An interventional study of GAI-Assisted Clinical Education and Conventional Clinical Education in Clinical and Education, sponsored by Taipei City Hospital. Completed at 1 site in Taiwan. Open to participants aged 18 Years and older, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-10-23.
Sponsored by Taipei City Hospital · Not applicable, Interventional, and Other
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.
This study investigated whether incorporating generative artificial intelligence (GAI) into traditional Chinese medicine (TCM) clinical education could improve clinical reasoning performance among TCM interns.
The study employed an assessor-blinded, nonrandomized, cluster-controlled design across three hospital branches in Taiwan. Participants were allocated to the intervention or control group according to their clinical training sites rather than through individual randomization.
Participants in the intervention group attended a three-hour introductory session covering the use of ChatGPT for TCM clinical case analysis, including disease location, etiology, disease nature, pathogenesis, differential diagnosis, and prescription decision-making. Following this session, participants could independently use ChatGPT during clinical rotations without a prescribed minimum frequency or duration.
Participants in the control group continued conventional clinical education, including clinical observation, case discussions, and instruction from supervising physicians, without structured GAI-assisted training.
Clinical reasoning performance was assessed before and after the educational intervention using written clinical case reports. Two independent TCM educators, blinded to group allocation, evaluated the reports across ten domains using a 10-point scoring scale for each domain. Total scores ranged from 10 to 100, with higher scores indicating better clinical reasoning performance.
Secondary outcomes included participants' perceptions of the four-element TCM diagnostic framework, assessed using an 11-item questionnaire with a seven-point Likert scale. Participants in the intervention group also completed a 12-item questionnaire using a five-point Likert scale to assess their perceptions of and satisfaction with GAI-assisted learning.
The study was approved by the Institutional Review Board of Taipei City Hospital (TCHIRB-11210001), and informed consent was obtained from participating interns.
Taipei City Hospital is the lead sponsor of 57 studies on the registry; 9 are open to participants now.
Counted across the registry records on this site, refreshed daily.
Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.
Exclusion Criteria:
Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Informed consent
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
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
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
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.
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.
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.
Time frame: Baseline (Month 0) and post-intervention (Month 3)
Change in Perceptions of the Four Elements of TCM Etiology and Pathogenesis
Participants' perceptions of the four-element traditional Chinese medicine diagnostic framework were assessed using an investigator-developed 11-item questionnaire with a seven-point Likert scale. The questionnaire was administered before and after the educational intervention in both groups. Responses were collected anonymously and could not be matched at the individual level across time points. Group-level changes in questionnaire responses were evaluated.
Time frame: Baseline (Month 0) and post-intervention (Month 3)
Change in Perceptions of and Satisfaction With GAI-Assisted Learning
Perceptions of and satisfaction with generative AI-assisted learning were evaluated among participants in the intervention group using an investigator-developed 12-item questionnaire with a five-point Likert scale. The questionnaire was administered at baseline (Month 0) and post-intervention (Month 3). Responses were collected anonymously and could not be linked at the individual level across assessment points. Changes in questionnaire responses were therefore evaluated at the group level.
Time frame: Baseline (Month 0) and post-intervention (Month 3)
Plan to share: No — Individual participant data will not be publicly shared because the study involves educational assessment records and questionnaire responses from a relatively small cohort of medical interns. Data confidentiality and participant privacy will be maintained in accordance with the approved institutional review board protocol.
No publications or documents are linked to this record.
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
This study is completed, as verified in Oct 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
Taipei City Hospital