AI Model Boosts Stroke Volume Measurement Accuracy in ICU
A machine learning model improves the accuracy and yield of stroke volume measurements in critically ill patients by estimating left ...
Tag: Machine Learning
Machine learning maps how national conditions track global mental health burden
A machine-learning panel study of 183 countries from 1990 to 2023 finds that GDP per capita, urbanization and life expectancy ...
AI Takes On the Flawed Math of Measuring Leaky Heart Valves
A new review in Cardiovascular Ultrasound explains how artificial intelligence tools, including deep learning PISA segmentation and 3D Auto Color ...
Acupuncture Meets the Machine: A Closed-Loop Plan to Quantify Every Needle Move
Researchers propose a closed-loop framework that quantifies acupuncture dose, needling technique, and patient feedback to make treatment measurable and reproducible.
Interpretable Bayesian Model Spots Dengue from Routine Blood Counts in Bangladesh
A proof-of-concept study in Bangladesh shows a Tree-Augmented Naive Bayes model using routine complete blood count data detected dengue with ...
AI Research on Eating Disorders Is Booming, but Almost Nothing Reaches the Clinic
A scoping review of 66 studies finds artificial intelligence research on eating disorders has grown rapidly since 2016, yet 77 ...
Machine learning traces shifting crash severity for Florida pedestrians and bicyclists
A Florida study of 60,300 pedestrian and bicyclist crashes found injury severity relationships shifted after COVID-19, with road user mode ...
New AI Model Learns a Generative Map of EEG Microstates While Preserving Their Spatial Shape
A new convolutional variational deep embedding model learns a generative latent manifold of EEG microstate topographies, offering soft cluster assignments ...
Improved Particle Swarm Optimization and Stacking Learning Target Power Grid Load Outliers
A new IPSO-Stacking integrated learning method identifies fluctuation outliers in power grid load data, with reported coverage performance stable above ...
Blood Test Model Built with Machine Learning Distinguishes First-Episode Schizophrenia from Healthy Controls
A retrospective case-control study from a single Chinese hospital built an internally validated machine learning model using six routine blood ...
Machine Learning Flags Knowledge Gaps as Key Barrier to HIV Testing in Burkina Faso Pregnancy Care
A machine learning analysis of Burkina Faso's 2021 Demographic and Health Survey identifies HIV knowledge as the dominant modifiable predictor ...
Machine-learning model predicts when sand production begins in gas and energy wells
Researchers report a machine-learning model, trained on CFD-DEM simulations, that predicts the critical drawdown pressure gradient at which sand production ...
Gaussian Process Model Learns Interpretable Graphs for Clinical Forecasting
A new Gaussian process framework learns sparse, ordered dependency graphs from irregular electronic health records while improving forecast accuracy and ...
Nanosensors and AI Join Forces to Catch Crop Diseases Before Symptoms Show
A narrative review synthesizes how nanosensors, nanoimaging and machine-learning pipelines could enable earlier crop disease detection, while flagging unresolved gaps ...
AI Turns Raw Stress Data Into 36 Physics Features to Predict Metal Fatigue
An AI framework using physics-informed features and Bayesian optimization predicted multiaxial fatigue life across 25 metals, with XGBoost reaching a ...
Physiology-guided AI model reads small echocardiography datasets with calibrated confidence
A new machine learning framework called CARDINAL improved discrimination and calibration for grading diastolic dysfunction in a small echocardiographic cohort ...
Electrical and Optical Properties Distinguish Adipose Tissue Depots and Offer a Promising Route to Monitoring Beiging
Researchers at the University of Oslo report that the passive electrical and optical properties of adipose tissue can distinguish between ...
Machine Learning Model for Surgical Complications in Older Adults Faces Methodological Critique
A commentary identifies four methodological flaws, including data leakage and overfitting, in a machine learning model predicting post-surgical complications in ...
Machine-Learning Model Targets Cystatin C Testing in Adults with Diabetes
A nine-predictor machine-learning model using routine laboratory data identified more than half of large negative eGFR discordance cases in adults ...
AI Model Predicts Secondary-School English Performance With Built-In Uncertainty
A new computational framework claims the best mean predictive performance across four English learner corpora, forecasting writing scores and speaking-proficiency ...
