Search research articles

Search research articles

Related Experiment Video

Updated: Apr 18, 2026

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Published on: July 28, 2023

A leakage-controlled machine learning framework for postprandial triglyceride phenotyping using synthetic clinical

Nattakitti Piyavechvirat¹, Yi-Jheng Huang^1,2, Qazi Mazhar Ul Haq^3,4

¹International Bachelor Program in Informatics, Yuan Ze University, Taouan, Taiwan.

Scientific Reports

|April 16, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

AI-Driven fetal distress monitoring SDN-IoMT networks.

PloS one·2025

Same author

Hierarchical graph-based integration network for propaganda detection in textual news articles on social media.

Scientific reports·2025

Same author

DeepCGAN: early Alzheimer's detection with deep convolutional generative adversarial networks.

Frontiers in medicine·2024

Same author

A Hybrid Hand-Crafted and Deep Neural Spatio-Temporal EEG Features Clustering Framework for Precise Emotional Status Recognition.

Sensors (Basel, Switzerland)·2022

Same author

Continual Learning Strategy in One-Stage Object Detection Framework Based on Experience Replay for Autonomous Driving Vehicle.

Sensors (Basel, Switzerland)·2020

Same author

Geometric and Textural Blending for 3D Model Stylization.

IEEE transactions on visualization and computer graphics·2017

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Whole blood viscosity (WBV) did not predict short-term triglyceride response in a synthetic cohort. This study highlights a privacy-preserving machine learning framework for metabolic research, emphasizing the need for real-world validation.

Area of Science:

Cardiovascular disease research
Metabolic health and disease
Biomedical data science

Background:

Whole blood viscosity (WBV) is linked to cardiometabolic risk.
The association between WBV and short-term postprandial triglyceride (TG) response is not well understood.
A novel, privacy-preserving machine learning (ML) framework was developed to investigate this relationship.

Purpose of the Study:

To assess the predictive value of WBV for short-term postprandial TG response.
To demonstrate a rigorously leakage-controlled ML framework for evaluating physiological associations.
To explore candidate physiological associations in a synthetic cohort.

Main Methods:

Utilized a statistically reconstructed, de-identified synthetic cohort.

Keywords:

Bioinformatics Calibration analysis Cardiometabolic risk Explainable artificial intelligence (XAI)Leakage-controlled modeling Machine learning Postprandial metabolism Triglyceride response Whole blood viscosity

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Related Experiment Videos

Last Updated: Apr 18, 2026

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Published on: July 28, 2023

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Implemented a leakage-controlled ML pipeline with fold-specific preprocessing and probability calibration.

Employed nested cross-validation, bootstrap uncertainty estimation, and SHAP for interpretability.

Main Results:

WBV showed negligible association with postprandial TG response in correlation and modeling analyses.
Fasting triglycerides (TG) demonstrated stable monotonic effects and clear phenotype discrimination.
A logistic regression model achieved stable discrimination (AUROC 0.91) with consistent calibration.

Conclusions:

WBV lacks reproducible predictive value for short-term postprandial TG response within this synthetic framework.
The study validates a privacy-preserving, calibration-aware ML workflow for metabolic research.
External validation in real-world cohorts is essential to confirm these findings.