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

Survival Tree01:19

Survival Tree

173
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
173
Data Validation01:15

Data Validation

283
Method validation is a crucial process in analytical chemistry designed to confirm that a given method consistently produces reliable and high-quality results. This process is essential when a method is applied to different sample matrices or when procedural modifications are made, ensuring that the results meet acceptable standards across various applications.
Key parameters for method validation include:
283
Theory of Attribution II: Kelley's Covariation Theory01:29

Theory of Attribution II: Kelley's Covariation Theory

43
Attribution theory plays a crucial role in social psychology, helping to explain how individuals interpret the causes of behavior. One prominent model within this field is Harold Kelley's covariation theory, which provides a systematic approach to determining whether internal traits or external circumstances drive a person's actions. The model posits that individuals rely on three key types of information—consensus, consistency, and distinctiveness—to make these judgments.Consensus:...
43
Variation01:19

Variation

7.2K
An important characteristic of any set of data is the variation in the data. In some data sets, the data values are concentrated closely near the mean; in other data sets, the data values are more widely spread out from the mean. The most common measure of variation, or spread, is the standard deviation, which is the square root of variance.
When independent and dependent variables are plotted on a scatter plot, the slope of a line is a value that describes the rate of change between the two...
7.2K
Classification of Systems-I01:26

Classification of Systems-I

348
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
348
Errors In Hypothesis Tests01:14

Errors In Hypothesis Tests

4.7K
When performing a hypothesis test, there are four possible outcomes depending on the actual truth (or falseness) of the null hypothesis and the decision to reject or not.
4.7K

You might also read

Related Articles

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

Sort by
Same author

Development and expert radiologist validation of a custom pipeline for simplification of oncology radiology reports using large language model.

Frontiers in oncology·2026
Same author

The impact of private equity acquisition of US hospitals on patient outcomes: A systematic review.

Journal of hospital medicine·2026
Same author

Postdeployment Monitoring and Surveillance Methods, Guidelines, and Possibilities for AI in Radiology.

Radiographics : a review publication of the Radiological Society of North America, Inc·2026
Same author

Risk Factors for Urinary Tract Infections in Patients with Multiple Sclerosis.

Neurology India·2026
Same author

Reporting checklist for foundation and large language models in medical research (REFINE): an international consensus guideline.

Diagnostic and interventional radiology (Ankara, Turkey)·2026
Same author

Efficacy and Safety of Edaravone in Amyotrophic Lateral Sclerosis: It is Safe but Does Not Stop Progression.

The Journal of the Association of Physicians of India·2025

Related Experiment Video

Updated: Oct 1, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

642

Clinical Explainability Failure (CEF) & Explainability Failure Ratio (EFR) - Changing the Way We Validate

Vasantha Kumar Venugopal1, Rohit Takhar2, Salil Gupta2

  • 1CARPL.AI, New Delhi, India. vasanth.venugopal@carpl.ai.

Journal of Medical Systems
|March 6, 2022
PubMed
Summary
This summary is machine-generated.

We introduce a new metric, Explainability Failure Ratio (EFR), to evaluate the trustworthiness of Artificial Intelligence (AI) in clinical settings. This metric assesses if AI explanations accurately reflect its diagnostic decisions, enhancing AI reliability in medical imaging.

Keywords:
AI (Artificial Intelligence)Deep learningExplainable AIMedical imaging

More Related Videos

An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

2.2K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.9K

Related Experiment Videos

Last Updated: Oct 1, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

642
An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

2.2K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.9K

Area of Science:

  • Medical Imaging Analysis
  • Artificial Intelligence in Healthcare
  • Clinical Validation of AI

Background:

  • Clinical adoption of Artificial Intelligence (AI) hinges on trustworthiness, influenced by validation, explainability, and interpretability.
  • Current AI validation in medical imaging often overlooks the accuracy of explanations (e.g., heat maps) in true positive cases.
  • A gap exists in evaluating how well AI-generated explanations align with their classification performance.

Purpose of the Study:

  • To introduce and define a novel metric, the Explainability Failure Ratio (EFR), to quantify explainability failures in AI.
  • To address the limitations in current AI evaluation metrics that do not assess the adequacy of AI-generated explanations.
  • To propose a more clinically-oriented approach to AI trustworthiness assessment.

Main Methods:

  • Defined Explainability Failure (EF) as a discrepancy between AI classification and its explanation, even when classification matches ground truth.
  • Derived the Explainability Failure Ratio (EFR) from Clinical Explainability Failure (CEF).
  • Applied the EFR metric to two AI algorithms designed for detecting consolidation on chest X-rays.

Main Results:

  • Measured EFR for two chest X-ray consolidation detection algorithms.
  • Observed a lower EFR in the algorithm with lower sensitivity for consolidation detection.
  • Demonstrated the applicability of the EFR metric in evaluating AI performance.

Conclusions:

  • AI trustworthiness requires evaluation beyond traditional statistical metrics, incorporating clinically-oriented measures like EFR.
  • The EFR metric provides a novel way to assess the adequacy of AI explanations in medical contexts.
  • Future AI validation should integrate explainability assessment to build greater clinical trust.