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

Related Concept Videos

Mechanistic Models: Compartment Models in Individual and Population Analysis

Mechanistic Models: Compartment Models in Individual and Population Analysis

Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...

You might also read

Related Articles

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

Sort by

Same author

Depth of neutrophil mobilization stratifies survival in ST-elevation myocardial infarction.

Nature cardiovascular research·2026

Same author

Clinical, Dietary, Lifestyle and Genetic Factors Associated With Age at Onset of Esophageal Adenocarcinoma.

United European gastroenterology journal·2026

Same author

Generalization of ML Models Between ECG and VCG Representation.

Studies in health technology and informatics·2026

Same author

DicomShield: A Pseudonymization Proxy for the Secondary Use of Imaging Data in the Research Context.

Studies in health technology and informatics·2026

Same author

Harnessing generative AI for predicting and optimizing antimicrobial peptides against drug-resistant infections.

npj antimicrobials and resistance·2026

Same author

dcFCI: Robust Causal Discovery Under Latent Confounding, Unfaithfulness, and Mixed Data.

IEEE transactions on pattern analysis and machine intelligence·2026

Search research articles

Related Experiment Video

Updated: Oct 15, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Machine learning with asymmetric abstention for biomedical decision-making.

Mariem Gandouz¹, Hajo Holzmann², Dominik Heider³

¹Department of Data Science in Biomedicine, Faculty of Mathematics and Computer Science, University of Marburg, 35032, Marburg, Germany.

BMC Medical Informatics and Decision Making

|October 27, 2021

Summary

Machine learning with abstention improves biomedical diagnostics by allowing models to abstain from low-confidence predictions. Asymmetric abstention intervals are particularly effective for imbalanced biomedical data.

Keywords:

Classification Diagnostics Machine learning Medical data science

More Related Videos

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

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

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Oct 15, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

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

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

Published on: August 16, 2020

Area of Science:

Biomedical informatics
Machine learning applications

Background:

Machine learning and artificial intelligence are increasingly used in biomedical decision-making.
Current models often lack the ability to abstain from low-confidence predictions, unlike human experts.
This can lead to critical errors in diagnostics, prognostics, and therapy recommendations.

Purpose of the Study:

To introduce and evaluate asymmetric abstention intervals for machine learning in biomedical contexts.
To compare the performance of asymmetric abstention with traditional symmetric abstention.
To determine the suitability of abstention methods for imbalanced biomedical datasets.

Main Methods:

Implementation of machine learning models incorporating abstention mechanisms.
Development and application of both symmetric and asymmetric abstention intervals.
Evaluation on three real-world imbalanced biomedical datasets.

Main Results:

Both symmetric and asymmetric abstention significantly improved classification performance across datasets.
Asymmetric abstention demonstrated comparable or reduced sample rejection rates compared to symmetric abstention.
The effectiveness of asymmetric abstention was particularly noted in highly imbalanced data scenarios.

Conclusions:

Machine learning with abstention offers a more robust approach to biomedical decision-making.
Asymmetric abstention intervals are a superior choice for handling imbalanced biomedical data.
This method enhances reliability in clinical applications by allowing models to defer uncertain predictions.