Machine Learning Model Identifies Key Predictors for Acute-on-Chronic Liver Failure in Cirrhosis
A LightGBM-based diagnostic model was developed and validated in a multicenter retrospective study to improve the timely identification and risk ...
Tag: Machine Learning
New federated learning framework balances fairness, accuracy and blockchain cost
A five-stage aggregation framework called Hybrid Fair reports top F1 scores in six of eight model–dataset combinations while cutting blockchain ...
Machine learning spots RISC-V hardware attacks from processor performance counters
Researchers built the first public RISC-V dataset combining hardware performance counters with instruction traces and showed that simple tree-based models ...
AI shows promise as a complementary tool in dental education, review finds
A systematic review finds AI applications in dental education were frequently linked to favorable diagnostic and examination performance, but the ...
Artemisinin May Curb Gastric Cancer Cells by Damping ERK Signaling
A new in vitro study reports that artemisinin suppresses gastric cancer cell proliferation, migration, and invasion while reducing ERK/MAPK pathway ...
New AI System Learns Interpretable Image-Labeling Rules Without Human Feedback
Researchers report a neuro-symbolic algorithm, IDB-FOIL, that learns interpretable image-labeling rules automatically without human feedback.
Adaptive AI framework keeps intrusion detection accurate as data drifts
A new adaptive learning framework combines temporal decay weighting, sliding-window retraining and closed-loop SHAP explanations to keep intrusion detection accurate ...
AI-Powered Stethoscope Flags Hidden Congestion in Heart Failure Patients Before Discharge
An AI-based auscultation device that detects congestion in patients discharged after acute heart failure was associated with higher risks of ...
Discourse2Draft: AI Tool Turns Queries Into Cited, Structured Drafts
NIEHS researchers have developed Discourse2Draft, a model-agnostic AI application that converts a user query into a structured, citation-anchored draft using ...
Machine Learning Model Predicts Survival in Rare Aggressive Bladder Cancer
A gradient boosting machine model built on SEER data from 2,117 patients outperformed TNM staging in predicting survival in bladder ...
AI Model Combines Carotid Plaque Scans and Inflammation Trajectories to Predict Stroke Recovery
A machine-learning model that fuses carotid plaque ultrasound texture features with week-long immune-inflammation trajectories predicted 90-day outcomes after stroke thrombectomy ...
AI Model Predicts Knee Pain Severity in Professional Distance Runners
A Gaussian process regression model trained on six training and anthropometric variables predicted self-reported knee pain severity in fifty professional ...
Dual-Stream AI Network Predicts Battery Heat and Health to Warn of Thermal Risks Early
A dual-stream AI network that jointly predicts lithium-ion battery temperature and state of health achieved a 92.6 percent timely warning ...
Nickel Nanoparticles Boost CO2 Dissolution in Seawater, With an AI Model Pinpointing the Sweet Spot
CMC-stabilized nickel nanoparticles raised CO2 dissolution in natural seawater to 67.2 percent in microfluidic experiments, with a Gaussian Process Regression ...
Neural Network Spots Cell Division in Breast Cancer Tissue with High Accuracy
A customised convolutional neural network detected mitotic figures in breast cancer histopathology images with a reported accuracy of 96.6 percent, ...
Self-Distilled Graph Learning Tames Noisy Labels in Multi-Label Feature Selection
Researchers have introduced SDMFS, a unified framework combining self-distillation and adaptive label graph learning that reportedly outperforms existing multi-label feature ...
Force-Plate AI Flags Abnormal Walking Patterns in a Fraction of a Second
A compact hybrid machine-learning model called GaitScreen uses ground reaction force recordings to flag pathological gait trials for clinical review ...
Machine Learning Study Links ENTPD5 to Radioresistance in Liver Cancer
An integrated machine-learning and single-cell study identifies ENTPD5 as a context-dependent candidate marker of radioresistance in hepatocellular carcinoma, with prognostic ...
Resistance-Based Features Boost Machine Learning Fault Detection in Power Grids
A hybrid framework that turns voltage and current measurements into resistance-based statistical features enabled Random Forest to classify electrical faults ...
Machine Learning Maps Soil Salinity at Depth—and Shows Where Predictions Falter
A study in Shandong Province, China, used quantile regression forests to map soil salinity across five depth intervals down to ...
