All traces

Deep learning models demonstrated proof-of-concept ability to predict knee osteoarthritis progression from medical imaging, with internal median AUCs up to 0.87 for surgical endpoints.

In 298 Iranian male taxi drivers, ROC and Random Forest analysis of the Persian CAARS-S:SV identified total-score cutoffs with 88% sensitivity and 86.7% specificity for adult ADHD screening.

An exploratory Light Gradient Boosting Machine model predicted 1-week willingness to reuse rubber dam isolation after microscopic root canal treatment with AUC 0.939 in held-out test and 0.983 in temporal validation.

AI research is moving ADHD diagnosis away from subjective interviews toward objective, data-driven tools, with EEG emerging as preferred modality for recent models.

Federated learning models trained on distributed patient data improved predictive performance over single-site local models across AUC, F1, sensitivity, PPV and PRAUC.

AI-assisted voter verification, biometric identification, and result-monitoring systems improved administrative coordination and voter-list accuracy in elections in Thailand, Indonesia, Philippines and Myanmar.

Researchers propose an HDR governance framework for AI-created human digital twins that would protect citizen autonomy after death through advance data directives and data trustees.

Efficient low-power field target detection, measured as shorter fixation duration and faster time to first target fixation, predicts higher diagnostic accuracy in digital cytology and can be rapidly acquired through standard 3-month training.

AI systems can provide simple, clear, well-documented answers to clinical questions about managing patients with hypertension to assist practicing physicians.

GPT-4 generated responses to 20 psychosis psychoeducational questions that were rated highly for accuracy, clarity, completeness and clinical utility.

Generative AI can personalize radiology trainee learning pathways and generate synthetic imaging cases and board-style questions to augment curriculum planning and assessment.

Machine learning models that integrate clinical and radiomics features achieved high pooled discrimination for predicting hematoma expansion, poor functional outcome, and mortality in adults with spontaneous intracerebral hemorrhage.

AI systems are being used in urology and hospital care to support image interpretation, risk stratification, clinical decision-making, documentation, and workflow optimization.

A preoperative model using Evans index, tumor-fourth ventricle relationship, and preoperative CSF diversion status achieved good external discrimination for postoperative hydrocephalus after posterior fossa tumor resection.

Structural modeling tools such as AlphaFold and RoseTTAFold enable high-accuracy 3D prediction of proteins encoded by multidrug-resistant bacterial genomes, facilitating functional annotation and accelerating design of new antimicrobial compounds.