Machine learning models significantly outperform traditional logistic regression in predicting emergency surgery for abdominal pain patients. An analysis of 38,214 individuals identified 4,208 requiring emergency surgical intervention. Key results showed that the Light GBM model achieved an area under the curve (AUC) of 0.899, improving clinical decision-making through enhanced sensitivity and specificity. Overall, these advancements […]
Category: Digital Surgery and Telemedicine
Triage-bot enhances emergency department triage efficiency in Canada.
Triage-bot, an AI-driven system based on the Canadian Triage and Acuity Scale, supports emergency department nurses by automating patient assessments. Key findings demonstrate that Triage-bot effectively measures vital signs and interprets patient expressions and tone for more accurate triage decisions. The systematic review indicates significant improvements in patient care through personalized instructions and remote monitoring. […]
Machine learning model surpasses clinical risk scores for GI bleeding
In a comparative analysis of an electronic health record-based machine learning model and established clinical risk scores for gastrointestinal bleeding, researchers found the model significantly outperformed the Glasgow-Blatchford Score and Oakland Score. With an area under the receiver-operating-characteristic curve (AUC) of 0.92 versus 0.89 (p
AI Model Effectively Quantifies Residual Pancreatic Cancer Post-Treatment
Development and validation of the ISGPP model marks a significant advancement in automating residual pancreatic cancer (RPC) quantification. The model demonstrated robust performance across diverse scanners, achieving mean F1 scores of 0.81-0.71 upon validation. A comprehensive dataset of 528 unique H&E slides from 528 patients facilitated training the model, which is now publicly available. This […]
New neural network enhances drug discovery for surgical treatments
A novel attention-based convolution transpositional interfusion network (ACTIN) has shown promising results for drug discovery with limited data. Utilizing just 393 training instances, ACTIN achieved state-of-the-art performance by leveraging graph convolution and transformer mechanisms to analyze drug and transcriptome data. It identifies pharmacophores that may benefit surgical patients, aiming to reduce complications and expedite recovery. […]
AI-driven gaming enhances laparoscopic cholecystectomy training effectiveness
An AI-powered mobile game, LapBot, was validated for teaching safe laparoscopic cholecystectomy skills. Among 903 global participants, increased game difficulty led to lower scores (p
AI Model Successfully Evaluates Surgical Skill in Robotic Distal Gastrectomy
An AI model effectively evaluates surgical skill in robotic distal gastrectomy (RDG) by accurately recognizing and analyzing instrument usage. Experienced surgeons demonstrated shorter durations using specific instruments during infrapyloric lymphadenectomy compared to non-experienced surgeons. This study showcases the feasibility of using AI for objective skill assessment in RDG, enhancing training and potentially improving patient outcomes […]
Augmented Reality System Enhances 3D Visualization in Liver Surgeries
An augmented reality (AR) system for laparoscopic liver surgery shows promise in improving visualization of internal anatomy. The system achieved a mean registration time of 2.4 minutes and a high accuracy rate of 93.8% in aligning preoperative 3D models with real-time laparoscopic images. Evaluations by surgeons demonstrate that this AR technology could significantly enhance tumor […]
Positive reaction to immersive robotic surgical training
Researchers found that using 3D visors for immersive robotic surgery training garnered positive feedback from medical students and residents. Nearly 90% of participants expressed high engagement and intention to use the technology. The median System Usability Scale score was 80, and the median Simulator Sickness Questionnaire score was 44.88. These results suggest that immersive reality […]
AI Platform Outperforms CT in Diagnosing Acute Appendicitis
Researchers validated an artificial intelligence platform for diagnosing acute appendicitis. The platform demonstrated high sensitivity (92.2%), specificity (97.2%), and negative predictive value (98.7%), outperforming CT scanning in accuracy metrics. Decision curve analysis showed a substantial net benefit, indicating the platform’s clinical utility in decision-making. The AI platform may assist clinicians in cases where access to […]