaking AI-assisted approach could significantly enhance diagnostic accuracy in proctology, […]
Deep learning model accurately predicts postoperative complications
A deep learning neural network (DLNN) showed superior predictive ability for postoperative complications in laparoscopic right hemicolectomy, achieving an accuracy of 86%. Key predictors included intraoperative minimal bleeding and adherence to fast-track recovery protocols. Compared to traditional machine learning models, the DLNN outperformed decision trees and random forests, showcasing potential for enhancing patient safety and […]
Machine learning predicts perineural invasion in cholangiocarcinoma patients
A novel machine learning model effectively predicts perineural invasion (PNI) in intrahepatic cholangiocarcinoma (ICC) patients preoperatively, offering new insights for clinical decision-making. The XGBoost algorithm demonstrated superior predictive performance, highlighting tumor size, number, and lymph node metastasis as key factors. Significant differences were observed in postoperative outcomes, with better progression-free survival and overall survival in […]
New robotic system enhances independence in endoscopic surgery
An innovative endoscopic assistive robot utilizing motion capture control allows surgeons to operate the endoscope with one hand, improving independence during procedures. The design addresses traditional friction wheel issues with an omnidirectional wheel, achieving a maximum delivery error of just 3.99% and enhancing rotational precision by 45.77%. Positive feedback emerged from both simulated and animal […]