Survey maps how machine learning exploits privileged information
A new survey reviews 107 papers on Learning Under Privileged Information and proposes a unified taxonomy of models and integration ...
Tag: Machine Learning
Machine learning models predict disability risk in older adults across three countries
A multi-cohort study reports moderate discrimination for predicting incident disability in older adults using a seven-predictor machine learning model validated ...
Nose shape predicts sex and ethnicity in North Indian populations, machine learning study finds
Machine learning models classified sex and ethnicity from nasal morphoscopic traits in 500 North Indian adults, with ethnicity predictions reaching ...
Boosted physics-informed neural network tracks computer virus spread with vertical transmission
A boosted Physics-Informed Neural Network with a hybrid Swish–ReLU activation reproduces the dynamics of a nonlinear SI1I2R computer-virus model with ...
Satellite Data and Explainable AI Predict Regional Heart Disease Risk
A new hybrid explainable machine learning framework combines satellite environmental data with health records to predict cardiovascular disease risk at ...
AI health prediction tools lag in low-income countries, review finds
A systematic review of 64 studies finds that only about one in five AI prediction models built on electronic health ...
Strict digital parenting linked to less teen screen time, but effects fade with age
A study of 8,089 adolescents found that stricter digital parenting restrictions were linked to less screen time, though the association ...
Hybrid AI models sharpen multi-disease outbreak forecasting in Zambia
Zambian researchers report that a hybrid SEIR and transformer model forecasting six diseases together beat single-disease models for most pathogens ...
Speech-based machine learning detects Alzheimer’s across English and Greek cohorts
An acoustic-only machine-learning pipeline distinguished mild-to-moderate Alzheimer's disease from healthy controls with up to 90.4% mean accuracy across English and ...
MRI radiomics models show promise but limited stability in predicting breast cancer response to chemotherapy
A retrospective study of 272 breast cancer patients found that a clinical signature based on HER2 and nodal status was ...
Machine learning predicts human oral drug bioavailability from animal data
A machine learning pipeline trained on 192 FDA-approved compounds predicts human oral bioavailability with an R2 of 0.766, outperforming previous ...
AI Takes Aim at Beam Losses and Downtime at Europe’s Spallation Source
The European Spallation Source is developing a strategy and pilot projects to apply artificial intelligence and machine learning across its ...
AI and Quality by Design Reshape the Future of Nanofiber Wound Dressings
A new review argues that combining electrospun nanofiber mats with quality by design principles and artificial intelligence could overcome the ...
Bibliometric Map Traces Computational Social Science From Big Data to Generative AI
A bibliometric analysis of 861 Scopus-indexed articles traces how computational social science evolved from agent-based modelling to generative artificial intelligence ...
Gut Microbe Virulence Factors Power New Machine Learning Test for IBD
Machine learning models using gut microbial virulence factor profiles classified inflammatory bowel disease with up to 90.17% accuracy in an ...
Ant-Inspired AI Learns to Read the Graceful Postures of Opera Training
A hybrid deep learning framework that combines ant colony optimization with a spatio-temporal variational autoencoder recognized nine opera teaching postures ...
Blood Gene Study Nominally Flags SLC51A and TPMT as Aneurysm Markers
An integrative analysis of blood transcriptomics and genetic data nominally prioritizes SLC51A and TPMT as exploratory candidate diagnostic genes for ...
Nanoscale map charts the spatial organization of the human cell surface
Proximity labeling of 85 antigens on human immune cells has produced a nanoscale map of the surface proteome, revealing functional ...
New Sequential Recommendation Model Blends Global and Intent-Aware Representations
A new method called CEGDSR combines global and disentangled intent-aware representations to improve sequential recommendation, outperforming several strong baselines on ...
From Nanoemulsion-Templated Drug Nanoparticles to Machine Learning Property Prediction: The Research Path of Lucas Attia
An AAPS Open editorial spotlights chemical engineer Lucas Attia, whose PhD work matured nanoemulsion templating for drug nanoparticle formulation and ...
