Chest CT Scans Could Secretly Reveal Your Heart Attack Risk Years Early
Researchers show that routine chest CT scans, combined with machine learning analysis of body composition and clinical data, can opportunistically ...
Tag: Machine Learning
Small AI on the Edge, Big AI in the Cloud: New Framework Sharpens Wind Speed Forecasts
A new cloud-edge AI framework called SMWPF combines a lightweight edge predictor with a Qwen-based cloud model to cut wind ...
Smart Threshold: X-ray CT adapts apple segmentation across 12 cultivars
An adaptive porosity-based segmentation method called Smart Threshold replaces fixed thresholds in apple CT imaging, revealing cultivar-specific tissue architecture and ...
New AI Risk Score Predicts Long-Term Disability After Stroke Using Routine Blood Tests
Researchers in China have developed an internally validated machine learning model that predicts long-term post-stroke disability from routine admission blood ...
Explainable AI spots diabetes risk stages with near-perfect accuracy
A machine learning framework classifies patients across three diabetes stages with 98.7% accuracy while explaining exactly which clinical variables drove ...
AI Guards the Factory Floor: New Review Maps the Future of Industrial IoT Cybersecurity
A new systematic review of 150 studies argues that AI-driven cybersecurity for the Industrial Internet of Things has reached impressive ...
Ensemble voting method tackles the problem of imperfect clinical reference standards in physiological monitoring
When a new monitoring device disagrees with the clinical assessment it is supposed to improve, standard diagnostic accuracy analyses cannot ...
AI Reads PET Scans to Predict Breast Cancer Molecular Subtypes Without a Biopsy
A deep learning model that fuses PET imaging features with clinical data predicted breast cancer molecular subtypes non-invasively, reaching an ...
AI Reads Liver Scans to Tell Hepatitis B Cirrhosis Apart from Schistosomiasis
A multicenter Chinese study shows that a machine-learning radiomics model built from routine non-contrast CT scans, combined with clinical features, ...
Solid-state batteries: a new frontier for robotics
A new analysis argues that solid-state batteries could transform robotics, revealing that a single commercial robot consumes an EV-equivalent 60 ...
AI Steps Into RNA Drug Discovery, From Small Molecules to Oligonucleotide Therapeutics
A new review maps how artificial intelligence is transforming RNA-targeted drug discovery across both small molecules and oligonucleotide therapeutics.
AI Can Classify National CO2 Emission Levels, But Only If It Never Sees the Country Before
A new study tests whether trade, governance and environmental tax indicators can classify national CO2 emission levels, and finds that ...
AI Models Predict When Sepsis Liver Injury Patients Will Die
Interpretable machine learning models predict 7-, 14-, and 28-day mortality in sepsis-associated liver injury, outperforming modified SOFA and MELD-Na in ...
AI Learns to Simulate Combustion Chemistry 860 Times Faster Without Breaking Physics
Argonne researchers built Phy-ChemNODE, a physics-constrained autoencoder-NeuralODE framework that emulates stiff methane combustion kinetics with 6x to 860x speedups while ...
Machine learning model forecasts respiratory disease activity despite hospital reporting delays
A sentinel hospital study in Guangzhou tested a reporting-lag-aware machine learning framework for seven-day-ahead forecasting of influenza, COVID-19 and Mycoplasma ...
AI Meets Radar Echoes to Pinpoint Wiring Faults With Near-Perfect Accuracy
A French research team has combined time-domain reflectometry with temporal convolutional networks to detect, locate, and characterize wiring faults, achieving ...
DistilBERT Outperforms Perceiver in the Hunt for Fake Hotel Reviews
A comparative study finds that a fine-tuned DistilBERT pipeline reliably detects deceptive hotel reviews while a Perceiver-based pipeline collapses toward ...
Your Phone Knows When You Are Stressed: KAIST Turns Everyday App Habits Into a Mental Health Signal
KAIST researchers developed a technology called SHIRBT-MMF that identifies daily stress from repeated smartphone behaviors such as messenger chatting, web ...
Wealth, Not Diet, Drives Global Thyroid Cancer Rates, Machine Learning Study Finds
A global machine learning study of 163 countries finds that national wealth and diagnostic intensity, not diet, explain most of ...
AI Meets the Mind: How Health Data Science Is Rewiring Neuroscience and Psychology
Artificial intelligence is quietly transforming two of the most intimate fields of medicine: neuroscience and psychology. A new editorial published ...
