AI-Assisted Learning in Medicine

NCT06945159 | Completed

• 1 other identifier: AI and medical education
• Study Type: observational
• Target: 1,632
• Locations: 1 country
• Sites: 2

Brief Summary

This multi-center retrospective cohort study investigates the real-world impact of integrating MetaGP-Edu, a proprietary AI tool fine-tuned for medical education, into the undergraduate Internal Medicine curriculum. Utilizing historical academic records from several major medical institutions in China across multiple academic years, the study compares the performance of student cohorts who learned via traditional methods only with subsequent cohorts who had supplementary access to MetaGP-Edu. The primary outcome measure is overall academic performance in the Internal Medicine course, assessed through final course scores. The analysis aims to determine if access to the AI tool as a supplementary resource is associated with differences in learning outcomes, while statistically accounting for baseline student characteristics and other potential confounders between the compared cohorts.

Conditions

Medical Student

Keywords

artificial intelligence; MetaGP-Edu; Large Language Model; Education

Outcome Measures

Primary Outcomes (1)

• academic performance

  The primary outcome measure was student academic performance in the Internal Medicine course, operationalized as the final numeric course score (scaled 0-100) obtained from official university transcripts

  1 year

Study Arms (2)

Pre-MetaGP-Edu Cohorts

This group includes all students who completed the Internal Medicine course at the six participating institutions during the academic years prior to 2022 (2020-2021 and 2021-2022). These students learned exclusively through the traditional curriculum methods described above, without access to the MetaGP tool.

Post-MetaGP-Edu Cohorts

This group includes all students who completed the Internal Medicine course starting from the 2022 academic year onwards (2022-2023 and 2023-2024). These students experienced the same core traditional curriculum components but also had access to MetaGP- as a supplementary learning resource throughout their course duration.

Eligibility Criteria

• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population comprises undergraduate medical students who completed the mandatory Internal Medicine curriculum at several major academic medical centers in China over multiple specified academic years. Inclusion in this retrospective analysis was determined by the availability of complete, official academic records for the relevant course during the defined time periods covering both before and after the implementation of the MetaGP-Edu tool.

You may not qualify if:

• Students with incomplete academic records for the course, those who transferred between institutions mid-course, or individuals identified as having repeated the course were excluded

Sponsors & Collaborators

• Kang Zhang: lead

Study Sites (2)

Peking Union Medical College

Beijing, China

Location

Peking University Health Science Center

Beijing, China

Location

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: April 18, 2025
• First Posted: April 25, 2025
• Study Start: June 1, 2020
• Primary Completion: December 1, 2024
• Study Completion: December 1, 2024
• Last Updated: April 25, 2025

Record last verified: 2025-04

Data Sharing

• IPD Sharing: Will not share

Locations

CN (2)