US National Health and Nutrition Examination Survey
PulseAugur coverage of US National Health and Nutrition Examination Survey — every cluster mentioning US National Health and Nutrition Examination Survey across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
Noura system enhances LLM dietary planning with executable specifications
Researchers have developed Noura, a system that enhances the planning capabilities of large language models for complex dietary management. Noura pairs LLM planning with executable personal specifications derived from c…
-
FairFRESH framework tackles household food recommendations with fairness and explainability
Researchers have developed FairFRESH, a novel neuro-symbolic framework designed to address the complexities of household food recommendations. This system learns individual user preferences and dietary rules to allocate…
-
AI model estimates biological age using diverse clinical data and SHAP
Researchers have developed a novel machine-learning framework to estimate biological age using a CatBoost regression model and SHAP for interpretability. This model was trained on a large dataset from the US National He…
-
New data fusion method tackles errors-in-variables in heterogeneous studies
Researchers have developed a novel data-fusion estimator designed to address errors-in-variables problems, particularly when dealing with heterogeneous populations and differing measurement error distributions between s…
-
New MM-GSA method analyzes input relevance from observational data
Researchers have developed MM-GSA, a novel metamodel-based approach for Global Sensitivity Analysis (GSA) using observational data. This method approximates the input-output relationship through supervised learning, add…
-
AI boom spurs "forever chemical" use in data center cooling
The burgeoning demand for AI infrastructure is driving an increase in the production of PFAS, also known as "forever chemicals," which are being used as an alternative to water for cooling data centers. Major chemical p…
-
New benchmark CoMedBench evaluates synthetic medical data utility
Researchers have introduced CoMedBench, a new benchmark designed to evaluate the fidelity and utility of synthetic medical data. This benchmark aims to address the challenges of using real patient data due to privacy re…
-
New Random Forest Method Estimates Conditional Laws for Functional Responses
Researchers have developed a new nonparametric framework for estimating conditional laws of functional outcomes, which allows for a deeper understanding of how covariates influence the distribution of entire functional …
-
LLMs simulate plausible patients but fail to represent real populations
A new study published on arXiv reveals that large language models, when tasked with simulating mental health patients, produce individually plausible cases but fail to represent realistic populations. Models like GPT-4o…
-
New research evaluates unsupervised subgrouping for health policy prioritization
A new research paper evaluates several unsupervised subgrouping methods for analyzing observational health data, aiming to identify interpretable subgroups for policy prioritization. The study compares K-means, fuzzy cl…
-
Machine learning models show bias in predicting Type 2 diabetes risk
A new study published on arXiv evaluates machine learning models for predicting Type 2 diabetes risk, finding that while models perform well internally, their effectiveness significantly decreases when applied to real-w…
-
New CardioMeta framework improves multi-disease prediction with calibrated probabilities
Researchers have developed CardioMeta, a new multi-task framework designed for the joint prediction of diabetes, hypertension, and cardiovascular disease. This framework aims to improve upon existing machine learning mo…
-
New AI framework links retinal images to systemic pathways for diabetic retinopathy
Researchers have developed Causal-RetiGraph, a novel framework that integrates retinal image analysis with systemic pathway modeling to better understand diabetic retinopathy (DR). This system constructs an interpretabl…
-
RetiSEM framework advances causal modeling for fragmented biomedical data · 2 sources tracked
Researchers have developed RetiSEM, a novel framework for recovering causal graphs and performing mediation analysis on fragmented biomedical data. This approach addresses the challenge of incomplete or non-jointly obse…
-
Machine Learning Models Offer Non-Invasive Dysglycemia Screening
Researchers have developed machine learning models for non-invasive dysglycemia risk screening, eliminating the need for laboratory tests. The LightGBM model demonstrated superior performance with an AUC of 0.820, outpe…
-
New foundation model analyzes wearable data for mental health insights
Researchers have developed a new foundation model called PAT (Pretrained Actigraphy Transformer) specifically for analyzing wearable movement data in mental health research. This open-source model uses self-supervised l…
-
Bio-inspired self-supervised learning enhances human activity recognition
Researchers have developed a new self-supervised learning approach for analyzing wrist-worn accelerometer data, aiming to improve human activity recognition (HAR). This method, inspired by bio-mechanical theories of mov…
-
New guideline tackles bias in health survey machine learning
A new guideline called Survey-aware Machine Learning (SaML) has been proposed to address biases in machine learning models trained on health survey data. Standard ML practices often overlook crucial survey design elemen…
-
New copula-based method corrects for endogeneity in treatment effect estimation
Researchers have developed a new statistical method to address endogeneity in treatment effect estimation, a common issue in healthcare research where proxy variables correlate with unobserved factors. The proposed copu…