Generative AI-Assisted Teaching and Clinical Reasoning Among TCM Interns

NCT07891325 | Completed

• 2 other identifiers: TCHIRB-11210001TPCH-114-25
• Study Type: interventional
• Target: 38
• Locations: 1 country
• Sites: 1

Brief Summary

This study evaluated the effects of generative artificial intelligence (GAI)-assisted education on clinical reasoning performance among traditional Chinese medicine (TCM) interns. An assessor-blinded, nonrandomized, cluster-controlled educational intervention study was conducted at three hospital branches in Taiwan. Participants were assigned to either a GAI-assisted education group or a conventional education group according to their clinical training sites. The intervention group received a three-hour introductory training session on ChatGPT and was encouraged to use the tool independently for clinical case analysis during subsequent clinical rotations. The control group received conventional clinical education without structured GAI-assisted training. The primary outcome was clinical reasoning performance, assessed through clinical case reports independently evaluated by two blinded TCM educators. Secondary outcomes included perceptions of the four-element TCM diagnostic framework and perceptions of GAI-assisted learning.

Conditions

Clinical; Education

Keywords

Generative Artificial Intelligence; ChatGPT; Traditional Chinese Medicine; Clinical Reasoning; Medical Education

Outcome Measures

Primary Outcomes (1)

• Change in Clinical Reasoning Performance Score

  Clinical reasoning performance was assessed using written clinical case reports independently evaluated by two blinded traditional Chinese medicine educators. Ten domains were scored from 1 to 10, including disease location, etiology, disease nature, pathogenesis, differential diagnosis, prescription selection, pathophysiological reasoning, overall clinical decision-making, information analysis, and clinical applicability of prescriptions. Total scores ranged from 10 to 100, with higher scores indicating better clinical reasoning performance. The mean score from the two evaluators was used for analysis. Changes in scores from baseline (Month 0) to post-intervention (Month 3) were compared between groups.

  Baseline (Month 0) and post-intervention (Month 3)

Secondary Outcomes (2)

• Change in Perceptions of the Four Elements of TCM Etiology and Pathogenesis

  Baseline (Month 0) and post-intervention (Month 3)

• Change in Perceptions of and Satisfaction With GAI-Assisted Learning

  Baseline (Month 0) and post-intervention (Month 3)

Study Arms (2)

GAI-Assisted Education

EXPERIMENTAL

Participants received a three-hour introductory training session on the use of ChatGPT for traditional Chinese medicine clinical case analysis. Following the training, participants were allowed to use ChatGPT independently during clinical rotations without a prescribed minimum frequency or duration of use.

Behavioral: GAI-Assisted Clinical Education

Conventional Clinical Education

ACTIVE COMPARATOR

Participants received conventional traditional Chinese medicine clinical education, including clinical observation, case discussions, and instruction from supervising physicians, without structured generative AI-assisted training.

Behavioral: Conventional Clinical Education

Interventions

GAI-Assisted Clinical Education BEHAVIORAL

A structured three-hour introductory training session was provided on the use of ChatGPT for traditional Chinese medicine clinical reasoning and case analysis. Training included demonstrations of disease location, etiology, disease nature, pathogenesis, differential diagnosis, and prescription decision-making. Participants subsequently used ChatGPT independently during clinical rotations as needed. No minimum frequency or duration of ChatGPT use was required.

GAI-Assisted Education

Conventional Clinical Education BEHAVIORAL

Participants continued routine traditional Chinese medicine clinical training, including supervised clinical observation, case-based discussions, and instruction from supervising physicians. No structured training in or assigned use of generative artificial intelligence tools was provided.

Conventional Clinical Education

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Aged 18 years or older.
• Enrolled in an undergraduate or postbaccalaureate traditional Chinese medicine (TCM) program.
• Completed the required TCM coursework and the first stage of the national TCM licensing examination.
• Provided informed consent to participate in the study.

You may not qualify if:

• Already licensed as a traditional Chinese medicine physician.
• Unable to complete the required study procedures.
• Declined to provide informed consent.

Sponsors & Collaborators

• Taipei City Hospital: lead

Study Sites (1)

Taipei City Hospital

Taipei, Taipei, 110, Taiwan

Location

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NON RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Masking Details: Two independent traditional Chinese medicine educators evaluated clinical case reports without knowledge of participants' group assignments. Participants and instructors were not blinded because of the nature of the educational intervention.
• Purpose: OTHER
• Intervention Model: PARALLEL
• Sponsor Type: OTHER GOV
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Attending Physician

Model Details: Participants were assigned to the intervention or control group according to their clinical training sites. One hospital branch received generative AI-assisted education, while two hospital branches continued conventional clinical education. Individual randomization was not performed.

Study Record Dates

• First Submitted: October 15, 2026
• First Posted: October 23, 2026
• Study Start: February 20, 2024
• Primary Completion: December 2, 2024
• Study Completion: May 30, 2025
• Last Updated: October 23, 2026

Record last verified: 2026-10

Data Sharing

• IPD Sharing: Will not share

Locations

TW (1)