Surgery

Artificial Intelligence for Postoperative Wound Monitoring: An Integrative Review of Digital Innovation and Clinical Feasibility.

Artificial intelligence (AI) has transformative potential in postoperative wound care through precise, automated, and timely wound assessment, yet specific applications to surgical wounds remain relatively unexplored compared to chronic wound care. This integrative review critically assesses the state-of-the-art in AI-driven postoperative wound monitoring, highlighting significant advancements, ex...

Evaluating large language models in answering patient questions about eye removal surgeries.

PURPOSE: To evaluate the performance of ChatGPT-4 and Gemini, two large language models (LLMs), in addressing frequently asked questions (FAQs) about eye removal surgeries. METHODS: A set of 24 FAQs related to enucleation and evisceration was identified through a Google search and categorized into preoperative, procedural, and postoperative topics. Each question was submitted three times to ChatGP...

Towards out-of-distribution detection using gradient vectors.

Deploying Deep Learning algorithms in the real world requires some care that is generally not considered in the training procedure. In real-world scen...

Artificial intelligence in cerebral cavernous malformations: a scoping review.

OBJECTIVES: Artificial Intelligence (AI) and Machine Learning (ML) are increasingly being applied in medical research, including studies on cerebral c...

Development of an interpretable machine learning model to predict short-term bleeding risk in patients receiving dual antithrombotic therapy following cardiac surgery.

INTRODUCTION: Bleeding is a serious complication in cardiac surgery, especially among patients receiving combined anticoagulant and antiplatelet thera...

Performance of a Novel Frameless and Maskless Robotic Head Motion Compensation System for Stereotactic Radiosurgery in a Realistic Clinical Environment with Healthy Volunteers.

PURPOSE: Stereotactic radiosurgery (SRS) is a nonsurgical method for treating brain abnormalities and small tumors. Traditional high-accuracy SRS requ...

Machine learning model for predicting a high comprehensive complication index following rectal cancer surgery.

Postoperative complications following rectal cancer surgery can significantly affect patient's health and prognosis. It has been reported that the com...

Technical Feasibility of Quantitative Susceptibility Mapping Radiomics for Predicting Deep Brain Stimulation Outcomes in Parkinson Disease.

BACKGROUND AND OBJECTIVES: Parkinson disease (PD) patients with motor complications are often considered for deep brain stimulation (DBS) surgery. Pre...

Fixed-time learning-based optimal tracking control for robotic systems with prescribed performance constraints.

This paper presents a fixed-time learning-based dynamic event-triggered control framework to address the optimal tracking control problem in robotic s...

Nivolumab plus ipilimumab for potentially resectable hepatocellular carcinoma: Long-term efficacy and biomarker exploration.

BACKGROUND & AIMS: Immune checkpoint inhibitor-based combination therapy has demonstrated high objective response rates in patients with hepatocellula...

Single Port Robot-Assisted Supraclavicular Flap Repair of Iatrogenic Hardware-Associated Pharyngeal Perforation: A Case Report.

BACKGROUND: The incidence of iatrogenic pharyngeal perforation has been reported to comprise 50%-75% of all pharyngeal perforations. In the context of...

Development and validation of a breast cancer survival prediction model based on perioperative anesthesia-related drug target genes and analysis of immune microenvironment and drug sensitivity.

INTRODUCTION: This study aimed to create a survival prediction model for breast cancer(BC) using perioperative anesthesia - related drug target genes(...

Development, external validation and integration into clinical workflow of machine learning models to support pre-operative assessment in the UK.

INTRODUCTION: Demand for surgical treatment is growing and patient complexity is increasing. The NHS England standard contract now requires that pre-o...

U-ConvNext: A Robust Approach to Glioma Segmentation in Intraoperative Ultrasound.

Intraoperative tumor imaging is critical to achieving maximal safe resection during neurosurgery, especially for low-grade glioma resection. Given the...

Generative AI in perioperative medicine and anesthesiology: ethical integration, educational innovation, and the future of clinical professionalism.

Generative artificial intelligence (AI) is rapidly transforming perioperative medicine, particularly anesthesiology, by enabling novel applications, s...

Ethics and Policy Challenges in Applying Artificial Intelligence in Medicine.

Artificial intelligence (AI) holds significant promise as a diagnostic and therapeutic adjunct, and it is being rapidly employed in health care. Imple...

Technical system of electroencephalography-based brain-computer interface: Advances, applications, and challenges.

Electroencephalography-based brain-computer interfaces have revolutionized the integration of neural signals with technological systems, offering tran...

A deep learning-clinical nomogram hybrid for predicting sentinel lymph node metastasis in melanoma.

BACKGROUND: Melanoma is a life-threatening skin malignancy, with sentinel lymph node metastasis (SLNM) serving as a critical prognostic factor. While ...

Fusion of Deep Transfer Learning and Radiomics in MRI-Based Prediction of Post-Surgical Recurrence in Soft Tissue Sarcoma.

Soft  tissue sarcomas (STS) are heterogeneous malignancies with high recurrence rates (33-39%) post-surgery, necessitating improved prognostic tools. ...

Comparison of the Diagnostic Utility of Computed Tomography Angiography Head With and Without 3-Dimensional Volume-Rendered Images for Aneurysm Detection in Subarachnoid Hemorrhage Patients Versus Digital Subtraction Angiography.

BACKGROUND AND OBJECTIVES: Generating computed tomography (CT) angiography (CTA) 3-dimensional (3D) volume-rendered (3DVR) images can be time consumin...