NCT05687968

Brief Summary

In Taiwan, an estimated 2.3 million individuals have diabetes, with a 44% increase observed among young adults and adolescents. Poor dietary habits and sedentary lifestyles are major risk factors for type 2 diabetes. The widespread use of smartphones has facilitated the development of digital health technologies, including digital food photography and artificial intelligence (AI), which show promise for personalized nutrition care and health promotion. While such technologies have demonstrated short-term success in diabetes management, their long-term effectiveness remains uncertain. This study aims to evaluate the effectiveness of a digital eHealth care intervention for individuals with diabetes. Participants will be recruited from the Diabetes Shared Care Network and community care centers in Taiwan and followed for 12 months. Eligible participants will be randomly assigned by computer to either a control or an eHealth care group. • eHealth Group: Receives a 10-minute digital nutrition education session using the lab-developed "3D/AR MetaFood food portion education platform" (https://sketchfab.com/susanlab108/collections) and is required to submit weekly dietary records through food images using the "Formosa FoodAPP." Participants will receive immediate dietary feedback from nutritionists, followed by AI-generated personalized feedback on the glycemic index (GI) and glycemic load (GL) of their meals. They will also be provided with educational videos on healthy eating, physical activity, and selecting low-GI/GL foods. Anthropometric measurements and baseline questionnaires will be collected at enrollment. Blood biochemistry, including HbA1c, will be measured at baseline, and at 3, 6, 9, and 12 months. Collected food image data will be used to train AI systems for real-time dietary feedback and to explore the relationship between nutrient intake and long-term glycemic control.

Trial Health

57
Monitor

Trial Health Score

Automated assessment based on enrollment pace, timeline, and geographic reach

Trial has exceeded expected completion date
Enrollment
39

participants targeted

Target at P25-P50 for not_applicable type-2-diabetes

Timeline
Completed

Started Oct 2022

Typical duration for not_applicable type-2-diabetes

Geographic Reach
1 country

1 active site

Status
recruiting

Health score is calculated from publicly available data and should be used for screening purposes only.

Trial Relationships

Click on a node to explore related trials.

Study Timeline

Key milestones and dates

Study Start

First participant enrolled

October 19, 2022

Completed
3 months until next milestone

First Submitted

Initial submission to the registry

January 9, 2023

Completed
9 days until next milestone

First Posted

Study publicly available on registry

January 18, 2023

Completed
2.7 years until next milestone

Primary Completion

Last participant's last visit for primary outcome

October 1, 2025

Completed
Same day until next milestone

Study Completion

Last participant's last visit for all outcomes

October 1, 2025

Completed
Last Updated

July 30, 2025

Status Verified

June 1, 2025

Enrollment Period

3 years

First QC Date

January 9, 2023

Last Update Submit

July 24, 2025

Conditions

Type 2 DiabetesAI-supported Real-time Dietary FeedbackM-health

Keywords

Diabetes MellitusAI-supported real-time dietary feedbackM-health

Outcome Measures

Primary Outcomes (2)

  • HbA1c

    the change of HbA1c

    baseline, 3 month, 6 month, 9 month, 12 month

  • Fasting glucose

    the change of Fasting glucose

    baseline, 3 month, 6 month, 9 month, 12 month

Secondary Outcomes (23)

  • Triglyceride (TG)

    baseline, 3 month, 6 month, 9 month, 12 month

  • Total cholesterol (TC)

    baseline, 3 month, 6 month, 9 month, 12 month

  • Low-density lipoprotein-cholesterol (LDL-C)

    baseline, 3 month, 6 month, 9 month, 12 month

  • Triglyceride-glucose (TyG)

    baseline, 3 month, 6 month, 9 month, 12 month

  • Estimated Glomerular filtration rate (eGFR)

    baseline, 3 month, 6 month, 9 month, 12 month

  • +18 more secondary outcomes

Study Arms (1)

eHealth group

EXPERIMENTAL

Participants in the eHealth group will receive a multi-component digital health intervention. This includes: 1. Real-time personalized dietary feedback based on weekly food image submissions via the Formosa FoodAPP, delivered initially by trained nutritionists and later by AI. 2. A 10-minute digital food portion size and nutrition education session using the lab-developed "3D/AR MetaFood" platform. 3. Access to educational videos on healthy eating, glycemic index/load, physical activity, and digital food recording.

Behavioral: Real-Time Personalized Dietary Feedback (via AI and Nutritionist)Behavioral: conventional nutrition education by dietitian

Interventions

Real-Time Personalized Dietary Feedback (via AI and Nutritionist)BEHAVIORAL

* Behavioral: "3D/AR MetaFood" Portion Size and Nutrition Education * Behavioral: Nutrition and Physical Activity Educational Videos

eHealth group
conventional nutrition education by dietitianBEHAVIORAL

The participants receive conventional health and nutrition education from state registered dietitian.

eHealth group

Eligibility Criteria

Age20 Years+
Sexall
Healthy VolunteersNo
Age GroupsAdult (18-64), Older Adult (65+)

You may qualify if:

  • years old or older
  • Pre-diabetes or diabetes
  • Taiwan nationality or fluent in Mandarin or Taiwanese
  • Not pregnant or breastfeeding
  • Capable (or assisted by a caregiver) of using a smartphone to photograph and record meals

You may not qualify if:

  • Eating disorders
  • Undergoing treatment for severe illnesses that could affect normal dietary intake (e.g., cancer)
  • Unable to use a smartphone to take photos and record food intake.

Contact the study team to confirm eligibility.

Sponsors & Collaborators

Study Sites (1)

Jung-Su Chang

Taipei, 110, Taiwan

RECRUITING

Related Publications (2)

  • Ho DKN, Chiu WC, Kao JW, Tseng HT, Yao CY, Su HY, Wei PH, Le NQK, Nguyen HT, Chang JS. Mitigating errors in mobile-based dietary assessments: Effects of a data modification process on the validity of an image-assisted food and nutrition app. Nutrition. 2023 Dec;116:112212. doi: 10.1016/j.nut.2023.112212. Epub 2023 Sep 9.

    PMID: 37776838BACKGROUND

  • Lee YB, Kim G, Jun JE, Park H, Lee WJ, Hwang YC, Kim JH. An Integrated Digital Health Care Platform for Diabetes Management With AI-Based Dietary Management: 48-Week Results From a Randomized Controlled Trial. Diabetes Care. 2023 May 1;46(5):959-966. doi: 10.2337/dc22-1929.

    PMID: 36821833BACKGROUND

MeSH Terms

Conditions

Diabetes Mellitus, Type 2Diabetes Mellitus

Interventions

Nutritionists

Condition Hierarchy (Ancestors)

Glucose Metabolism DisordersMetabolic DiseasesNutritional and Metabolic DiseasesEndocrine System Diseases

Intervention Hierarchy (Ancestors)

Health PersonnelHealth Care Facilities Workforce and Services

Study Officials

  • Jung-Su Chang, PhD.

    College of Nutrition, Taipei Medical University

    PRINCIPAL INVESTIGATOR

Central Study Contacts

Jung-Su Chang, PhD.

CONTACT

886-66382736susanchang@tmu.edu.tw

Study Design

Study Type
interventional
Phase
not applicable
Allocation
NA
Masking
NONE
Purpose
SUPPORTIVE CARE
Intervention Model
SINGLE GROUP
Sponsor Type
OTHER
Responsible Party
SPONSOR

Study Record Dates

First Submitted

January 9, 2023

First Posted

January 18, 2023

Study Start

October 19, 2022

Primary Completion

October 1, 2025

Study Completion

October 1, 2025

Last Updated

July 30, 2025

Record last verified: 2025-06

Data Sharing

IPD Sharing
Will not share

Locations

TW(1)