Tag
This article examines the evolving landscape of uveitis care, emphasizing the need to unify ophthalmologic subspecialties through education and artificial intelligence to improve outcomes for this vision-threatening condition.
The SAVE-O2 AI trial demonstrates autonomous oxygen titration significantly improves normoxemia maintenance and reduces hypoxemia duration compared to manual methods in hospitalized acutely ill adults.
This study evaluates four commercially available AI systems for diabetic retinopathy screening in Tanzania, demonstrating high sensitivity for referable and proliferative DR and highlighting considerations for implementation in low-resource
A pioneering study shows that AI-enhanced ECG screening combined with epidemiological data can identify undiagnosed Chagas disease cases, improving early detection and care in endemic Brazil.
Highlight Deep learning applied to 12-lead ECG signals enables estimation of 10-year ischemic stroke risk with moderate discrimination and good calibr
A pilot study demonstrates that ChatGPT-4 can feasibly collect accurate and satisfactory medical histories from pediatric emergency patients, streamlining triage and reducing documentation burden.
This article explores AMBUSH-AI, a novel AI-driven system utilizing ultrasound modalities to accurately predict burn wound depth, improving diagnostic accuracy beyond current clinical standards and potentially guiding optimal surgical decis
A study benchmarking large language models in gynecologic oncology demonstrates that guideline-anchored retrieval-augmented generation (RAG) configurations outperform baseline and literature-only AI systems in clinical decision support, hig
A prospective multicenter study demonstrates that AI-driven virtual native enhancement (VNE) MRI can accurately detect and quantify myocardial scars without contrast agents, potentially reducing the need for gadolinium-based imaging in clin
A pilot study evaluating Ray-Ban Meta AI eyeglasses demonstrated high accuracy in single object identification and moderate performance in descriptive tasks, suggesting promise for aiding individuals with low vision.
The MAIPI deep learning model offers a novel, accurate prognosis tool for mantle cell lymphoma, using standard H&E stained biopsy images, bypassing need for molecular tests or expert pathology, and enhancing risk stratification for indi
A novel artificial intelligence algorithm enables continuous, noninvasive monitoring of inspiratory muscle effort and patient-ventilator dyssynchrony during mechanical ventilation, demonstrating accuracy comparable to invasive gold standard
AI-enabled point-of-care EEG monitoring accurately measures seizure burden, showing a dose-dependent association with unfavorable clinical outcomes at discharge, highlighting its potential in critical care.
A study comparing physician-based surprise question, AI-driven GEST model, and a combined approach shows improved accuracy and efficiency in predicting 6-month mortality among older ED patients.
This article explores a novel AI framework that identifies distinct collagen deposition patterns in MASLD, offering improved molecular specificity and prognostic value beyond traditional fibrosis assessments.
A historically grounded review of how physicians, librarians, publishers, and now algorithms have filtered the expanding medical literature, shaping what counts as visible, credible, and clinically actionable knowledge.
A fine-tuned ensemble of tabular foundation models moderately predicted pathological complete response after TNT and showed potential to support watch-and-wait selection after recalibration.
In a large Korean health-screening cohort, chest radiograph-derived age acceleration was associated with both prevalent and incident PRISm and obstructive lung disease, supporting chest X-ray AI as a potential opportunistic marker of early
A retrospective cohort study using AI to analyze radiology reports reveals high prevalence of incidental thyroid findings, strong association with diagnostic cascades, and potential overdiagnosis of low-risk thyroid cancers.
A cross-sectional evaluation of AI-generated clinical notes found significant quality deficits compared to human-produced notes, particularly in thoroughness, organization, and usefulness.
