An AI-Integrated Relational Curriculum Mapping Framework for Alignment and Transparency in Medical Education: Implementation Study

BACKGROUND: Medical school curricula are managed through fragmented, static tools that prevent faculty and curriculum committees from seeing a unified view of content scope, sequence, and licensing examination alignment. Governance relies on manual reporting that is neither timely nor consistent, and no widely adopted platform incorporates a generative AI agent that queries a relational curriculum database to produce tailored, on-demand reports. OBJECTIVE: This study aimed to design, implement, and evaluate a 4-phase, AI-integrated relational curriculum mapping framework providing faculty self-directed curriculum search; cross-course alignment reports classifying content as redundant, complementary, or a gap, with recommendations; and alignment with United States Medical Licensing Examination (USMLE) content and accreditation requirements. METHODS: We implemented the framework during academic year 2025-2026. It captures session learning objectives (SLOs) annually; maps them to program objectives, course objectives, USMLE codes, Association of American Medical Colleges keywords, and Bloom's levels using a large language model with expert verification; centralizes verified data in a relational database (Airtable) with faculty read-only search; and uses a second AI agent via an API to generate on-demand reports on scope, sequence, redundancy, gaps, and USMLE alignment across all 16 preclerkship courses and all clinical clerkship rotations. RESULTS: Course directors gained self-directed curriculum access through Airtable Extensions search. Cross-course vertical alignment reports identified redundant, complementary, and gap findings and generated course-level recommendations. An analysis of 2 preclerkship courses identified 50 matched SLO pairs across 3 USMLE pathology domains within minutes. A USMLE Step 1 alignment report across all 16 courses identified a curriculum-wide pathology coverage deficit (42% vs a target of 45%-55%) that was descriptively consistent with institutional performance data (not formally tested). An accreditation query identified all preclerkship and clerkship content on a specified topic and generated Data Collection Instrument-ready documentation within seconds. A Medical Education Program Objective coverage analysis across all 9 clinical clerkships, generated within minutes, found documented coverage for 24 of 25 (96%) program objectives and 1 objective with no matching SLO in any clerkship, a gap not previously tracked. In a blinded validation study, 3 independent course directors each coded a 30-SLO sample; agreement with the database (Fleiss κ, 3 raters plus database) was substantial at the exact-code level (κ=0.67, 95% CI 0.55-0.78) and almost perfect at the USMLE domain level (κ=0.94, 95% CI 0.88-1.00). CONCLUSIONS: An AI-integrated relational curriculum database with a faculty-facing search interface can convert curriculum governance from a periodic, retrospective activity into a continuous, self-service one, producing alignment and gap analyses within minutes rather than weeks. Workload effects have not been formally measured. Extension to assessment items and prospective correlation with licensing examination outcomes are planned.

Authors

Institutions

Publication Details

Journal
JMIR Medical Education
Published
2026-11-12
DOI
https://doi.org/10.2196/107727
Primary Topic
Innovations in Medical Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

An AI-Integrated Relational Curriculum Mapping Framework for Alignment and Transparency in Medical Education: Implementation Study

Robert M. Badeau, Danielle Dickey, Jennifer Laury
JMIR Medical Education
Innovations in Medical Education
article

An AI-Integrated Relational Curriculum Mapping Framework for Alignment and Transparency in Medical Education: Implementation Study

Robert M. Badeau, Danielle Dickey, Jennifer Laury
article en

Abstract

BACKGROUND: Medical school curricula are managed through fragmented, static tools that prevent faculty and curriculum committees from seeing a unified view of content scope, sequence, and licensing examination alignment. Governance relies on manual reporting that is neither timely nor consistent, and no widely adopted platform incorporates a generative AI agent that queries a relational curriculum database to produce tailored, on-demand reports. OBJECTIVE: This study aimed to design, implement, and evaluate a 4-phase, AI-integrated relational curriculum mapping framework providing faculty self-directed curriculum search; cross-course alignment reports classifying content as redundant, complementary, or a gap, with recommendations; and alignment with United States Medical Licensing Examination (USMLE) content and accreditation requirements. METHODS: We implemented the framework during academic year 2025-2026. It captures session learning objectives (SLOs) annually; maps them to program objectives, course objectives, USMLE codes, Association of American Medical Colleges keywords, and Bloom's levels using a large language model with expert verification; centralizes verified data in a relational database (Airtable) with faculty read-only search; and uses a second AI agent via an API to generate on-demand reports on scope, sequence, redundancy, gaps, and USMLE alignment across all 16 preclerkship courses and all clinical clerkship rotations. RESULTS: Course directors gained self-directed curriculum access through Airtable Extensions search. Cross-course vertical alignment reports identified redundant, complementary, and gap findings and generated course-level recommendations. An analysis of 2 preclerkship courses identified 50 matched SLO pairs across 3 USMLE pathology domains within minutes. A USMLE Step 1 alignment report across all 16 courses identified a curriculum-wide pathology coverage deficit (42% vs a target of 45%-55%) that was descriptively consistent with institutional performance data (not formally tested). An accreditation query identified all preclerkship and clerkship content on a specified topic and generated Data Collection Instrument-ready documentation within seconds. A Medical Education Program Objective coverage analysis across all 9 clinical clerkships, generated within minutes, found documented coverage for 24 of 25 (96%) program objectives and 1 objective with no matching SLO in any clerkship, a gap not previously tracked. In a blinded validation study, 3 independent course directors each coded a 30-SLO sample; agreement with the database (Fleiss κ, 3 raters plus database) was substantial at the exact-code level (κ=0.67, 95% CI 0.55-0.78) and almost perfect at the USMLE domain level (κ=0.94, 95% CI 0.88-1.00). CONCLUSIONS: An AI-integrated relational curriculum database with a faculty-facing search interface can convert curriculum governance from a periodic, retrospective activity into a continuous, self-service one, producing alignment and gap analyses within minutes rather than weeks. Workload effects have not been formally measured. Extension to assessment items and prospective correlation with licensing examination outcomes are planned.

JMIR Medical EducationVol. 12
Texas A&M University (US)
Quality education
Innovations in Medical Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon