All traces

AI models using diffusion tensor imaging to detect white matter changes show potential for early Alzheimer's diagnosis with clinical value.

Retrospective validation of Harrison Enterprise CTB on 3424 ED scans showed 98.3% NPV for urgent findings, with 64% of encounters identified as true negatives potentially eligible for expedited disposition and no remaining false negatives requiring urgent intervention during the index presentation.

AIxTHY-assisted digital cytology increased sensitivity for higher-risk Bethesda categories and improved agreement with expert consensus while cutting slide review time.

Using a Super Learner ensemble to estimate propensity scores, shifting each patient's odds of receiving abciximab during PCI reduced 6-month mortality, with a strong pro-treatment incremental policy showing significant benefit.

In simulated RCT time-to-event data, random survival forest retained predictive performance better when treatment-covariate interactions were present than when they were absent.

Fully automated AI-based lesion segmentation achieved excellent overlap and high quantitative agreement with expert manual delineation for lymphoma on whole-body FDG PET/CT.

Interpretable ML models classified prevalent CVD among middle-aged and elderly CKD patients with test AUCs of 0.753 in the US NHANES cohort using XGBoost and 0.769 in the China CHARLS cohort using logistic regression.

Deep learning models, especially U-Net variants, achieved Dice scores up to 0.93 for automated segmentation of cervical tumors and related structures on MRI, suggesting improved efficiency and reproducibility over manual segmentation.

Monthly hydro-climatic machine learning models reproduced observed storage variability at two Taiwan reservoirs with high Nash-Sutcliffe efficiency when static capacity curves were assumed.

AI tools now span molecular design, synthesis planning, catalyst optimization, and product verification to compress candidate spaces and accelerate decision-making in organic synthesis workflows.

Weighted balanced accuracy (WBAn) provides a regulatory-aligned, risk-based evaluation for multiclass medical AI that weights errors by severity and links development to real-world performance, demonstrated in X-ray lung disease detection.

The AI music platform workflow update gives creators greater control over chorus variation and arrangement in AI-generated tracks.

The Joint Commitment On Frontier Responsibilities outlines four layers of internal safety monitoring and external audits intended to establish safety standards as AI firms test new products through self-policing.

Among surveyed university design students in Pakistan, AI design tools were widely adopted for idea generation and were perceived by a large majority as enhancing originality and productivity.

Journalists and AI-ethics leads in Spanish newsrooms identify establishing ethical guidelines and newsroom training as key actions to achieve responsible GenAI use.