AI-Assisted Academic Writing, Medical Education, Narrative Review Writing
Conditions
Keywords
Artificial Intelligence, Medical Education, Postgraduate Education, Narrative Literature Review, Academic Writing, SANRA
Brief summary
This randomized, parallel-group, assessor-blinded educational study will evaluate whether one session of AI-assisted structured guidance improves the quality of narrative literature reviews written by medical postgraduate students. A total of 102 students enrolled in an academic writing course will be randomly assigned to either an AI-assisted structured guidance group or a free AI use group. Both groups may use AI tools under academic integrity requirements and will complete a narrative literature review according to the same course requirements. The guidance group will receive one structured guidance session approximately two weeks before final submission. The session will be based on the six dimensions of the Scale for the Assessment of Narrative Review Articles (SANRA). The primary outcome is the final SANRA total score of the submitted narrative literature review.
Detailed description
Generative artificial intelligence is increasingly used by medical students and postgraduate trainees for literature searching, summarization, outlining, and academic writing. However, free use of AI may be associated with inaccurate information, unsupported statements, fabricated references, and inadequate academic judgment. This study is designed to evaluate whether structured guidance can improve the quality and academic integrity of AI-assisted narrative review writing. Participants will be medical postgraduate students enrolled in an academic writing course. After informed consent and baseline data collection, participants will be randomized in a 1:1 ratio to an AI-assisted structured guidance group or a free AI use group. Both groups will complete a narrative literature review of approximately 2,000 Chinese characters according to the same course requirements and may use AI tools under academic integrity requirements. Participants in the AI-assisted structured guidance group will receive one structured guidance session approximately two weeks before final submission. The session will be based on the six SANRA dimensions: explanation of the importance of the article, statement of aims or questions, description of the literature search, reference support for key statements, scientific reasoning, and appropriate presentation of data and content. The instructor will provide directional and methodological feedback but will not directly write or edit the students' text line by line. Participants in the free AI use group will complete the review according to the same course requirements without the structured guidance session. After submission, all narrative reviews will be anonymized and assessed by independent outcome assessors blinded to group allocation. The primary outcome is the final SANRA total score. Secondary outcomes include SANRA item scores, multiple-source academic writing self-efficacy, and reference authenticity error rate.
Interventions
BEHAVIORALAI-Assisted Structured Guidance
A single structured guidance session delivered approximately two weeks before final submission. The session is based on the six SANRA dimensions and provides directional and methodological feedback on narrative review writing and appropriate AI use, without direct writing or line-by-line editing of students' text.
BEHAVIORALFree AI Use
Participants may use AI tools freely under academic integrity requirements while completing the narrative literature review. Students are responsible for verifying AI-generated content, medical facts, and reference authenticity.
Sponsors
Zhongshan Ophthalmic Center, Sun Yat-sen University
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
OTHER
Masking
SINGLE (Outcomes Assessor)
Masking description
Outcome assessors will be blinded to group allocation. Final narrative literature reviews will be anonymized before assessment, with names, student identifiers, group assignment, guidance records, and AI use declarations removed. Independent assessors will evaluate the anonymized reviews using the SANRA scale.
Intervention model description
Participants will be randomly assigned in a 1:1 ratio to either the AI-assisted structured guidance group or the free AI use group. Both groups will complete a narrative literature review according to the same course requirements. The intervention group will receive one AI-assisted structured guidance session approximately two weeks before final submission, while the control group will not receive the structured guidance session.
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
Yes
Inclusion criteria
1. Master's students enrolled in the Academic Standards and Thesis Writing course. 2. Willing to participate in this study, able to understand the study procedures and randomization arrangement, and able to provide written informed consent. 3. Able to complete literature searching, use AI tools, and complete online questionnaires.
Exclusion criteria
1. Students who have confirmed withdrawal from the course, suspension of study, long-term leave, or other known objective reasons that prevent participation in subsequent major teaching activities and study procedures. 2. Students who have participated in pilot testing, intervention material development, assessment training, or data processing related to this study.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Final SANRA Total Score | Week 2 | The quality of the final narrative literature review will be assessed using the Scale for the Assessment of Narrative Review Articles (SANRA). The SANRA total score ranges from 0 to 12, with higher scores indicating better quality of the narrative review.The outcome will be assessed based on the narrative literature review submitted at Week 2. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| SANRA Item 1 Score: Importance of the Article | Week 2 | This outcome assesses SANRA item 1, which evaluates whether the importance of the narrative review article is adequately explained. The item score ranges from 0 to 2, with higher scores indicating better reporting.The outcome will be assessed based on the narrative literature review submitted at Week 2. |
| SANRA Item 2 Score: Aims or Questions | Week 2 | This outcome assesses SANRA item 3, which evaluates whether the literature search process is described. The item score ranges from 0 to 2, with higher scores indicating better reporting.The outcome will be assessed based on the narrative literature review submitted at Week 2. |
| SANRA Item 3 Score: Literature Search Description | Week 2 | This outcome assesses SANRA item 3, which evaluates whether the literature search process is described. The item score ranges from 0 to 2, with higher scores indicating better reporting.The outcome will be assessed based on the narrative literature review submitted at Week 2. |
| SANRA Item 4 Score: Referencing | Week 2 | At final submission of the narrative literature review; assessment completed within 4 weeks after final submission.The outcome will be assessed based on the narrative literature review submitted at Week 2. |
| SANRA Item 5 Score: Scientific Reasoning | Week 2 | This outcome assesses SANRA item 5, which evaluates whether the scientific reasoning is based on appropriate evidence. The item score ranges from 0 to 2, with higher scores indicating better scientific reasoning.The outcome will be assessed based on the narrative literature review submitted at Week 2. |
| SANRA Item 6 Score: Data and Content Presentation | Week 2 | This outcome assesses SANRA item 6, which evaluates whether data and content are presented appropriately. The item score ranges from 0 to 2, with higher scores indicating better presentation.The outcome will be assessed based on the narrative literature review submitted at Week 2. |
| Change From Baseline in Multiple-Source Academic Writing Self-Efficacy Score | Baseline and Week 2 | Multiple-source academic writing self-efficacy will be assessed using an adapted 8-item Multiple-Source Academic Writing Self-Efficacy Scale. The change from baseline to final submission will be analyzed. Higher scores indicate greater self-efficacy in integrating multiple sources for academic writing. |
| Reference Authenticity Error Rate | Week 2 | The proportion of references with authenticity errors will be calculated for each submitted narrative literature review. References will be verified using available bibliographic information such as DOI, PMID, title, authors, PubMed, CrossRef, Web of Science, Google Scholar, journal websites, or publisher websites. A higher error rate indicates poorer reference authenticity.The outcome will be assessed based on the narrative literature review submitted at Week 2. |
Countries
China
Contacts
CONTACTGuangming Jin
Outcome results
None listed