Study on the Medical Education Capability of the EyeTeacher Artificial Intelligence Platform

NCT06759012 | Not Yet Recruiting

• 1 other identifier: THU01-20240100
• Study Type: interventional
• Target: 252
• Locations: 7 countries
• Sites: 7

Brief Summary

With the rise of generative artificial intelligence and large language models, medical education is undergoing a significant transformation. Numerous studies have highlighted the limitations of traditional educational knowledge acquisition and the potential impact of artificial intelligence on medical education, resident training, and continuing education for clinical practitioners. However, there is a lack of real-world experiments on the effectiveness of AI-integrated education. Artificial intelligence can provide extensive educational resources and tools that are not limited by geographical location or language, thereby lowering the barrier to accessing high-quality medical education and promoting educational equity. Nevertheless, the performance of AI models trained by different medical institutions or healthcare systems may vary. To offer a more universal, accessible, high-quality, and interconnected educational journey. We have developed a virtual ophthalmology teacher, which developed based on foundational model and large language models. This model, named EyeTeacher provide comprehensive theoretical knowledge and clinical skills enhancement for untrained medical students. To verify the effectiveness of our EyeTeacher across different national ophthalmology education systems and languages, we plan to implement a randomized controlled trial. This trial will assess the clinical capabilities of all participants and explore the advantages and disadvantages of the system compared to traditional teaching methods.

Conditions

Medical Education

Keywords

Medical education; Multimodality AI; Generative AI

Outcome Measures

Primary Outcomes (1)

• Grade of ophthalmology examination

  Title: Ophthalmology Theoretical Examination. The examination includes 40 multiple-choice questions and two essay questions related to ophthalmology knowledge, to be completed within one hour without the use of reference materials. The exam will be graded by experts based on a standardized answer key. The score ranges from 0 to 100, with a higher score indicating a deeper understanding of the ophthalmology knowledge. Students in both the interventional group and the control group will complete the exam within the specified time on the EyeTeacher system. The data will be collected in the system's backend.

  1 day after complete lectures

Secondary Outcomes (2)

• Time of studying ophthalmology

  1 day after complete lectures

• Feedback of teaching from students

  1 day after complete lectures

Study Arms (2)

Interventional group

EXPERIMENTAL

Attend EyeTeacher lecture before taking the regular ophthalmology lecture in medical school.

Other: EyeTeacher

Control group

NO INTERVENTION

Attend regular ophthalmology lectures in medical school.

Interventions

EyeTeacher OTHER

Participants randomized to the intervention group will receive access to the EyeTeacher system, along with their username, password, and a user manual, one week before the start of the course. They will follow instructions on the website and complete a quiz before and after each course. After completing the EyeTeacher curriculum, they will take the first examination (Examination 1) and complete a set of questionnaires. A classroom will be provided for study purposes, but no restrictions will be imposed on the study location. Following the EyeTeacher section, participants will attend the ophthalmology course in the regular training program, with support from the EyeTeacher system. They will be evaluated according to the ophthalmology posting's evaluation criteria (Examination 2).

Interventional group

Eligibility Criteria

• Age: 21 Years - 40 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64)

You may qualify if:

• Clinical medical students who have not taken ophthalmology courses
• Age 21-40
• Gender not restricted
• Sign the informed consent form

You may not qualify if:

• Refusal of the research protocol.
• Participants unwilling or unable to understand and complete the questionnaire.

Sponsors & Collaborators

• Tsinghua University: lead

Study Sites (7)

University of Melbourne

Melbourne, Victoria, 3010, Australia

Location

Peking Union Medical College Hospital

Beijing, Beijing Municipality, 430022, China

Location

University of Ghana

Accra, Greater Accra Region, P.O. Box LG 586, Ghana

Location

Sankara Nethralaya

Chennai, Tamil Nadu, 600 006, India

Location

University of Malaya

Kuala Lumpur, 50603, Malaysia

Location

Duke-NUS medical school

Singapore, 169857, Singapore

Location

Moorfields Eye Hospital

London, EC1V 2PD, United Kingdom

Location

Related Publications (2)

• He B, Kwan AC, Cho JH, Yuan N, Pollick C, Shiota T, Ebinger J, Bello NA, Wei J, Josan K, Duffy G, Jujjavarapu M, Siegel R, Cheng S, Zou JY, Ouyang D. Blinded, randomized trial of sonographer versus AI cardiac function assessment. Nature. 2023 Apr;616(7957):520-524. doi: 10.1038/s41586-023-05947-3. Epub 2023 Apr 5.

  PMID: 37020027 BACKGROUND

• Benitez TM, Xu Y, Boudreau JD, Kow AWC, Bello F, Van Phuoc L, Wang X, Sun X, Leung GK, Lan Y, Wang Y, Cheng D, Tham YC, Wong TY, Chung KC. Harnessing the potential of large language models in medical education: promise and pitfalls. J Am Med Inform Assoc. 2024 Feb 16;31(3):776-783. doi: 10.1093/jamia/ocad252.

  PMID: 38269644 BACKGROUND

Central Study Contacts

Yueyuan Xu

CONTACT

+86 186 1065 2799; xuyy17@mails.tsinghua.edu.cn

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Purpose: OTHER
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: December 5, 2024
• First Posted: January 6, 2025
• Study Start: January 5, 2025
• Primary Completion: December 30, 2025
• Study Completion: December 30, 2025
• Last Updated: January 6, 2025

Record last verified: 2024-12

Data Sharing

• IPD Sharing: Will not share

Locations

SG (1); GB (1); AU (1); MY (1); GH (1); IN (1); CN (1)