Ranks distinct AI gain and problem claims from the published record. Scores reward impact, independent source strength, scale, confidence, and recency.
In a retrospective study of 340 pancreatic ductal adenocarcinoma patients, investigators developed machine learning models combining CT radiomics and clinical predictors to predict synchronous liver metastasis preoperatively. In an independent validation cohort of 102 patients, the best linear model (LDA) reached AUC 0.828 and the nonlinear model (MLP) reached AUC 0.822, both showing good calibration with Hosmer-Lemeshow P values of 0.551 and 0.682.
Researchers systematically reviewed 41 studies through January 2025 that used deep learning to generate synthetic postcontrast T1-weighted MRI from precontrast images alone, aiming to reduce gadolinium use. Most work was in neuroimaging, using GANs and CNNs, and a targeted meta-analysis of 15 brain tumor studies reported high whole-image similarity metrics.
Researchers built a machine learning pipeline to predict retention times in capillary gas chromatography, training six algorithms on 608 data points covering 73 instrument settings and 61 C1-C12 hydrocarbons from RESTEK chromatograms and literature. The adaptive boosting support vector regression model achieved R2 scores of 0.992-0.993 on validation and testing sets.
In a cross-sectional study of 120 diabetes outpatients at a tertiary Endocrinology and Nutrition Department, researchers used the PIIXMED AI-system to analyze rectus femoris ultrasound images and quantify intramuscular fat percentage (FATi). By publication date 2026-08-24, they reported that higher FATi was associated with adverse metabolic profiles and microvascular complications.
A May 2025 peer-reviewed study surveyed 335 adults about AI anxiety, attitudes, use, and perceived knowledge. It found women reported higher anxiety and lower positive attitudes, use, and perceived knowledge than men, and that higher anxiety correlated with less positive attitudes overall.
On June 13 2025, Crime Science published a systematic literature review of AI and NLP for online fraud detection. The authors screened 2457 records and analyzed 223 studies, mapping data sources, algorithms, and evaluation metrics across 16 fraud types and summarizing best-performing methods for detecting scams in text.
Published March 2024, this peer-reviewed article analyzes automated systems used in public decision-making for migration, asylum and mobility. It finds that GDPR and AI Act definitions centered on fully automated decisions miss common practices where systems assist human decision-makers, and it proposes a taxonomy to support fundamental rights analysis.
The paper reviews persistent bottlenecks in moving evidence-based interventions into routine care and describes how data science and AI methods can help extract and synthesize implementation materials, analyze context, and support stakeholder engagement and adaptation, illustrated with a live precision oncology project and the ImpleMATE platform.
ace