Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 19, 2026

Determining The Electromyographic Fatigue Threshold Following a Single Visit Exercise Test
06:00

Determining The Electromyographic Fatigue Threshold Following a Single Visit Exercise Test

Published on: July 27, 2015

Machine Learning Application to Predict Bicycle Ergometer Test Results: a Prospective Cohort Study.

E V Berezina1, K A Blinova2, O A Dmitrieva3

  • 1DSc, Head of the Department of Physics, Chemistry, and Mathematics; Ivanovo State Medical University, 8 Sheremetevsky Prospect, Ivanovo, 153012, Russia.

Sovremennye Tekhnologii V Meditsine
|May 18, 2026
PubMed
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

[A Comprehensive Regional Rehabilitation Program for Children with Hearing Impairments with Active Parental Involvement: The Ivanovo Region Experience].

Vestnik otorinolaringologii·2026
Same author

Changes in coastal ecosystems affected by overburden dumping from amber open-cut mining on the Sambia Peninsula (Baltic Sea).

Marine pollution bulletin·2024
Same author

[The periprocedural myocardial infarction and probability of the developing of the contrast-induced acute kidneys injury in clinical practice. Case report].

Terapevticheskii arkhiv·2022
Same author

[Influenza vaccination and prognosis for patients with high cardiovascular risk].

Terapevticheskii arkhiv·2022
Same author

A Sorbent with Synthetic Ligand for Removing Pro-atherogenic and Pro-inflammatory Components from Human Blood Plasma.

Acta naturae·2022
Same author

Fluorescence properties and quantum-chemical modeling of tert-butyl-substituted porphyrazines: Structural and ionization effect.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2020
Same journal

Diagnostic Potential of New Systemic Inflammation Markers (MLR, SIRI, CAR, dNLR, ALB/dNLR) in Predicting the Severity of Pathogenic Signs of Rheumatoid Arthritis.

Sovremennye tekhnologii v meditsine·2026
Same journal

A New Quantitative Method for Assessing the Ultrastructure of Cardiomyocyte Mitochondria of the Right Atrial Appendage.

Sovremennye tekhnologii v meditsine·2026
Same journal

Functional Suitability Evaluation of Radioimmunoconjugates of Nanobodies against PD-L1 and HER2/neu for Tumor Theranostics.

Sovremennye tekhnologii v meditsine·2026
Same journal

Efficiency of Kolmogorov-Arnold Networks in Small Medical Samples (Case Study of 2D Brain MRI Image Segmentation).

Sovremennye tekhnologii v meditsine·2026
Same journal

Neural Network Technologies for Age Estimation in Children from Orthopantomograms (a Pilot Study).

Sovremennye tekhnologii v meditsine·2026
Same journal

16S rRNA Metabarcoding Used to Identify the Etiology of Infective Endocarditis Agents.

Sovremennye tekhnologii v meditsine·2026
See all related articles
This summary is machine-generated.

Machine learning accurately predicts bicycle ergometry test outcomes using six-minute walk test data. This approach aids in planning cardiac rehabilitation when ergometry tests are not feasible.

Area of Science:

  • Cardiology
  • Biomedical Engineering
  • Machine Learning

Background:

  • Cardiac rehabilitation is crucial for patients post-myocardial infarction.
  • Bicycle ergometry tests (BET) and six-minute walk tests (6MWT) are common assessment tools.
  • Predictive modeling can optimize rehabilitation planning.

Purpose of the Study:

  • To develop an optimal machine learning technique to predict bicycle ergometry test (BET) results.
  • To utilize parameters from the six-minute walk test (6MWT) for these predictions.

Main Methods:

  • Employed machine learning algorithms including random forest, gradient boosting, k-nearest neighbors, and multiple linear regression.
  • Utilized data from 56 acute myocardial infarction patients undergoing cardiac rehabilitation.
Keywords:
bicycle ergometry testcardiac rehabilitationgradient boostingmachine learningpredictionsix-minute walk test

Related Experiment Videos

Last Updated: May 19, 2026

Determining The Electromyographic Fatigue Threshold Following a Single Visit Exercise Test
06:00

Determining The Electromyographic Fatigue Threshold Following a Single Visit Exercise Test

Published on: July 27, 2015

  • Evaluated model performance using determination coefficient, mean absolute error, mean square error, and root mean square error, with SHAP analysis for interpretation.

    • Main Results:

    • The gradient boosting model achieved the highest prediction accuracy (R² ≈ 0.99) for both 6MWT distance and BET metabolic equivalent.
    • Key predictors for 6MWT distance included heart rate, age, and BMI.
    • Significant factors for predicting metabolic equivalent were 6MWT distance, step count, and BMI.

    Conclusions:

    • A gradient boosting machine learning model effectively predicts BET outcomes from 6MWT data.
    • This method serves as a valuable tool for planning cardiac rehabilitation, especially when BET is challenging.
    • SHAP analysis enhanced model interpretability and confidence in predictions.