Search research articles

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

Search research articles

Related Experiment Video

Updated: Jul 9, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Machine Learning Models for ASCVD Risk Prediction in an Asian Population - How to Validate the Model is Important.

Yu-Chung Hsiao¹, Chen-Yuan Kuo², Fang-Ju Lin^3,4

¹Department of Internal Medicine, National Taiwan University Hospital.

Acta Cardiologica Sinica

|November 29, 2023

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

Response to the correspondence regarding "age-inappropriate white matter injury reveals hidden cerebral small vessel disease burden and mortality risk".

Cerebral circulation - cognition and behavior·2026

Same author

Clinical Characteristics, Healthcare Resource Utilization, and Costs of Patients with Generalized Pustular Psoriasis in Taiwan: A National Claims Database Study.

Psoriasis (Auckland, N.Z.)·2026

Same author

Response to "Comment on 'recent trends of LDL-C control and lipid-lowering therapy in patients with ASCVD in Taiwan: 2015-2020".

Journal of the Formosan Medical Association = Taiwan yi zhi·2026

Same author

Age-inappropriate white matter injury reveals hidden cerebral small vessel disease burden and mortality risk.

Cerebral circulation - cognition and behavior·2026

Same author

Comparative evaluation of open-access Bayesian calculators for vancomycin area under the concentration-time curve estimation in non-critically ill hospitalized adults in Taiwan.

Journal of infection and chemotherapy : official journal of the Japan Society of Chemotherapy·2026

Same author

Tigecycline-Associated Hypofibrinogenemia and Major Bleeding: Incidence, Predictors, and Clinical Outcomes in a Retrospective Cohort.

Infection and drug resistance·2026

This summary is machine-generated.

Machine learning models show potential for predicting atherosclerotic cardiovascular disease (ASCVD) risk in Taiwan. Transfer learning approaches require careful validation to ensure reliable ASCVD risk prediction for improved patient care.

Area of Science:

Cardiovascular Disease Epidemiology
Machine Learning in Healthcare
Biostatistics and Predictive Modeling

Background:

Atherosclerotic cardiovascular disease (ASCVD) poses a significant global health burden, with a high prevalence in Taiwan.
Existing ASCVD risk assessment tools lack widespread acceptance and validation within the Taiwanese population.
The need for robust, localized risk prediction models is critical for effective preventative strategies.

Purpose of the Study:

To evaluate the feasibility of employing machine learning (ML) models, incorporating transfer learning, for ASCVD risk prediction in Taiwan.
To develop and validate predictive models using Taiwanese patient cohorts.
To assess the performance of ML models in predicting major adverse cardiovascular events.

Main Methods:

Keywords:

Atherosclerotic cardiovascular disease Machine learning Risk prediction model

More Related Videos

An R-Based Landscape Validation of a Competing Risk Model

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Related Experiment Videos

Last Updated: Jul 9, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

An R-Based Landscape Validation of a Competing Risk Model

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Utilized two multi-center observational registry cohorts (T-SPARCLE and T-PPARCLE) in Taiwan.
Selected predictive variables based on established European, U.S., and Asian clinical guidelines.
Employed ten-fold cross-validation and temporal validation for binary classification and time-to-event analyses.

Main Results:

Initial binary classification showed competitive performance for eXtreme Gradient Boosting (XGBoost) and random forest (AUC-ROC 0.72-0.73).
Temporal validation revealed performance degradation, with AUC-ROC dropping for XGBoost (0.66) and random forest (0.69), highlighting challenges in generalizability.
Time-to-event analyses yielded concordance indices around 0.70 across most models, indicating moderate predictive capability.

Conclusions:

Machine learning models, particularly with transfer learning, demonstrate potential utility for developing cardiovascular risk prediction tools.
Rigorous temporal validation is crucial to ensure the reliability and generalizability of ML-based risk prediction models.
Further refinement and validation are necessary for future clinical implementation to enhance patient care for ASCVD.