A study to validate educational interventions and assessment tools for behavioral economics dialogue skills using AI-simulated patients in diabetes care.

Educational intervention for behavioral economic communication skills using AI-simulated patients in diabetes care and validation of an assessment tool: A three-group comparative study among junior, specialty-trained, and expert physicians - 3-Group Comparison of AI-Simulated Patient Education for Diabetes

Status

Active, not recruiting

Phases

Unknown

Study type

Interventional

Source

JPRN

Registry ID

JPRN-UMIN000061418

Enrollment

Registered

2026-06-20

Start date

2026-07-01

Completion date

Unknown

Last updated

2026-09-14

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

Conditions

Type 2 Diabetes Mellitus

Interventions

A single session of behavioral economic communication training using AI-simulated patients (interaction with 3 cases and reviewing feedback, approx. 40-50 min) for three cohorts: (1) junior physicians

Eligibility

Sex/Gender

All

Inclusion criteria

Inclusion criteria: Physicians who provided written informed consent. Physicians meeting any of the following: Junior physicians (3-7 years post-grad), Specialty-trained physicians in Endocrinology and Diabetes (without Diabetology Board certification), or Board-certified Diabetologists.

Exclusion criteria

Exclusion criteria: Those who have difficulty preparing an internet environment or device. Those judged inappropriate by the principal investigator.

Design outcomes

Primary

Measure	Time frame
Change in AI-generated total score for behavioral economic communication skills from Pre-test to Post-test (approximately 40-50 minutes after the start of the study).	—

Secondary

Measure	Time frame
Change in self-efficacy (confidence levels, Q1-Q4) from Pre-test to Post-test. Change in the number of dialogue turns (rounds of conversation) required to reach a consensus with the AI patient. Mean scores of the System Usability Scale (SUS) in the post-intervention questionnaire. Comparison of baseline AI-generated scores among the three groups (junior, specialty-trained, and expert physicians) to verify construct validity.	—

Measure

Time frame

Change in self-efficacy (confidence levels, Q1-Q4) from Pre-test to Post-test. Change in the number of dialogue turns (rounds of conversation) required to reach a consensus with the AI patient. Mean scores of the System Usability Scale (SUS) in the post-intervention questionnaire. Comparison of baseline AI-generated scores among the three groups (junior, specialty-trained, and expert physicians) to verify construct validity.

—

Countries

Japan

Contacts

Public ContactIchiro Nojima

Okayama University Hospital Dept. of Nephrology, Rheumatology, Endocrinology and Metabolism

kohaku8551@yahoo.co.jp086-235-7235

Outcome results

None listed

Source: JPRN (via WHO ICTRP) · Data processed: Sep 19, 2026