Endocervical gastric-type adenocarcinoma (GAS) is one of the most aggressive subtypes of cervical cancer and is frequently underdiagnosed due to morphological ambiguity, leading to delayed diagnosis. Despite the availability of molecular and genomic assays, their high cost, complexity, and limited reproducibility restrict clinical use. This study therefore proposes a highly sensitive artificial intelligence (AI)-assisted diagnostic… Continue reading Artificial intelligence-assisted histopathological diagnosis of endocervical gastric-type adenocarcinoma: a multicenter model development and validation study
Category: Tech
Explainable Machine Learning for Predicting Deep Vein Thrombosis in Critically Ill Patients with COPD: Development and Multicenter External Validation
Background: Deep vein thrombosis (DVT) is a frequent yet underrecognized complication in critically ill patients with chronic obstructive pulmonary disease (COPD). Existing risk assessment tools are not specifically tailored to this high-risk population. We aimed to develop and externally validate an interpretable machine-learning model for early prediction of DVT in ICU-admitted COPD patients.Methods: Adult COPD… Continue reading Explainable Machine Learning for Predicting Deep Vein Thrombosis in Critically Ill Patients with COPD: Development and Multicenter External Validation
Digital Therapeutics for Postoperative Rehabilitation after Arthroscopic Rotator Cuff Repair: A Single-Center, Assessor-Blinded, Randomized Pilot Study
Background: Home-based rehabilitation after arthroscopic rotator cuff repair (ARCR) often lacks objective monitoring. To address this limitation, we developed the ANAPA digital rehabilitation (DR) system, which includes a patient-facing mobile application for clinical efficacy evaluation (ANAPA ME) and a physician-facing measurement application for technical assessment (ANAPA PS). This study compared the safety and preliminary efficacy… Continue reading Digital Therapeutics for Postoperative Rehabilitation after Arthroscopic Rotator Cuff Repair: A Single-Center, Assessor-Blinded, Randomized Pilot Study
Translating artificial intelligence into clinical practice for gastrointestinal endoscopy: current applications and future perspectives
Artificial intelligence (AI) has emerged as a transformative tool in gastrointestinal (GI) endoscopy, addressing challenges in detection, diagnosis, and decision-making. In upper GI endoscopy, AI supports blind spot monitoring, Helicobacter pylori diagnosis, and the identification of premalignant and malignant lesions, with high accuracy and reduced miss rates. In lower GI endoscopy, computer-aided detection improves adenoma… Continue reading Translating artificial intelligence into clinical practice for gastrointestinal endoscopy: current applications and future perspectives
The Impact of Hypoglycaemia on Quality of Life in Adults With Type 1 Diabetes Using Contemporary Diabetes Technologies: A US National Survey
Background: Use of contemporary diabetes technologies, including continuous glucose monitoring (CGM) and hybrid closed-loop insulin pumps (HCLs), has expanded rapidly among people with Type 1 diabetes. However, limited research has characterised the impact of hypoglycaemia on quality of life in this population.Methods: We analysed cross-sectional survey data from US adults aged ≥ 18 years who… Continue reading The Impact of Hypoglycaemia on Quality of Life in Adults With Type 1 Diabetes Using Contemporary Diabetes Technologies: A US National Survey
Voluntary use of LLM-powered virtual standardized patients and medical students’ interview performance: An observational study
Background: Large language model (#LLM )-powered Virtual Standardized Patients (VSPs) offer scalable practice opportunities for clinical interviewing, but their added value within established human Standardized Patient (SP) curricula remains unclear. This study examined how self-directed VSP engagement relates to interview performance on traditional SP assessments through the lens of self-regulated learning theory.Methods: We analyzed VSP… Continue reading Voluntary use of LLM-powered virtual standardized patients and medical students’ interview performance: An observational study
AI-based burn image assessment: Reliability and clinical error patterns of multimodal large language models in a repeated-inference study
Accurate assessment of #burn depth and total body surface area (TBSA) is critical for clinical decision-making; however, it remains subjective and prone to interobserver variability. Multimodal large language models (MLLMs) are increasingly encountered in clinical contexts, but whether these systems can reliably assess burn images remains unclear. We evaluated four MLLMs (GPT-5.4 Pro, Grok 4.1,… Continue reading AI-based burn image assessment: Reliability and clinical error patterns of multimodal large language models in a repeated-inference study
Bridging the Gap: Using an Asynchronous E-Learning Module to Improve Internal Medicine Residents’ Confidence and Preparedness in Ambulatory Blood Pressure Monitoring Interpretation
Background: Ambulatory blood #pressure monitoring (ABPM) is considered a reference standard for diagnosing #hypertension and is recommended for out-of-office blood pressure assessment, yet internal medicine residents receive limited training in its interpretation. We conducted a needs assessment to identify gaps in hypertension and ABPM education and developed an asynchronous e-learning module to address these deficiencies.… Continue reading Bridging the Gap: Using an Asynchronous E-Learning Module to Improve Internal Medicine Residents’ Confidence and Preparedness in Ambulatory Blood Pressure Monitoring Interpretation
Multikingdom microbiome-based machine learning enables multiple sclerosis diagnosis
Emerging evidence suggests a role for the gut bacteria in the pathogenesis of multiple sclerosis (#MS ); however, the role of other microorganisms and their diagnostic potential for MS remain poorly explored. Here, we analyzed large-scale metagenomic data derived from fecal samples (discovery cohort n = 1152; total n = 1306 across 3 geographically diverse… Continue reading Multikingdom microbiome-based machine learning enables multiple sclerosis diagnosis
2 Medical News 