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 Videos

Global Sensitivity Analysis for Robust XAI: Quantifying Clinical Risk and Prediction Instability in Dermoscopic Image

Giulia Vannucci1, Renato Patrik Williame Coppolecchia2, Roberta Siciliano1

  • 1Department of Electrical Engineering and Information Technology, Polytechnic and Basic Sciences School, University of Naples Federico II, Napoli, Italy.

Risk Analysis : an Official Publication of the Society for Risk Analysis
|March 31, 2026
PubMed
Summary

Related Concept Videos

Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches01:23

Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches

536
Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
536
Sensitivity, Specificity, and Predicted Value01:13

Sensitivity, Specificity, and Predicted Value

1.8K
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
1.8K

You might also read

Related Articles

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

Sort by
Same author

Regularized reduced rank regression for mixed predictor and response variables.

The British journal of mathematical and statistical psychology·2026
Same author

Adjacent-room dual-console Remote Surgical Training (ReST) with takeover capability on the da Vinci Xi: a porcine-model feasibility study.

Journal of robotic surgery·2026
Same author

Reduced rank regression for mixed predictor and response variables.

The British journal of mathematical and statistical psychology·2025
Same author

Ideal Timing of Reimplantation in Patients with Periprosthetic Knee Infection Undergoing 2-Stage Exchange: A Diagnostic Scoring System.

The Journal of bone and joint surgery. American volume·2024
Same author

Platelet inhibition with orodispersible ticagrelor in acute coronary syndromes according to morphine use: the TASTER study final results.

European heart journal. Cardiovascular pharmacotherapy·2023
Same author

The combined evaluation of fibrinogen and D-dimer levels are a helpful tool to exclude periprosthetic knee infection.

Journal of orthopaedic research : official publication of the Orthopaedic Research Society·2023
Same journal

Effectiveness of Communication Strategies on Risk Perception in Technoscience: A Systematic Literature Review Through an Argumentation Theory Approach.

Risk analysis : an official publication of the Society for Risk Analysis·2026
Same journal

The Roles of Place Attachment and Geovisualizations on Hurricane Storm Surge Risk Perceptions and Behavioral Intentions.

Risk analysis : an official publication of the Society for Risk Analysis·2026
Same journal

Scientists' Experiences With Getting Help Making Strategic Communication Choices.

Risk analysis : an official publication of the Society for Risk Analysis·2026
Same journal

Correction to "Evolutionarily Optimal Risk Aversion".

Risk analysis : an official publication of the Society for Risk Analysis·2026
Same journal

Toward Resilient Cross-Regional Emergency Governance: A Demand-Driven and Propagation-Based Evolutionary Cooperation Framework.

Risk analysis : an official publication of the Society for Risk Analysis·2026
Same journal

Competition and Collaboration in the AI Race: Country-LevelDirectional Evidence for Risk Monitoring and Policy.

Risk analysis : an official publication of the Society for Risk Analysis·2026
See all related articles
This summary is machine-generated.

Deep learning models for skin cancer detection show high accuracy but are unreliable due to image variations. This study quantifies their robustness, ensuring safer clinical use of artificial intelligence diagnostic systems.

Area of Science:

  • Dermatology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Deep learning models achieve high accuracy in predicting malignant skin lesions.
  • Operational uncertainties in image acquisition (lighting, device settings, skin characteristics) compromise model reliability in clinical settings.
  • This instability creates an unquantified diagnostic risk, hindering safe clinical implementation of AI diagnostic systems.

Purpose of the Study:

  • To rigorously quantify the robustness of a convolutional neural network (CNN) architecture against variations in critical optical image parameters.
  • To move beyond simple accuracy metrics and provide a robust, risk-quantified assessment of AI model performance.
  • To establish the confidence level required for the accreditation and safe clinical deployment of AI-based diagnostic systems.
Keywords:
clinical riskconvolutional neural networkdermoscopic imagesglobal sensitivity analysis

Related Experiment Videos

Main Methods:

  • Utilized global sensitivity analysis to assess the CNN architecture's robustness.
  • Quantified the impact of five critical optical image parameters on model predictions.
  • Focused on identifying and measuring model instability under varying operational conditions.

Main Results:

  • The study successfully quantified the instability of the CNN architecture concerning optical image parameters.
  • Sensitivity analysis provided a risk-quantified assessment of the model's performance, highlighting areas of vulnerability.
  • The findings demonstrate a method for evaluating AI diagnostic system robustness beyond nominal accuracy.

Conclusions:

  • Quantifying model robustness is essential for the safe clinical implementation of AI in dermatology.
  • Global sensitivity analysis offers a rigorous approach to assessing diagnostic risk associated with AI systems.
  • This work provides a foundation for establishing confidence and accreditation for AI-based diagnostic tools in healthcare.