Virtual Health Coaching With Artificial Intelligence for Glycemic Control in Type 2 Diabetes

NCT07165730 | Not Yet Recruiting

• 2 other identifiers: UNHAS-VHC-AI-202502209/UN4.22/PT.01.03/2025
• Study Type: interventional
• Target: 206
• Locations: 1 country
• Sites: 1

Brief Summary

This study aims to evaluate the effectiveness of a virtual health coaching program based on artificial intelligence (AI) in improving blood sugar control among people with type 2 diabetes in primary health care settings in Jeneponto and Bantaeng, Indonesia. The intervention will be delivered through the DIACOACH application, which provides personalized coaching, lifestyle guidance, and self-care support. Participants will be randomly assigned to either the intervention group, receiving virtual health coaching for 12 weeks, or the control group, receiving standard diabetes education. Main outcomes include fasting blood sugar and HbA1c levels. Other outcomes include self-care adherence, dietary behavior, and quality of life. This trial seeks to provide evidence on whether AI-based virtual coaching is a practical and effective digital health solution to support diabetes self-management in community health settings with limited resources.

Conditions

Type 2 Diabetes Mellitus (T2DM)

Keywords

Virtual Health Coaching; Artificial Intelligence (AI); Glycemic Control

Outcome Measures

Primary Outcomes (2)

• Fasting Blood Glucose (FBG)

  Change in fasting blood glucose (mg/dL) from baseline to post-intervention, measured using standardized laboratory methods

  Baseline and 12 weeks after intervention

• Glycated Hemoglobin (HbA1c)

  Change in HbA1c (%) from baseline to post-intervention, measured using standardized laboratory methods.

  Baseline and 12 weeks after intervention.

Secondary Outcomes (3)

• Self-care Adherence

  Baseline and 12 weeks after intervention.

• Dietary Behavior

  Baseline and 12 weeks after intervention.

• Physical Activity

  Baseline and 12 weeks after intervention.

Study Arms (2)

Virtual Health Coaching (DIACOACH)

EXPERIMENTAL

Participants in this group will receive a 12-week virtual health coaching program through the DIACOACH application. The app provides adaptive education, reminders, self-care monitoring, and AI-based personalized feedback to support glycemic control.

Behavioral: Virtual Health Coaching with Artificial Intelligence (DIACOACH)

Standard Diabetes Education

ACTIVE COMPARATOR

Participants in this group will receive standard diabetes education provided by primary health care centers, including routine counseling sessions and printed health information.

Behavioral: Standard Diabetes Education

Interventions

Virtual Health Coaching with Artificial Intelligence (DIACOACH) BEHAVIORAL

Participants in the intervention group will receive a 12-week virtual health coaching program using the DIACOACH application. The program includes adaptive digital education on diet, physical activity, and medication adherence, personalized reminders, daily self-monitoring, and feedback powered by artificial intelligence. The intervention is designed to improve self-care adherence and glycemic control (FBG, HbA1c, RBG) among adults with type 2 diabetes mellitus in primary care settings.

Virtual Health Coaching (DIACOACH)

Standard Diabetes Education BEHAVIORAL

Participants in the control group will receive standard diabetes education usually provided in primary health care centers. This includes routine counseling sessions, printed educational materials, and general advice on diet, physical activity, and medication adherence, without the use of the DIACOACH application.

Standard Diabetes Education

Eligibility Criteria

• Age: 18 Years - 65 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Diagnosed with Type 2 Diabetes Mellitus for more than 3 months
• Age between 30 and 56 years
• Able to read and understand instructions
• Have access to a digital device (smartphone or similar)
• In stable clinical condition

You may not qualify if:

• Diagnosed with Type 1 Diabetes Mellitus
• Patients with severe complications (e.g., advanced nephropathy, retinopathy, cardiovascular disease)
• Patients currently undergoing other structured interventions
• Patients on long-term steroid therapy
• Patients without access to a digital device

Sponsors & Collaborators

• Hasanuddin University: lead

Study Sites (1)

Public Health Center of Bontomatene and Public Health Center of Binamu Kota

Makassar, South Sulawesi, 90245, Indonesia

Location

MeSH Terms

Conditions

Diabetes Mellitus, Type 2

Interventions

Artificial Intelligence

Condition Hierarchy (Ancestors)

Diabetes Mellitus; Glucose Metabolism Disorders; Metabolic Diseases; Nutritional and Metabolic Diseases; Endocrine System Diseases

Intervention Hierarchy (Ancestors)

Algorithms; Mathematical Concepts

Central Study Contacts

Nuurhidayat Jafar, Dr

CONTACT

+6281355576066; nuurhidayat@unhas.ac.id

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NON RANDOMIZED
• Masking: NONE
• Purpose: TREATMENT
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Doctor

Model Details: This study uses a quasi-experimental design with a non-equivalent control group model. Participants will be assigned in parallel to either the intervention arm, receiving virtual health coaching through the DIACOACH application for 12 weeks, or the control arm, receiving standard diabetes education in primary health care settings. The study aims to evaluate changes in glycemic control and self-management behaviors between groups

Study Record Dates

• First Submitted: September 3, 2025
• First Posted: September 10, 2025
• Study Start: September 15, 2025
• Primary Completion: December 31, 2025
• Study Completion (Estimated): June 15, 2026
• Last Updated: September 10, 2025

Record last verified: 2025-09

Locations

ID (1)