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 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 simplified approach for efficiency analysis of machine learning algorithms.

PeerJ. Computer science·2024
Same author

Ethical Data Collection for Medical Image Analysis: a Structured Approach.

Asian bioethics review·2023
Same author

Multimodal covid network: Multimodal bespoke convolutional neural network architectures for COVID-19 detection from chest X-ray's and computerized tomography scans.

International journal of imaging systems and technology·2022
Same author

Advancements of MRI-based Brain Tumor Segmentation from Traditional to Recent Trends: A Review.

Current medical imaging·2021

Related Experiment Video

Updated: Jun 12, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

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

Published on: October 10, 2018

8.2K

Trade-off between training and testing ratio in machine learning for medical image processing.

Muthuramalingam Sivakumar1, Sudhaman Parthasarathy2, Thiyagarajan Padmapriya2

  • 1Department of Computer Science and Engineering, Thiagarajar College of Engineering, Madurai, TamilNadu, India.

Peerj. Computer Science
|September 24, 2024
PubMed
Summary

Choosing the right train-test split ratio is crucial for machine learning model performance. This study shows that varying ratios significantly impacts accuracy, highlighting the need for a balanced approach to avoid overfitting or underfitting.

Keywords:
Medical image processingOverfittingTrain-test splitUnderfitting

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.7K

Related Experiment Videos

Last Updated: Jun 12, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

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

Published on: October 10, 2018

8.2K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.7K

Area of Science:

  • Computer Science
  • Data Science
  • Biomedical Imaging

Background:

  • Artificial intelligence (AI) and machine learning (ML) are increasingly vital for decision-making.
  • Model performance is highly dependent on the ratio of training to testing data.
  • Effective model generalization requires careful consideration of dataset splitting.

Purpose of the Study:

  • To investigate the impact of different train-test split ratios on ML model performance.
  • To evaluate how these ratios affect model generalization capabilities.
  • To identify optimal splitting strategies for diverse ML applications.

Main Methods:

  • Utilized the BraTS 2013 dataset for analysis.
  • Trained multiple ML models including Logistic Regression, Random Forest, K-Nearest Neighbors, and Support Vector Machines.
  • Experimented with train-test split ratios from 60:40 to 95:05.

Main Results:

  • Observed significant variations in model accuracy across different train-test split ratios.
  • Demonstrated that extreme ratios can lead to overfitting or underfitting.
  • Highlighted the trade-offs between performance metrics, statistical significance, and resource allocation.

Conclusions:

  • Selecting an optimal train-test split ratio is critical for reliable ML model development.
  • Balancing model performance and generalization requires careful ratio selection.
  • Findings provide insights into enhancing the effectiveness of ML applications through strategic data splitting.