Effect of ChatGPT versus Conventional Search Tools on Medical Students Clinical Reasoning Performance: A Prospective Crossover Study

A Prospective Randomized Crossover Study Comparing the Impact of ChatGPT and Conventional Online Search Tools on Clinical Reasoning and Knowledge Retrieval Among Second-Year Medical Students

Status

Active, not recruiting

Phases

Early Phase 1

Study type

Interventional

Source

TCTR

Registry ID

TCTR20260218005

Enrollment

Registered

2026-02-18

Start date

2026-01-19

Completion date

Unknown

Last updated

2026-08-03

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Clinical reasoning performance Medical education AI-assisted learning Artificial Intelligence ChatGPT Clinical Reasoning Medical Students Education, Medical Educational Technology Information Retrieval Decision Making

Interventions

Participants will use ChatGPT during structured case-based learning tasks to retrieve information and support clinical reasoning. Students will complete predefined clinical scenarios and submit answer

Experimental Behavioral,Active Comparator Behavioral

ChatGPT-assisted information retrieval and clinical reasoning,Conventional online search tools assisted information retrieval and clinical reasoning

Eligibility

Sex/Gender

All

Age

18 Years to 30 Years

Inclusion criteria

Inclusion criteria: 1.Second-year medical students enrolled at the Faculty of Medicine, Kasetsart University 2. Attendance in scheduled study sessions during the study period 3. Ability to use online search tools and AI platforms 4. Provide written informed consent

Exclusion criteria

Exclusion criteria: 1. Students who decline to provide informed consent 2. Students absent during either study phase 3. Incomplete participation in assigned intervention sessions

Design outcomes

Primary

Measure	Time frame
ClinicalReasoningScore Immediately after completion of each intervention phase (end of Phase 1 and end of Phase 2) A standardized scoring rubric, assessed after each phase.,SelfPerceivedUnderstanding After last intervention phase Likert-scale questionnaire on perceived understanding of the case content	—

Secondary

Measure	Time frame
KnowledgeTestScore Immediately after each intervention phase Score from a structured multiple-choice knowledge test based on the study cases	—

Countries

Thailand

Contacts

Public ContactPinkawas Kongmalai

Faculty of Medicine, Kasetsart University

pinkawass@hotmail.com0815703867

Outcome results

None listed

Source: TCTR (via WHO ICTRP) · Data processed: Aug 10, 2026