Ranks distinct AI gain and problem claims from the published record. Scores reward impact, independent source strength, scale, confidence, and recency.
On August 24, 2026, a peer-reviewed study reported development and validation of an interpretable machine learning model to predict progression risk in 342 patients with normal-tension glaucoma enrolled at a tertiary hospital. The team integrated corneal biomechanical parameters, genetic risk scores, and tear molecular biomarkers, selecting predictors with LASSO and multivariable logistic regression, and compared random forest, SVM, and logistic regression models using AUC, calibration, and decision curve analysis with SHAP interpretation.
This umbrella review synthesized 27 systematic reviews with over 14 million participants to examine AI applications in mental health care between 2021 and 2025. It found AI improved early detection and risk stratification for depression, anxiety, stress, PTSD and suicidal ideation, and that chatbots and mobile platforms expanded access and engagement.
A December 2023 peer-reviewed analysis in Environmental Technology & Innovation used bibliometric methods to examine how new technologies, especially blockchain and artificial intelligence, are being applied to circular economy goals. The authors describe production and consumption as environmentally unsustainable and assess literature on opportunities and challenges.
Published December 6, 2023, this peer-reviewed literature review in Education Sciences examined 63 articles from 2010 onward on AI and machine learning in e-learning. It found adaptive algorithms are used to tailor learning paths to individual needs, with multiple studies reporting improved engagement, retention, and academic performance.
This PRISMA systematic review evaluated 33 peer-reviewed studies (2019-2026) comprising 50 deep learning models that predict knee osteoarthritis progression from medical imaging. It extracted AUC as primary outcome, categorized nine different progression definitions, and assessed bias with PROBAST-AI, finding median internal AUCs of 0.87 for surgery, 0.78 for structural, and 0.79 for symptomatic endpoints.
Researchers retrospectively analyzed 306 patients who had microscopic root canal treatment with rubber dam isolation between May and November 2025, defining willingness to reuse at 1-week follow-up as the outcome, with 246 willing and 60 unwilling. They trained six models on 26 variables and found the LightGBM model retained 12 predictors and achieved the highest exploratory AUCs of 0.939 and 0.983.
A systematic review and meta-analysis of 13 studies covering 247 sites and 158,435 patient samples evaluated federated learning models, mostly using FedAvg, against local and centralized models on diagnostic performance metrics.
By October 2025, a peer-reviewed study examined AI use in electoral management in Indonesia, Thailand, Philippines and Myanmar between 2019 and 2024, finding that biometric voter identification, cyber-based registration, and real-time result monitoring streamlined administration and improved list accuracy, particularly amplifying coordination in Thailand.
ace