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

Reliability and Validity01:29

Reliability and Validity

13.2K
Reliability and validity are two important considerations that must be made with any type of data collection. Reliability refers to the ability to consistently produce a given result. In the context of psychological research, this would mean that any instruments or tools used to collect data do so in consistent, reproducible ways.
13.2K
Sensitivity, Specificity, and Predicted Value01:13

Sensitivity, Specificity, and Predicted Value

677
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...
677

You might also read

Related Articles

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

Sort by
Same author

Is it time to introduce an artificial intelligence curriculum in undergraduate medical education? medical students' perspectives: a systematic review and meta-analysis.

BMC medical education·2026
Same author

Design of a mobile application and evaluation of its effects on clinical outcomes in patients with dry eye disease: a study protocol for a randomized controlled trial.

Trials·2026
Same author

Changing the landscape of medical anatomy education: impact of flipped classroom pedagogy on learning outcomes and perceptions of medical students in practical gastrointestinal anatomy.

BMC medical education·2026
Same author

Design and evaluation of a gamified mobile application for teaching cardiac rhythm interpretation to nursing students: a quasi-experimental pre-post study.

BMC medical education·2026
Same author

Aspects Supporting and Hindering Type 2 Diabetes Self-Management in Web-Based Educational Portals: Usability Testing Study With Updated Framework in Razavi-Khorasan, Iran.

JMIR human factors·2026
Same author

Predicting nephrotic syndrome outcomes in children using machine learning: insights from a cross-sectional study.

BMC nephrology·2025

Related Experiment Video

Updated: Sep 17, 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

587

Explainable artificial intelligence for predicting medical students' performance in comprehensive assessments.

Haniye Mastour1,2, Toktam Dehghani3, Ehsan Moradi4

  • 1Department of Medical Education, School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran.

Scientific Reports
|July 3, 2025
PubMed
Summary

This study introduces a machine learning framework with explainable AI to predict medical student performance on comprehensive assessments. The model accurately identifies at-risk students, enabling targeted interventions and personalized feedback for improved educational outcomes.

Keywords:
Artificial intelligenceArtificial intelligence in educationComprehensive medical assessmentsExplainable AIMachine learningMedical licensing exams

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.1K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.6K

Related Experiment Videos

Last Updated: Sep 17, 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

587
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.1K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.6K

Area of Science:

  • Medical Education
  • Artificial Intelligence in Healthcare
  • Machine Learning Applications

Background:

  • Comprehensive medical assessments are vital but burdensome for students and institutions.
  • Current AI models lack the interpretability and reliability for educational decision-making.
  • Need for predictive analytics in medical education to support student success.

Purpose of the Study:

  • To develop and validate a machine learning (ML) framework with explainable AI (XAI) for predicting medical student performance.
  • To integrate academic and non-academic attributes for enhanced predictive accuracy.
  • To provide actionable insights for educators and learners through interpretable AI.

Main Methods:

  • Retrospective cohort study across three universities.
  • Utilized a stacking meta-model combining ensemble techniques (Random Forest, Adaptive Boosting, XGBoost).
  • Employed SHapley Additive exPlanations (SHAP) for model interpretability.

Main Results:

  • Achieved high discriminative performance with AUC-ROC of 0.97 (CMPIEs) and 0.99 (CCAs).
  • High F1-scores of 0.966 (CMPIEs) and 0.994 (CCAs) demonstrated model effectiveness.
  • Identified high-impact courses as key predictors and generated individualized risk profiles.

Conclusions:

  • The XAI-enhanced ML framework accurately predicts medical student performance on high-stakes assessments.
  • SHAP analysis offers granular insights, enabling educators to implement targeted interventions and curriculum adjustments.
  • Personalized feedback and early support can enhance learning outcomes for medical students.