NCT07743658

Brief Summary

This study evaluates whether Explainable Artificial Intelligence (XAI) explanations integrated into medical training improve AI literacy, reduce cognitive workload, and enhance learner trust compared to traditional lecture methods. Third-year medical students participated in a randomized controlled trial assessing the CerViD-MultiModal diagnostic framework during a neuroimaging diagnostic module focused on fornix atrophy in early and late mild cognitive impairment

Trial Health

87
On Track

Trial Health Score

Automated assessment based on enrollment pace, timeline, and geographic reach

Enrollment
120

participants targeted

Target at P50-P75 for not_applicable

Timeline
Completed

Started May 2026

Shorter than P25 for not_applicable

Geographic Reach
1 country

1 active site

Status
completed

Health score is calculated from publicly available data and should be used for screening purposes only.

Trial Relationships

Click on a node to explore related trials.

Study Timeline

Key milestones and dates

Study Start

First participant enrolled

May 30, 2026

Completed
Same day until next milestone

Primary Completion

Last participant's last visit for primary outcome

May 30, 2026

Completed
16 days until next milestone

Study Completion

Last participant's last visit for all outcomes

June 15, 2026

Completed
1 month until next milestone

First Submitted

Initial submission to the registry

July 29, 2026

Completed
6 days until next milestone

First Posted

Study publicly available on registry

August 4, 2026

Completed
Last Updated

August 4, 2026

Status Verified

July 1, 2026

Enrollment Period

Same day

First QC Date

July 29, 2026

Last Update Submit

July 29, 2026

Conditions

Medical Education

Keywords

Explainable Artificial IntelligenceMedical Student EducationNeuroimaging InterpretationMild Cognitive ImpairmentSHAPLIME

Outcome Measures

Primary Outcomes (2)

  • AI Literacy Score

    Continuous score (0-100 scale) measuring conceptual knowledge, practical application, ethical awareness, and critical evaluation of AI systems in medicine

    Immediately post-intervention (Day 1)

  • System Usability Scale (SUS) Score

    Standardized 10-item scale assessing user perception of system usability, converted to a 0-100 overall score

    Immediately post-intervention (Day 1)

Study Arms (2)

Control Group

ACTIVE COMPARATOR

Participants complete a 45-minute traditional lecture module on AI in neuroimaging using static text and bar charts

Other: Traditional AI Lecture Module

XAI-Enhanced Group

EXPERIMENTAL

Participants complete an interactive 45-minute lecture module supplemented with CerViD-MultiModal visual XAI explanations (SHAP summary charts and LIME patient-specific explanations

Other: XAI-Enhanced Interactive Module (CerViD-MultiModal)

Interventions

Traditional AI Lecture ModuleOTHER

Standard educational instruction delivered via traditional slides and static charts explaining neuroimaging AI outputs.

Control Group
XAI-Enhanced Interactive Module (CerViD-MultiModal)OTHER

Standard educational instruction delivered via traditional slides and static charts explaining neuroimaging AI outputs.

Also known as: CerViD-MultiModal Framework, SHAP and LIME Educational Module
XAI-Enhanced Group

Eligibility Criteria

Age18 Years+
Sexall
Healthy VolunteersYes
Age GroupsAdult (18-64), Older Adult (65+)

You may qualify if:

  • Enrolled as a third-year medical student in the clinical neuroscience rotation at the University of Liberia.
  • Willing and able to complete the 45-minute educational module and post-intervention evaluations.
  • Provided informed consent to participate in the study.

You may not qualify if:

  • Prior formal coursework, professional training, or specialized technical degree in artificial intelligence, machine learning, or computer science.
  • Inability to complete the post-intervention assessment.

Contact the study team to confirm eligibility.

Sponsors & Collaborators

Study Sites (1)

University of Liberia Medical School

Monrovia, Montserrado County, 1000, Liberia

Location

Related Publications (1)

  • Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems (NeurIPS). 2017;30:4765-4774.

    BACKGROUND

MeSH Terms

Conditions

Cognitive Dysfunction

Condition Hierarchy (Ancestors)

Cognition DisordersNeurocognitive DisordersMental Disorders

Study Design

Study Type
interventional
Phase
not applicable
Allocation
RANDOMIZED
Masking
NONE
Purpose
HEALTH SERVICES RESEARCH
Intervention Model
PARALLEL
Model Details: Participants were randomized into two parallel groups (Control vs. XAI-Enhanced) for a 45-minute educational intervention.
Sponsor Type
OTHER
Responsible Party
PRINCIPAL INVESTIGATOR
PI Title
Mr.

Study Record Dates

First Submitted

July 29, 2026

First Posted

August 4, 2026

Study Start

May 30, 2026

Primary Completion

May 30, 2026

Study Completion

June 15, 2026

Last Updated

August 4, 2026

Record last verified: 2026-07

Data Sharing

IPD Sharing
Will share

De-identified individual participant data collected during the study, including post-intervention assessment scores for AI literacy, System Usability Scale (SUS) ratings, NASA Task Load Index (NASA-TLX) workload metrics, and confidence scores, will be made available upon reasonable request. All direct and indirect identifiers will be removed prior to data sharing to preserve participant privacy.

Shared Documents
STUDY PROTOCOL, SAP, ANALYTIC CODE
Time Frame
De-identified individual participant data and supporting documents will become available within 6 months following publication of the study results in a peer-reviewed journal and will remain accessible for up to 3 years.
Access Criteria
Data and supporting materials will be shared with qualified academic researchers and clinical educators whose formal proposal has been approved by the research team. Access is granted solely for scientific research and meta-analytic purposes. Requests should be submitted via email directly to the Principal Investigator.

Locations

LI(1)