All traces

ChatGPT-5 provided fully guideline-concordant answers in 10 of 17 endodontic antibiotic prophylaxis scenarios, performing best on classic teaching topics like infective endocarditis prophylaxis and antibiotic selection, dosage, and timing.

Adolescents with higher rumination and depression showed greater authentic self-disclosure to generative AI, indicating GenAI is being used as an outlet for personal disclosure.

Instructors using generative AI to draft fillable study guides for introductory biology can reduce drafting time and get help organizing content and creating alternative question formats.

Advanced LLMs like ChatGPT-4.5 can provide accurate, comprehensive periodontal information to patients seeking quick answers to common gum disease questions.

Proposed EU KIDS Act would require the biggest digital platforms to prove child safety is built into design, including curbs on addictive features and AI companions.

Artist Jackie Ryan used generative AI software to produce elements of a portrait that became a finalist in the Brisbane portrait prize after the prize opened to declared AI works.

A relation-aware graph convolutional network method for medical AI legal compliance improved cross-modal legal semantic alignment and bias localization, achieving high entity alignment accuracy and root-node recall.

Machine learning with SHAP interpretability predicted enfortumab vedotin toxicities including grade 3-4 events, diarrhea, and dose skipping in advanced urothelial carcinoma patients using real-world data.

AI tools for sepsis, VTE, diabetic retinopathy, cardiac amyloidosis, and pediatric asthma were feasibly deployed into routine clinical practice across diverse health care settings.

GPT-4.1 scored poster images alone and predicted which AAST abstracts reached publication with 58.5% overall accuracy, rising to 74.2% in Violence, Societal, and Behavioral and 62.2% in Hemorrhage, Resuscitation, and Vascular Control.

Gemini AI-generated overviews provided good-quality information for management of lower limb pain in children with hypermobility-associated conditions when retrieved via Google searches.

Across UK Biobank, NHANES, and a Tianjin hospital cohort, machine learning models flagged lower bone mineral density as a recurrent contributor to age-related macular degeneration risk prediction alongside age.

A three-step ML framework using SHAP and cross-validation achieved high LOOCV AUCs and flagged self-reported factors like treatment expectations and self-efficacy as candidate predictors of recovery at 3 months in spinal pain patients receiving chiropractic care.

Researchers were able to extract asthma control and exacerbation data from routine EMRs using SQL and a large language model, suggesting it may be feasible to assess clinical remission in Japanese patients initiating triple therapy.

Combining Aidoc AI with a human radiologist increased sensitivity for intracranial hemorrhage on non-contrast head CT to 96.0% while maintaining 99.4% specificity, detecting cases missed by radiologists alone.