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 Videos

Predicting Daily Cardiovascular Emergencies Using Weather and Air Quality Data: A 23-Year Machine-Learning Analysis

Hsiang-Han Chen¹, Pei-Shan Tsai², Yu-Chia Chen¹

¹Department of Computer Science and Information Engineering National Taiwan Normal University Taipei Taiwan.

|June 15, 2026

Summary

Related Concept Videos

What is Weather?

What is Weather?

Steps in Outbreak Investigation

Steps in Outbreak Investigation

In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:

You might also read

Related Articles

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

Sort by

Same author

Ultra-early decompression and prevention of secondary injury in traumatic spinal cord injury: A single-center study.

The journal of spinal cord medicine·2026

Same author

Gut microbiome signatures discriminate deep vein thrombosis through machine learning and metabolic analysis.

Scientific reports·2026

Same author

Methodological comparison of capillary and venous blood parameters in pediatric <i>Mycoplasma pneumoniae</i> pneumonia: a prospective study with exploratory machine learning assessment.

Translational pediatrics·2026

Same author

Expansion Duroplasty For Severe Cervical Spinal Cord Swelling After Traumatic Injury: A Step-by-Step Surgical Protocol.

Journal of visualized experiments : JoVE·2026

Same author

Hierarchical Amplification-Interlinked CRISPR-Cas14a Luminescent Biosensor Coupled with Portable Photonic Crystal Biochip-Boosted Time-Delayed Signaling for the Diagnosis of Pediatric <i>Mycoplasma pneumoniae</i> Pneumonia.

Analytical chemistry·2026

Same author

Unplanned readmission after surgery for spinal metastases: The influence of data source on a surgical oncology quality indicator - A systematic review and descriptive meta-analysis.

European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology·2026

Same journal

Association Between Geomagnetic Activity and Unsuccessful Out-of-Hospital Cardiac Arrest.

GeoHealth·2026

Same journal

Aurora-Associated Geomagnetic Activity and Health: A Review With Focus on Neurological Implications.

GeoHealth·2026

Same journal

Residential Greenspace and Domestic Gardens, Genetic Predisposition, and Incident Glaucoma: A Prospective Cohort Study.

GeoHealth·2026

Same journal

Characterizing the Compound Extreme Temperature and PM<sub>2.5</sub> Pollution Events: A Multi-Country Analysis.

GeoHealth·2026

Same journal

Hybrid Supervised-Unsupervised Modeling for Post-Hurricane Private Well Contamination Risk Score Using Empirical Validation and Community-Informed Assessment.

GeoHealth·2026

Same journal

A Comparative Analysis of Wildland Fire Smoke PM<sub>2.5</sub> Exposure Estimates Across California From 2008 to 2018.

GeoHealth·2026

See all related articles

This summary is machine-generated.

Daily air pollution, especially nitrogen oxides (NOx), significantly predicts cardiovascular disease (CVD) emergencies, particularly in cooler weather. Machine learning models effectively forecast these events, aiding targeted public health warnings.

Area of Science:

Environmental Health
Cardiovascular Epidemiology
Data Science

Background:

Short-term weather and air quality fluctuations impact cardiovascular emergencies.
Predictive value of daily environmental factors on population-level cardiovascular disease (CVD) emergency visits is not fully understood.

Purpose of the Study:

To evaluate how weather and air quality conditions influence daily CVD emergency visits across Taiwan.
To identify high-risk environmental regimes and key predictors of CVD emergencies using machine learning.

Main Methods:

Utilized 23 years of nationwide data (2000-2022) from Taiwan.
Applied unsupervised learning (UMAP, K-means) to identify environmental patterns and high-risk days.
Trained supervised learning models (Random Forest, LightGBM, XGBoost) and used SHAP values for predictor interpretation.

Keywords:

CVD prediction air quality variable cardiovascular disease environmental health machine learning meteorological variable

Related Experiment Videos

Main Results:

High-risk CVD days were associated with cool temperatures and elevated air pollution, particularly nitrogen oxides (NOx).
Tree-based models achieved high predictive accuracy (R² up to 0.67, MAE 7-8%), with best performance for elderly populations and northern Taiwan.
NOx-related metrics were identified as dominant predictors of CVD emergency visits.

Conclusions:

Machine learning effectively predicts daily CVD emergencies using high-resolution environmental data.
Identified specific environmental regimes and pollution metrics (NOx) that increase acute CVD risk.
Results support developing region-specific early-warning systems for cardiovascular emergencies focused on air pollution monitoring.