A multimodal risk stratification model using deep learning and tabular data
Cardiovascular disease and stroke kill millions every year, yet medicine still waits for the first symptom before acting. A team ...
Tag: model
GPT-5 Missed More Than a Quarter of Confirmed Pediatric Growth Plate Fractures on X-rays
Artificial intelligence systems that read medical images are usually celebrated for what they catch. Far less attention is paid to ...
AI model combining ultrasound and digital breast tomosynthesis improves specificity in breast cancer triage
The distinction between breast-level and participant-level output deserves careful attention when interpreting the reported performance figures. In clinical breast imaging, ...
Simple 10-point score predicts dangerous body cooling in children during fracture surgery
Every year, millions of children break an arm or a leg, and a substantial fraction of them end up on ...
New Quantum-Proof Digital Signature Survives Simulated Quantum Attacks
The race to build quantum computers has long been framed as a distant threat, but cryptographers now treat it as ...
Neighborhood Health Hubs Deliver Big Blood Pressure Gains in Underserved Communities
Five small storefront wellness centers scattered across the low-income neighborhoods of Memphis have achieved something that has long eluded the ...
Questionnaire Model Ranks HIV Testing Encounters for Extra Support
A questionnaire-based machine-learning model developed from HIV sentinel surveillance data ranked testing encounters among men who have sex with men ...
AI chatbots miss suicide risk cues when conversations unfold naturally, study finds
A controlled evaluation of ChatGPT, Gemini and Doubao shows that how prior disclosures are presented changes crisis response safety, with ...
Constructing the evaluation model of students’ behaviors participation and analysing the teaching strategies for physical education class based on YOLO11
A Yanshan University team trained YOLO11 to recognize student behaviors during Baduanjin practice sessions, achieving a stable mAP of 0.932, ...
Smarter Forecasting and Shared Storage Cut Costs in Provincial Power Markets
A new study combines optimized renewable forecasting with shared energy storage scheduling to cut operating costs and curtailment in China's ...
A rogue microRNA sabotages the neuron’s mitochondrial cleanup crew in Alzheimer’s disease
Deep inside the neurons of an aging brain, mitochondria are quietly failing. These organelles, which supply the enormous energy demands ...
When the Clock Ticks in the Cell: Exercise Timing Reshapes a Parkinson’s-Linked Enzyme
Scientists studying Parkinson's disease have long focused on the molecular wreckage left behind by faulty genes and misfolded proteins. A ...
Open-source deep learning model reads activity intensities from wrist accelerometers in chronic pain
A team of Dutch researchers has released an open-source deep learning model that converts raw wrist-worn accelerometer signals into activity ...
Bi-level surrogate model slashes cost of optimizing refinery distillation columns
Optimization design of crude oil distillation unit using bi-level surrogate model
AI Reads the Literature to Learn What Genes Do
A new transformer model called LitGene learns gene function by reading the scientific literature and aligning it with Gene Ontology ...
Model-Free Predictive Control Breaks the Modeling Bottleneck at Coal-Fired Power Plants
Coal-fired power plants are among the most unforgiving environments for advanced control engineering. Their boilers, heaters, and steam systems are ...
Safety-first AI ensemble catches every flood signal in Sri Lanka river trial
A solar-powered IoT node and a recall-optimized LSTM–XGBoost ensemble achieved 100% positive-class recall on a Sri Lankan river's single test ...
Money Flows Backward: Why Hong Kong’s Mangroves Survive on Stewardship, Not Self-Renewal
Deep in Hong Kong's Deep Bay, where skyscrapers give way to tidal mudflats and the rustle of 60,000 migratory birds, ...
AI model forecasts ICU vital signs and flags kidney injury earlier
The study's architectural choices reflect a broader shift in how machine learning researchers approach clinical time-series data. The Temporal Fusion ...
Brain Oxygen and EEG Monitors Predict Outcomes in Children With Severe Head Injuries
A new study shows that combining brain oxygen saturation, EEG-derived sedation monitoring, clinical scores and a blood biomarker can predict ...
POPULAR NEWS
-
Study Identifies HLA-B27 Positivity and Systemic Conditions in Ocular Disorder Patients
-
Peptide-Targeted Nanoparticles Show Promise for Breast Cancer MRI
-
Endothelial Activation and Stress Index Linked to Mortality in Stroke ICU Patients
-
Computational and Cellular Study Links Air Pollutants to NOS2 in Depression