Ranks distinct AI gain and problem claims from the published record. Scores reward impact, independent source strength, scale, confidence, and recency.
Researchers described GIN-CRC-Pareto, a graph-based multi-task learning system designed to predict miRNA-mRNA binding pairs, identify seed match pairings, and classify seed match subtypes in colorectal cancer. By publication on 2026-09-05, experiments showed strong predictive performance including 0.909 accuracy and 0.969 AUC on the binding prediction task.
In a prospective cohort analysis of 4713 participants from the Multi-Ethnic Study of Atherosclerosis, researchers developed a 10-year CVD risk model integrating clinical, lifestyle, and cognitive measures. After selecting 21 predictors, they trained logistic regression, traditional machine learning models, and H2O AutoML, with AutoML achieving the highest performance at AUC 0.882 and accuracy 0.864 by the September 2026 publication date.
Researchers developed and externally validated an ultrasound-based habitat subregional radiomics model to predict invasive breast cancer with a DCIS component before surgery. Using 1063 patients across two centers, they delineated tumors on 2D ultrasound, clustered them into three intratumoral habitats, and built machine learning models evaluated by AUC, calibration, and decision curve analysis.
In a mixed-methods study of 60 university EFL learners in two intact classes, researchers tested AI-mediated language instruction against traditional instruction. By November 2023, they reported that the AI group scored higher on post-tests of grammar, vocabulary, reading and writing, and reported higher L2 motivation and self-regulated learning strategy use, with 14 interviewed students describing more engaging, personalized experiences.
A systematic review and diagnostic meta-analysis of 20 studies, 14 in quantitative synthesis, evaluated machine learning models to predict clinical pregnancy or live birth after assisted reproductive technology. As of the August 2026 publication, pooled sensitivity was 0.737 and specificity 0.789 with a DOR of 10.49 and acceptable discrimination on SROC, but heterogeneity was very high.
Researchers compared large language models and clinicians on 34 real-world glaucoma cases, with glaucoma specialists scoring responses on medical accuracy, key-point recall, and logical completeness. AI models produced structured reasoning with weighted mean scores overlapping attending ophthalmologists and exceeding some residents.
Published October 22, 2025, this PLOS One scoping review examined literature on AI and large language models like ChatGPT in medical education. It found potential for personalized learning alongside a set of ethical challenges, synthesizing 50 studies from three major databases covering 2010 to August 2024.
A systematic review published October 14, 2025 synthesized peer-reviewed literature from January 2020 to July 2025 on AI in nutrition and dietetics, covering dietary assessment, personalized nutrition and chronic disease management, generative AI and conversational agents, public health nutrition, sensory science, and ethics.
ace