CT-Based Machine-Learning Model Predicts Which Children Need Repeat Lung Lavage
A combined CT radiomics and clinical machine-learning model predicted the need for repeat bronchoalveolar lavage in children with mycoplasma pneumoniae ...
Tag: Machine Learning
Lightweight AI training framework sharpens dangerous blood glucose forecasts in type 1 diabetes
A new training framework called GLIMMER improves blood glucose forecasting in type 1 diabetes by penalizing errors in dangerous glucose ...
Scoping review maps generative AI in healthcare and finds a carbon blind spot
A scoping review of 24 studies finds generative AI models achieving up to 99.9 percent accuracy in healthcare tasks, but ...
Nature-Inspired Helicoidal Composites Review Maps AI-Driven Path to Impact Resistance
A new review links mantis shrimp-inspired helicoidal composites, automated fiber placement, AI-based defect control, and self-healing microparticles to superior impact ...
Connected Cars Could Become Mobile Weather Stations for Climate and COVID Research
A new review finds that sensors already built into Brazilian vehicles could complement the country's 775 fixed weather stations and ...
One Transition State, Many Products: String Method Exposes Hidden Reaction Pathways
A Saitama University team used the double-ended string method across 33 reaction systems to uncover alternative pathways that conventional reaction-path ...
AI Moves 3D Printed Concrete From Open Loop to Closed Loop
A review of 58 studies finds artificial intelligence reshaping 3D printed concrete across material design, printing process control, and structural ...
Research report: Time-dependent diffusion MRI versus conventional DWI for dual-parameter assessment of non-enhancing gliomas: IDH mutation and Ki-67 labeling index
A retrospective study of 173 patients found that time-dependent diffusion MRI models classified IDH mutation status and Ki-67 index in ...
Implantable chip reads cross-brain synchrony to flag mental states in real time
EPFL researchers have built a low-power implantable chip, LogSync, that extracts synchrony biomarkers across brain regions and decodes cognitive and ...
Potholes Predict Chaos: Machine Learning Fuses Pavement Data with Traffic Risk
A machine learning model that combines New York City pavement condition data with live traffic measurements substantially outperforms a traffic-only ...
Radar Point Clouds Get a Reality Check: YOLOv3 Beats Rivals in Landmark Detection Study
A landmark head-to-head study finds that a YOLOv3 image detector outperforms point-cloud-native and modular machine learning methods for detecting moving ...
Machine Learning Predicts Opaque Bubble Layer Risk During Keyhole Laser Vision Surgery
Machine learning models built from preoperative eye measurements predicted both the occurrence and the relative area of opaque bubble layers ...
AI models learn when to say ‘I don’t know’ through conformalized selective regression
Researchers have introduced Conformalized Selective Regression, a framework that uses conformal prediction to let regression models abstain when uncertainty is ...
Chaos theory finds footholds in cardiology, neurology and oncology, review finds
A systematic review of 20 studies finds chaos theory applied across cardiology, neurology and oncology, but with wide heterogeneity and ...
Hierarchical machine learning framework targets smarter energy management in distribution grids
A new open access study proposes a four-layer framework combining machine learning forecasting, uncertainty-aware optimization, and automated fault redispatch for ...
CT venous-phase radiomics models distinguish early from advanced gastric cancer before surgery
A retrospective study found that CT venous-phase radiomics models, led by logistic regression, distinguished early from advanced gastric cancer with ...
MRI-based radiomics nomogram predicts axillary lymph node status before breast cancer surgery
A retrospective study of 201 patients built a nomogram combining ultrafast DCE-MRI and ADC radiomics features with clinical risk factors ...
Machine learning picks the fastest linear solvers for porous media simulations
Researchers have developed a machine learning algorithm that selects and tunes preconditioned linear solvers on the fly during multiphysics porous ...
Machine learning predicts HIV patients at risk of dropping out of antiretroviral care
Random Forest and XGBoost models predicted loss to follow-up among ART patients in Zimbabwe with high internal accuracy, while LIME ...
Kinetic Models Could Bridge the Gap Between Lab-Scale Algae Wastewater Treatment and Real Industry
A new review argues that kinetic modelling of Chlorella growth, pollutant removal, and product formation is the key to scaling ...
