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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

175
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
175

You might also read

Related Articles

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

Sort by
Same author

Unlocking Azulene Functionalization via Strain-Induced Azulyne Intermediates.

Journal of the American Chemical Society·2026
Same author

Integrated bioinformatics, single-cell analysis, and experimental validation identify quercetin as a potential therapeutic candidate for intervertebral disc degeneration.

Naunyn-Schmiedeberg's archives of pharmacology·2026
Same author

Deciphering small sequence differences in T cell receptor-antigen pairing.

Nature communications·2026
Same author

Gene-Specific Analysis of Clonal Hematopoiesis Identifies ASXL1 as a Risk Factor for Lung Cancer.

bioRxiv : the preprint server for biology·2026
Same author

Associations of Normalization and Regularization with Machine Learning Overfitting in Cross-dataset Classification of Deaths Using Transcriptomic and Clinical Data: A Secondary Analysis of Publicly Available Databases.

Journal of clinical and translational pathology·2026
Same author

PHKG2 confers resistance of ESCC to cisplatin and enhances CXCL8-dependent immunosuppression to exacerbate tumorigenesis.

Cell death & disease·2026
Same journal

Changes in Three-Dimensional Intrahepatic Biliary Structures in Patients With Hepatobiliary Diseases Visualized Using Tissue-Clearing Methods.

Laboratory investigation; a journal of technical methods and pathology·2026
Same journal

Genome-wide SNP-based Profiling of Loss of Heterozygosity Reveals Distinct Molecular Subgroup-specific Patterns in Gastrointestinal Stromal Tumors (GIST).

Laboratory investigation; a journal of technical methods and pathology·2026
Same journal

AI-Assisted HER2 Scoring in Breast Cancer: Diagnostic Agreement and Understanding Discordance.

Laboratory investigation; a journal of technical methods and pathology·2026
Same journal

Corrigendum to "POU2F3 in Small Cell Lung Cancer (SCLC): Diagnostic Utility in Neuroendocrine-Low/Negative SCLC and Discrimination From Other Thoracic Malignancies and Other Small Blue Round Cell Tumors" [Laboratory Investigation 2026;106(6):106124].

Laboratory investigation; a journal of technical methods and pathology·2026
Same journal

Assessing the Effects of a 3D Pathology Tissue-Processing Workflow on Downstream Molecular Analyses.

Laboratory investigation; a journal of technical methods and pathology·2026
Same journal

Transcription Factor Ets-1 is a Central Regulator of Redox Balance and Liver Regeneration Through EGF and TGF-β1 Signaling.

Laboratory investigation; a journal of technical methods and pathology·2026
See all related articles

Related Experiment Video

Updated: Nov 17, 2025

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

7.2K

Performance and efficiency of machine learning algorithms for analyzing rectangular biomedical data.

Fei Deng1, Jibing Huang1, Xiaoling Yuan2

  • 1School of Electrical and Electronic Engineering, Shanghai Institute of Technology, Shanghai, China.

Laboratory Investigation; a Journal of Technical Methods and Pathology
|February 12, 2021
PubMed
Summary
This summary is machine-generated.

Machine learning algorithms like random forests (RF) and decision trees (DT) show similar accuracy for classifying multi-category outcomes in large biomedical datasets. Optimizing feature selection enhances model efficiency without sacrificing classification performance.

More Related Videos

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.8K
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

8.5K

Related Experiment Videos

Last Updated: Nov 17, 2025

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

7.2K
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.8K
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

8.5K

Area of Science:

  • Biomedical data science
  • Machine learning applications
  • Cancer research informatics

Background:

  • Large-scale biomedical datasets ('omics, population studies, surveys) are typically rectangular with minimal missing data.
  • Increasing sample sizes necessitate more efficient and accurate analytical algorithms for rigorous research.
  • Existing machine learning (ML) algorithms' performance in classifying multi-category outcomes in such data is not well understood.

Purpose of the Study:

  • To compare the performance and efficiency of four ML algorithms (Random Forests, Decision Trees, Artificial Neural Networks, Support Vector Machines) for classifying multi-category outcomes in large, rectangular biomedical datasets.
  • To evaluate the impact of dimension reduction on classification accuracy and computational efficiency.

Main Methods:

  • Utilized a large rectangular dataset of female breast cancer cases from the Surveillance, Epidemiology, and End Results-18 database (2004-2016).
  • Classified a five-category cause of death outcome using Decision Trees (DT), Random Forests (RF), Artificial Neural Networks (ANN), and Support Vector Machines (SVM).
  • Employed tenfold cross-validation and feature optimization via dimension reduction based on information entropy.

Main Results:

  • All four ML algorithms (DT, RF, ANN, SVM) demonstrated comparable accuracy in classifying the five-category cause of death, outperforming multinomial logistic regression.
  • Dimension reduction, retaining 32 or more features, maintained classification accuracy while significantly decreasing running time for RF, ANN, and SVM.
  • RF achieved 70.23% accuracy, ANN 70.16%, DT 69.21%, and SVM 69.06%, all exceeding the 68.12% accuracy of multinomial logistic regression.

Conclusions:

  • Random Forests, Decision Trees, Artificial Neural Networks, and Support Vector Machines offer similar accuracy for multi-category outcome classification in large, rectangular biomedical datasets.
  • Feature selection and dimension reduction techniques, guided by information gain, can substantially improve model efficiency without compromising predictive accuracy.
  • This study highlights the potential of optimized ML approaches for analyzing large-scale biomedical data, particularly in cancer research.