AI News Archive: May 22, 2026 — Part 16
Sourced from 500+ daily AI sources, scored by relevance.
- veo 3.1
Google Veo 3.1 — AI Video Generator Overview | JXP
- MeshGPT
Transform ideas into 3D models effortlessly with AI tools
- Claw Set -AI
Premium OpenClaw AI Hosting
- Seedance video generator
Words into Frames
- The AI Project Manager Certification
AMIGA Framework stop enterprise transformations from failing
- Guanlan Energy
Privacy-first AI room scanner for Feng Shui & energy flow
- WorldX
Type one sentence. Get a living AI world in 5 minutes.
- Release Lab by Creator Music Prompts
Check AI songs before Spotify release
- SoulCue
Your daily AI coach for emotional wellness
- WriteTitan
90 Seconds. One Post. Make The Feed Stop.
- AI Pregnancy Calorie Calculator
Personalized AI‑powered pregnancy calorie guide.
- Faux-API SMTP Relay
AI-powered SMTP relay for modern developers
- АІ Tech Partners
Since 2025, we have evolved into a leading .
- BeSyntient
First Visual Social Network for iA & People
- Scriptio
AI YouTube Script Writer for Tamil & Tanglish Creators
- LoongForge
A high-performance training framework for LLM, VLM, VLA, Wan
- GetshortifyAI
Beat the ATS. Land the Interview.
- Melody Genie
Write lyrics with the mind of any artist, 7 AI music tools.
- AI Inspo | Image to Video Generator
Turn any image into a dynamic video in seconds.
- Link To Text | Video To Text
Turn Videos and Audio Into Text in Seconds
- Dokie: AI Presentation Maker
Your AI presentation agent for instant professional slides.
- Retinal Electrophysiological Patterns in Alzheimer's Disease: A Multi-Domain Signal Processing Framework for Non-Invasive Biomarker Discovery Using a Portable ERG Device
Alzheimer's disease (AD) is a neurodegenerative disorder affecting more than 55 million people worldwide, with a diagnosis that remains predominantly clinical and frequently delayed. The electroretinogram (ERG) offers a non-invasive electrophysiological method for detecting retinal dysfunction associated with neurodegeneration; however, it remains unclear whether robust and reliable candidate biomarkers can be extracted from ERG signals beyond conventional amplitude- and latency-based parameters. Here we present a pilot study of a multi-domain signal processing framework applied to ERGs recorded from 46 participants (20 AD patients, 26 controls) with a handheld device (RETeval, LKC Technologies) using sinusoidal (1-50 Hz) and photopic ISCEV protocols. Five complementary techniques were implemented: (i) multiscale fuzzy entropy (MSFuzzyEn); (ii) FFT harmonic analysis; (iii) stimulus-response wavelet time-frequency coherence (WTC); (iv) a novel inter-cycle lag variant of sample entropy (
- Design and Validation of an AI-Assisted Sequential Screening Framework for Psychological Distress in Glaucoma
Purpose: Psychological distress is highly prevalent in glaucoma and is associated with worse adherence, reduced quality of life, and faster disease progression. However, distress is rarely assessed in ophthalmology settings due to time, workflow, and staffing constraints. We evaluated two artificial intelligence (AI)-based screening strategies, designed to efficiently identify distressed primary open angle glaucoma (POAG) patients during routine care, aiming to achieve effective, resource conscious, low burden clinical screening. Design: Hybrid retrospective cohort and prospective cross-sectional study. Participants: The retrospective cohort included >3,000 POAG patients from the Duke Ophthalmic Registry. Prospective validation was conducted in a separate 300 POAG patient cohort who completed patient-reported distress screening. Methods: Using retrospective data, a neural network model was trained to predict an electronic health record (EHR)-derived computable phenotype of distress ("s
- Predicting Substance Use and Psychotic-Like Experiences in Adolescents
Adolescence is a critical developmental window for the emergence of substance use and psychosis-spectrum symptoms, yet early risk for these outcomes remains poorly understood. Using longitudinal data from the Adolescent Brain Cognitive Development (ABCD) Study (n=10,134), we tested whether demographic, clinical, and structural and functional neuroimaging measures assessed in childhood (mean baseline age=9.96 years) predict later adolescent substance use, psychotic-like experiences, and/or their co-occurrence. Multivariate machine learning models reliably predicted later emergence of psychotic-like experiences (AUROC=0.780) and their co-occurrence with substance use (AUROC= 0.828), as well as substance use on its own (AUROC=0.626). Distinct patterns of functional brain connectivity, task-related brain activation, demographic, and clinical factors differentiated each outcome. Findings suggest that partially dissociable developmental risk profiles are detectable as early as childhood, and
- Integrated Machine Learning-PanGWAS Reveals Chromosome-Encoded Persistence Networks and Plasmid Plasticity in Recurrent Urinary Tract Infection in Escherichia coli
Background: Recurrent urinary tract infections(rUTI) represent a major clinical challenge due to persistent clinical symptoms, repeated antibiotic exposure, and increased risk of multidrug resistance. Further clinical management of rUTI remains challenging, as existing diagnostic and treatment guidelines are largely designed for uncomplicated, acute infections. Though uropathogenic Escherichia coli (UPEC) is the predominant cause of community-acquired UTIs, pathogen-derived genomic features that may predispose certain E. coli strains to repeatedly establish infection are not fully understood. Methods: To comprehensively dissect distinct genetic signals across genomic compartments that distinguish rUTI-associated isolates from those causing sporadic infection, the pan-genome analysis in three different frameworks (i) Combined genomes (chromosome + plasmid), (ii) bacterial chromosomes only and (iii) plasmid-only was conducted. A comprehensive evaluation of population structure was perfor
- Does Recording Hardware Matter for Clinical Speech Recognition Evaluating ASR Performance Across Consumer Devices
Ambient clinical intelligence (ACI) systems use automatic speech recognition (ASR) to capture patient-provider conversations for downstream clinical documentation. However, many ASR evaluations are conducted under controlled conditions using specialized hardware. We evaluated how recording devices influence transcription performance of contemporary ASR engines applied to clinical dialogue. Thirty-five primary care encounters were re-enacted from transcribed conversations and recorded using five devices simultaneously: smartphone, laptop microphone, portable recorder, clip-on microphone, and a desktop microphone. Six ASR engines were evaluated using word error rate (WER), clinical concept extraction precision and recall, and sentence-level semantic similarity. Median WER ranged from 16.7% to 20.7% across engines. Engine choice produced larger variation in transcription performance than recording device, although device-related differences were statistically significant. Overall, contemp
- MASHA: A Multi-Agent System for Healthcare Sentiment Analysis Using AI for Migraine Detection in Arabic Tweets
Migraine detection and sentiment analysis in healthcare have become increasingly important, particularly with the rise of social media platforms like Twitter, where users often share their personal health experiences. This study presents MASHA (Multi-Agent System for Healthcare Sentiment Analysis), an artificial intelligence (AI)-driven framework that integrates multiple machine learning (ML) models for sentiment analysis of Arabic tweets related to migraines. The system leverages a multi-agent architecture to handle tasks such as data acquisition, pre-processing, model training and real-time decision-making. Key ML models, including Support Vector Machines (SVM), Naive Bayes (NB) and Logistic Regression (LR), are integrated using ensemble techniques, leading to improved classification performance. Experiments conducted on a dataset of Arabic tweets demonstrate that MASHA outperforms traditional methods, achieving an accuracy of 90.0% and an F1-score of 89.46%. Moreover, the system's s
- Evidence-Graded Decision Authorization for Safe Clinical AI: A Constrained Reasoning Framework
Clinical AI systems have achieved strong predictive performance; however, prediction accuracy is not sufficient for clinical safety. Retrieval-augmented generation (RAG) improves factual accuracy, and general-purpose LLM guardrails constrain surface-level output safety, but these mechanisms do not govern the inferential gap between available clinical evidence and permissible clinical claims. We propose Evidence-Graded Decision Authorization (EGDA), a framework that separates evidence extraction, sufficiency assessment, and claim-level authorization through domain-specific rules. In a controlled experiment using 60 breast cancer decision-snapshot cases (1,260 system outputs across three arms evaluated by LLM-as-Judge with expert calibration), EGDA reduced the unjustified inference rate to 8.0% (vs. 48.7% for unconstrained LLM and 47.7% for RAG; risk difference vs. unconstrained -40.7%, 95% CI -46.9 to -34.0, p < 0.001), raised the appropriate refusal rate to 95.0% (vs. 56.9% and 56.9%;
- Genetic architecture of high-dimensional liver radiomic phenotypes and their role in common metabolic diseases
The liver plays a central role in systemic metabolism, yet large-scale genetic studies of quantitative liver imaging phenotypes remain limited. Here, we applied deep learning-based segmentation and radiomics extraction to derive 200 well-defined liver MRI features across multiple categories and imaging contrasts in 43,176 UK Biobank participants. Association analyses revealed steatosis-independent radiomic signals predicting incident chronic liver disease beyond conventional risk factors. We conducted genome-wide association studies in 37,725 individuals and identified multiple heritable liver MRI features; joint genetic structure and pleiotropy analyses demonstrated that these radiomic traits capture complex genetic architecture beyond the extent of hepatic steatosis. These MRI features showed widespread genetic overlap with plasma proteins, metabolites, and cardiometabolic traits through shared genetic loci and genetic correlations independent of adiposity. We identified putative cau
- Retrospective cohort study extracting coexisting background breast-lesion features from stage I-III invasive breast cancer
Background Background breast features are frequently noted in pathology reports alongside invasive breast cancer but rarely factor into prognosis or treatment decisions. Their relationship to tumor characteristics and patient outcomes remains incompletely characterised. Methods We conducted a retrospective cohort study of 7,603 patients with Stage I-III invasive breast cancer (diagnosed 1991-2022, age <80 years) from the Joint Breast Cancer Registry in Singapore. Natural language processing (NLP) was applied to 9,754 free-text pathology reports to extract co-existing background breast features, with accuracy validated by dual-reviewer assessment of 200 reports. Unsupervised hierarchical clustering grouped extracted features into three categories. Associations with tumor characteristics were assessed by multinomial logistic regression, and ten-year overall survival by Cox proportional hazards models (median follow-up 9.6 years; 620 deaths). Results Here we show that NLP-based extraction
- Digital biomarkers for insulin resistance screening in daily life
One in four adults has insulin resistance (IR), a modifiable driver of type-2 diabetes that can precede diagnosis by a decade. However, IR assessment remains clinic- and laboratory-based, limiting repeated population screening. We tested whether free-living wearable data can detect IR in adults with normoglycemia or prediabetes. Machine-learning models using continuous glucose monitor (CGM)-based glucose dynamics and smartwatch-based heart rate/heart rate variability were developed in Study 1 (N = 97) and externally validated without retraining in Study 2 (N = 61, 31% IR prevalence). The best-performing CGM-based model achieved AU-ROC = 0.873 [0.756-0.967] and AU-PRC = 0.816 [0.640-0.934], outperforming an anthropometrics-only baseline (AU-ROC = 0.749, AU-PRC = 0.593). Findings are the first to detect IR from wearables without blood tests or structured glucose challenges, with state-of-the-art comparable performance. By enabling continuous at-home screening, this approach can identify
- Biological aging clock from routine clinical and anthropometric measurements in diverse populations
Aging is accompanied by a progressive decline in physiological function that contributes to chronic disease development. Biological clocks estimated from high-dimensional clinical and biological measurements may provide more granular tracking of the aging processes. Current biological clocks, however, have limited cross-ancestry generalizability and clinical applicability. Here, we developed a multi-ancestry biological clock (ClinBAG) using 22 routine blood and anthropometric biomarkers in 14,328 age- and sex-balanced individuals from the All of Us Research Program. We tested the association of ClinBAG with 434 traits and evaluated its ability to predict incident disease in 152,733 non-overlapping individuals. We also conducted genome-wide association studies in European (N=74,675), African (N=22,315), and Admixed American ancestry individuals (N=19,940). Among 190 neurological phenotypes, elevated ClinBAG was associated with cognitive decline, increased incidence of dementia (HR=1.020
- Waymo pauses driverless car service in Atlanta and Texas ahead of potentially dangerous storms
Waymo has suspended driverless car services in Atlanta and Texas after one of its vehicles was stranded by flooding during heavy rains that will likely also hinder travel in a large swath of the U.S over the holiday weekend.