AI News Archive: May 3, 2026 — Part 6
Sourced from 500+ daily AI sources, scored by relevance.
- Transforming Patient Voices into Early Predictors of Survival Using Nonlinear Mixed-Effect Models and AI/ML for Patient-Centered Decision-Making
Patient-reported outcomes (PROs) capture the patient voice and have been associated with improved clinical outcomes in oncology, but their prognostic and predictive value remains underutilized due to challenges in interpreting these highly variable and noisy PRO data. Here, we developed a quantitative modeling framework integrating nonlinear mixed-effects (NLME) and item response theory (IRT) to characterize symptom-level PRO trajectories and transform them into clinically actionable predictors. Using longitudinal PRO data from 589 patients with metastatic cancers in the PRO-TECT trial, we modeled 332,920 symptom responses to estimate patient-specific PRO trajectory parameters while accounting for variability and noise. IRT-NLME modeling captured heterogeneous symptom-level PRO dynamics and is more informative than modeling with composite PRO scores. PRO trajectory parameters were strongly associated with overall survival, acute care utilization, and treatment modifications. Machine le
- Predicting first-onset depression in adolescents: Do general population models generalize to youth with ADHD?
Background: Most studies seeking to identify youth at increased risk for depression have developed prediction models using a limited set of risk factors in general population samples. It is unclear whether these models generalize to high-risk youth. Here, we developed machine learning algorithms to predict first-onset depression in youth from the general population and high-risk youth with attention-deficit/hyperactivity disorder (ADHD). Methods: Participants were 4803 unrelated children from the ABCD study with no prior mood disorder and complete data at baseline (age 9-10 years) and 2-year follow-up. Support Vector Machine, Random Forest, and Elastic Net models were used to predict first-onsets from clinically-relevant risk factors spanning mental and physical health, cognitive, dispositional, interpersonal, and socio-environmental domains. Predictive performance was evaluated in the full sample and separately in participants with ADHD (N=584, 12.16%). Results: Models trained on the
- An Efficient and Interpretable Learning Approach for Large-Scale Histopathology Data
Prostate cancer (PCa) remains one of the leading causes of cancer-related mortality among men, and histopathological analysis of prostate biopsy specimens is central to diagnosis and risk stratification. Whole-slide Images (WSIs) capture rich morphological information, but their gigapixel scale and the large number of extracted tissue patches make exhaustive annotation and model training computationally expensive. Attention-based Multiple Instance Learning (MIL) has emerged as an effective weakly supervised framework for WSI analysis, enabling slide-level prediction without requiring patch-level annotations. However, training MIL models on large histopathology cohorts remains resource intensive because many extracted patches are non-informative, and some patches are often processed repeatedly during training. To address these challenges, we propose an efficient and interpretable learning framework for large-scale histopathology analysis. Our method combines a pathology-pretrained UNI e
- Longitudinal Tracking of Valve Regurgitation from Peripheral Photoplethysmography Using a 1D Hemodynamic Surrogate: a Joint MCMC-Kalman Framework
Aortic (AR) and mitral (MR) regurgitation are progressive valvulopathies whose management depends on tracking severity over months to years, currently via infrequent clinic-bound echocardiography. We investigated whether peripheral photoplethysmography (PPG) can track AR and MR longitudinally despite unknown day-to-day hemodynamic variation. A one-dimensional Navier--Stokes arterial model from aortic root to pedal digital artery, with parametric AR and MR at the inlet, generated distal waveforms from which we extracted eleven morphological features. Univariate sensitivity, Cramer--Rao bound, and feature-ablation analyses quantified theoretical observability under realistic noise and physiological variability. A neural surrogate of the 1D model was embedded in a joint Markov Chain Monte Carlo (MCMC)--Kalman scheme that tracked regurgitant fraction monthly while marginalizing over unknown systemic parameters. Across 240 synthetic patients spanning stable and high-risk AR and MR, with and
- A Clinical Prediction Model for Sudden Cardiac Arrest Presenting as Pulseless Electrical Activity
Background: The incidence of sudden cardiac arrest (SCA) manifesting as pulseless electrical activity (PEA) has increased, and survival remains extremely low. Methods for early identification and management of high-risk individuals are needed, but no clinical risk scores currently exist to predict PEA-SCA. Our objective was to develop and validate a clinical prediction model for PEA-SCA. Methods: From an ongoing prospective, population-based study of SCA in Portland, Oregon (catchment pop. ?1 M, 2002-2020), we identified PEA-SCA adults. Lifetime clinical records were compared with those of a control group with >50% prevalence of significant coronary disease. Prediction models were constructed using backwards stepwise logistic regression in a training dataset (67%) and evaluated in a validation dataset (33%). Model discrimination was assessed using receiver operating characteristic curves (C statistic). External validation was performed in a geographically distinct population in Ventura
- Continuous monitoring of endotracheal tube obstructions using naturally occurring pressure and flow oscillations
The endotracheal tube resistance dominates the total airway resistance in most intubated patients. Mucus deposition and biofilm formation can rapidly increase tube resistance and thereby contribute to serious ventilatory impairments, including dynamic hyperinflation, intrinsic PEEP build-up, added work of breathing, and patient-ventilator asynchrony. During controlled mechanical ventilation, an increased tube resistance can be inferred from the difference between peak and plateau pressure, but this approach fails during pressure-supported spontaneous breathing. Here, we present a method that estimates the linear and nonlinear components of tube resistance from naturally occurring airway pressure and flow fluctuations at the airway opening, without a tracheal pressure sensor and without applying mandatory forced oscillations. This is achieved by solving the equation of motion using band-pass filtered airway pressure and flow signals. Band-pass filtering isolates the relevant resistive a
- Unmeasured but Not Unbiased: The Missingness Demographic Leakage Audit (MDLA) for Calibration-Aware Fairness Evaluation in Critical Care Mortality Prediction
Objective Clinical prediction models trained on electronic health records are routinely evaluated for fairness on observed feature values, but the informativeness of which measurements are absent remains unaudited. We developed the Missingness Demographic Leakage Audit (MDLA), a reproducible four-step informatics framework that tests whether patterns of clinical measurement absence function as latent demographic proxies - constituting a bias pathway invisible to standard fairness audits. Materials and Methods We applied MDLA across development (MIMIC-IV v2.2; n=50,827; mortality 10.2%) and external validation (eICU-CRD v2.0; n=137,773; mortality 9.5%) cohorts following TRIPOD+AI standards. XGBoost, random forest, and logistic regression were trained on 43 clinical features and 44 binary missingness indicators. MDLA quantified demographic predictability from missingness alone, tested feature-level associations with Bonferroni correction, and verified model reliance via ablation. A calib
- fridgeBee
No more "what do I cook?" — ever again.
- OpenAI’s Cute New AI ‘Pets’ Can Help You Vibe Code
OpenAI’s Cute New AI ‘Pets’ Can Help You Vibe Code PCMag UK
- OpenAI adds AI pets to its Codex coding tool
OpenAI has new AI-generated pets for codex app to help you vibe code
- Sony's AI Robot Can Probably Beat You at Table Tennis
Sony is demonstrating just a small fraction of what physical AI might be able to do.
- AI may be able to detect signs of pancreatic cancer before tumors are visible on scans, study suggests
The technology identifies patterns in the pancreas that are invisible to the human eye
- convention.sh
Stop AI agents from writing sloppy TypeScript
- Cybercriminals struggling to adopt AI in their work, research suggests
Researchers analysed discussions from the CrimeBB database.
- Access all your AI tools in one spot with this Chrome extension, now $75 for life
See answers from multiple AI models in one convenient spot thanks to ChatPlayground AI.
- Largest-ever Make it in the Emirates opens on Monday with first-ever AI showcase
Largest-ever Make it in the Emirates opens Monday with 120,000 visitors plus first-ever AI showcase
- Cover Story: AI Drives Markets as Valuations Race Ahead of Earnings
Cover Story: AI Drives Markets as Valuations Race Ahead of Earnings Caixin Global
- Sam Altman invites Elon Musk to GPT-5.5 party amid $134 billion legal battle because ‘world needs more love’
OpenAI CEO Sam Altman has invited Elon Musk to the GPT-5.5 launch party amid the high profile lawsuit. Altman while handing out the invite on a social media post noted ‘world needs more love’
- Chinese court rules companies can't fire workers just because AI is cheaper — ruling says automation alone doesn't justify layoffs
Chinese courts ruled that companies cannot automatically fire workers simply because AI can do the job more cheaply, declaring that automation alone does not justify dismissal under labor law.
- It’s Illegal in China to Lay Someone Off to Replace Them with AI, Court Finds
"Employers are prohibited from shifting operating costs to employees."
- China court bars AI-only layoffs and pay cuts
The court ruled against a 40% pay cut and dismissal after AI automated a worker's role.
- Chinese court rules firms can't lay off workers on AI grounds
A Chinese court ruled that tech firms cannot fire employees solely to replace them with AI, emphasizing that technological advancement doesn't justify unilateral layoffs or salary cuts. This decision highlights the government's balancing act between fostering AI development and maintaining labor market stability amidst economic challenges and high youth unemployment.
- Chinese court says AI displacement is no excuse for firings
A Chinese court ruled that companies can’t use AI as a justification for getting rid of employees.
- Democrat and Republican Voters United on Key Issue: Hatred of Data Centers
"This is the most bipartisan issue since beer." The post Democrat and Republican Voters United on Key Issue: Hatred of Data Centers appeared first on Futurism .
- Nvidia’s push into physical AI sparks rally in Asian partners
Nvidia’s push into physical AI sparks rally in Asian partners The Japan Times
- Nvidia's push into physical AI sparks rally in Asian tech partners
Nvidia has expanded its roster of Asian partners in recent years, primarily through deeper chip-focused ties with suppliers such as SK Hynix Inc. and Samsung Electronics Co
- Systemic ELOVL6 activity predicts survival and represents a modifiable target of amyotrophic lateral sclerosis
Amyotrophic lateral sclerosis (ALS) is characterized by profound metabolic reprogramming, yet the lack of biomarkers for specific druggable targets remains a major hurdle for precision medicine. We hypothesized that peripheral lipid biosynthetic signatures could serve as both prognostic indicators and a roadmap for identifying novel disease-modifying targets. We assessed serum fatty acid (FA) metabolic pathways in two independent longitudinal cohorts (n = 37 and n = 38) using high-dimensional CoxBoost modeling. Primary outcomes were survival and functional staging milestones, including non-invasive ventilation and gastrostomy. The biological relevance of the identified candidate was further assessed through correlation with plasma neurofilament light-chain (NfL) levels. Causality and therapeutic potential were validated in Drosophila melanogaster models of TDP-43 proteinopathy via genetic ablation and pharmacological inhibition. Our multi-parametric model, comprising two clinical varia
- Adobe’s brand visibility tools for an AI-powered world
Adobe’s brand visibility tools for an AI-powered world
- Uncluttr - Clean up your tabs
The tab bar was never meant for 80+ tabs. Let AI organize it
- Blurts-Voice to Any Task App
Speak your chaos. Blurts turns it into tasks.
- Tambr
Turn any story into a multi-voice audiobook
- Posting Machine AI
Turn your LinkedIn into a sales pipeline for B2B founders
- Graphloom
The home for Etsy sellers - AI images + listings in 60s
- AI Leads
Wake up to 10 warm UK prospects daily — we do the outreach
- TripSlay
AI trip planning with maps and memories
- AI Local Recorder
100% Offline AI Voice Recorder
- Image 2
GPT Image 2
- Mom AI Agent
AI-powered parenting guide for confident moms
- CharmAii – AI Wingman
AI replies, flirting help & conversation starters
- Agent Pixels
Security Cams for pixelated agents running in Paperclip AI.
- Over/Under Market Intelligence
AI-leveraged analysis of prediction markets finds the edge
- Citedge
AI recommends your competitors. We fix that.
- Parentum
Take control of your child’s screen time with better balance
- The Multivac
Which LLM thinks best? Blind peer-judged leaderboard.
- BeVisible
Rank on Google & Get mentioned by AI
- MockRounds AI
Practice interviews that actually feel real.
- Recommend Anime: AI Tracker
AI Anime Recommendations, Anime DNA, Watchlist & Calendar