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: Jul 16, 2026

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells
10:37

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells

Published on: August 22, 2025

A Simulation-Based Stress-Testing Framework for Evaluating the Transportability of Imaging-Derived Logistic Risk

Betül Tiryaki Baştuğ1, Özlem Türelik2, Sinan Topuz3

  • 1Department of Radiology, Faculty of Medicine, Bilecik Şeyh Edebali University, Bilecik 11000, Türkiye.

Diagnostics (Basel, Switzerland)
|July 15, 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

Clinicopathological Evaluation of Cholesterolosis in Cholecystitis: Histopathological Patterns and Metabolic Correlates.

Journal of clinical medicine·2025
Same author

Development and Proof-of-Concept Evaluation of a Structured Reporting Template for Emergency Radiology Using Synthetic Cases.

Diagnostics (Basel, Switzerland)·2025
Same author

A Novel Radiology-Adapted Logistic Model for Non-Invasive Risk Stratification of Pigmented Superficial Skin Lesions: A Methodological Pilot Study.

Diagnostics (Basel, Switzerland)·2025
Same author

Experimental Investigation into the Effect of Variable Inflation Intervals on Capsule Thickness in Tissue Expander.

Plastic surgery (Oakville, Ont.)·2025
Same author

Age- and Gender-Based Tongue Volume Variations on Asymptomatic Patients: A Simplified Approach to Form Baseline Data for Obstructive Sleep Apnea.

Diagnostics (Basel, Switzerland)·2025
Same author

Exploring Variations in Lumbar Canal Width: An MRI Study on Asymptomatic Patients by Age and Gender.

Journal of clinical medicine·2024

This study shows that imaging-based logistic risk models are structurally robust and transportable across different skin lesion types. Simulation stress-testing confirms their reliability even with data variations, supporting clinical use.

Area of Science:

  • Medical Imaging
  • Biostatistics
  • Machine Learning in Healthcare

Background:

  • Imaging-based logistic models are crucial for non-invasive risk stratification.
  • Their robustness and transportability across diverse biological contexts require further investigation.

Purpose of the Study:

  • To develop a simulation-based stress-testing framework.
  • To evaluate the structural robustness and transportability of a radiology-adapted logistic risk model.
  • To assess model performance across distinct cutaneous lesion phenotypes under aligned and perturbed conditions.

Main Methods:

  • Implemented a simulation framework using three synthetic cohorts (nodular, subcutaneous, vascular).
  • Evaluated model performance under naïve transfer, recalibration, and revision.
Keywords:
calibrationdecision curve analysisimaging-based risk stratificationlogistic regressionmodel transportabilitysimulation-based methodologystructural perturbationstructural robustness

Related Experiment Videos

Last Updated: Jul 16, 2026

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells
10:37

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells

Published on: August 22, 2025

  • Introduced structural perturbations (coefficient changes, nonlinearities) to simulate outcome process independence.
  • Assessed performance using discrimination (ROC-AUC, PR-AUC), calibration, decision curve analysis, and Monte Carlo stability.

    • Main Results:

    • Naïve transfer showed stable discrimination (ROC-AUC ≈ 0.78-0.84) across phenotypes.
    • Calibration shifts were observed but corrected via recalibration.
    • Structural perturbations resulted in modest discrimination reduction but consistent performance patterns.
    • Structural variables were highly transferable; vascular features showed phenotype-dependent variability.
    • Decision curve analysis confirmed consistent clinical utility.

    Conclusions:

    • The radiology-adapted logistic model exhibits structural robustness across heterogeneous phenotypes.
    • Performance variations were mainly due to calibration, not structural failure.
    • Robustness persisted under structural perturbations, indicating stability beyond idealized assumptions.
    • Simulation-based stress-testing is a rigorous method for evaluating model transportability before clinical validation.