Skip to main content
OpenTrials
Completed

NCT Number: NCT07160972

AI-Based Lifestyle Guidance Study

The X Life model is an innovative AI-based lifestyle guidance system designed to provide tailored health management recommendations for individuals with T2DM or prediabetes, leveraging continuous glucose monitoring (CGM) data, wearable activity and sleep metrics, and baseline clinical information. Despite its potential, a lack of in-depth understanding of real-world user experiences remains a key barrier to clinical adoption.

This exploratory user study aims to systematically assess the usability, acceptability, and user experience of the X Life model in the target population, to identify facilitators and barriers to adoption, and to preliminarily explore the association between X Life use and changes in user-reported outcomes, behavior patterns, and device-monitored health metrics.

Completed

Looking for future studies?

Notify Me

Key information

Conditions

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

Age range

18 year–70 year

Sex eligibility

All sexes

Study type

Interventional

Phase

Not applicable

Primary location

Shanghai Sixth People's Hospital

Shanghai, China

Who can participate

Healthy volunteers accepted: Yes

Only the study team can determine whether someone qualifies for participation.

Inclusion criteria

  • Age 18-70 years.
  • Prediabetes or Type 2 diabetes mellitus (diagnosed according to recognized clinical criteria).
  • Owns and is proficient in using a smartphone with compatible applications.
  • Willing and able to wear study devices (CGM, activity tracker).
  • Willing to use the X Life model terminal and comply with study procedures.
  • Able to understand and provide written informed consent (including participation in interviews).

Exclusion criteria

  • Severe chronic diabetic complications or recent acute diabetic complications.
  • Early-onset adult T2DM.
  • Recent severe hypoglycemic events.
  • Cognitive impairment.
  • Pregnancy, severe hepatic/renal/thyroid disease, acute infection, psychiatric disorders affecting participation.
  • Planned major surgery or treatment likely to significantly impact glucose or weight during the study period.
  • Allergy to device materials (CGM sensor, activity tracker, AI terminal).
  • Any condition deemed unsuitable by the investigator.

Treatment and study plan

Lifestyle management

Other

Participants will use the X Life system via AR glasses or mobile terminal (smartphone/tablet) for 7 days. The system provides personalized dietary and exercise recommendations at dynamic trigger points (before/after meals, before/after exercise, before bedtime) using baseline clinical data, real-time CGM readings, dietary images, activity data, and wearable monitoring (activity, sleep, heart rate). Standard care guidance will also be provided in accordance with national dietary and physical activity guidelines.

Primary outcomes

  1. User Experience Score

    Time frame: 7 days after intervention initiation

    User experience will be assessed using a validated questionnaire covering usability, usefulness, satisfaction, and acceptability. Each item is rated on a 5-point Likert scale. Higher scores indicate better user experience.

Secondary outcomes

  1. Change in self-reported diabetes self-management behaviors

    Time frame: Baseline and 7 days after intervention initiation

    Diabetes self-care activities will be assessed using the SDSCA scale. Each item is rated on a scale of 0-7 days. Higher scores indicate better self-management behavior.

  2. Change in diabetes-related distress

    Time frame: Baseline and 7 days after intervention initiation

    Diabetes distress will be assessed using the DDS. Each item is rated on a 6-point Likert scale. Higher scores indicate greater distress.

  3. Change in self-efficacy

    Time frame: Baseline and 7 days after intervention initiation

    Self-efficacy will be assessed using the validated Self-Efficacy Scale. Each item is rated on a 10-point Likert scale. Higher scores indicate greater self-efficacy.

  4. Composite Wearable Device Metrics

    Time frame: Baseline and 7 days after intervention initiation

    Physiological and behavioral data will be captured by wearable devices. Each metric will be reported and analyzed separately: Daily activity level: Steps/day; Sleep duration: Hours/night; Sleep architecture: % of light/deep/REM sleep; Resting heart rate: Beats per minute, etc.

  5. Correlation between AI-predicted and actual CGM glucose values

    Time frame: From baseline to 7 days after intervention initiation

    intraclass correlation, mean absolute relative difference, RMSE, Bland-Altman analysis, etc.

  6. Change in psychological well-being

    Time frame: Baseline and 7 days after intervention initiation

    Psychological well-being will be assessed using the WHO-5 Well-Being Index, a validated 5-item questionnaire. Each item is rated on a 6-point Likert scale (0 = at no time, 5 = all of the time). Raw scores range from 0 to 25, which are multiplied by 4 to yield a final score ranging from 0 to 100. Higher scores indicate better well-being.

  7. Composite Continuous Glucose Monitoring (CGM) Metrics

    Time frame: Baseline, 7 days after intervention initiation

    Glycemic control and variability will be evaluated using multiple CGM-derived measures. Each metric will be reported and analyzed separately: Time in Range (TIR): % of glucose values within 3.9-7.8 (for individuals without diabetes) or 10.0 (for individuals with diabetes) mmol/L; Mean glucose: mmol/L; Coefficient of variation (CV): %; Time above range (TAR): % of glucose values >10.0 mmol/L; Time below range (TBR): % of glucose values <3.9 mmol/L, etc.

  8. Expert Panel Evaluation of AI-Generated Dietary Recommendations

    Time frame: 7 days after intervention initiation

    Independent nutrition experts will score the AI-generated dietary recommendations using two validated diet-quality indices. Each index will be reported and analyzed separately: AHEI-2010: Overall score 0-110, higher = better diet quality. Standard 11 components (each 0-10), summed to total; DQI-I: Overall score 0-100, higher = better diet quality. Standard four domains (variety, adequacy, moderation, overall balance), etc.

  9. Expert Panel Evaluation of AI-Generated Exercise Recommendations

    Time frame: 7 days after intervention initiation

    Exercise recommendations generated by the system will be evaluated by an expert panel using a validated structured rating scale. The scale includes five dimensions (Timing, Glycemic Safety, Individualization, FITT principle and Feasibility & Clarity), each scored independently, with a total score calculated as the weighted sum of all domains. Each domain scored 0-2 (0 = not met, 1 = partially met, 2 = fully met). Weighted composite score range: 0-10. Higher scores indicate better quality of exercise recommendations.

Sponsors and collaborators

Lead sponsor

Li Huating

Other

Registry information

Important dates

Study start
2025
Primary completion
2025
Study completion
2025
First posted
Sep 8, 2025
Registry last updated
Dec 2, 2025

OpenTrials presents study information sourced from ClinicalTrials.gov. The official registry record should be consulted for the latest information.

View the official ClinicalTrials.gov record (opens in a new tab)

This listing is for discovery and informational purposes only. It is not medical advice, does not guarantee that a study is recruiting, and does not determine eligibility. Contact the study team and a qualified healthcare professional when considering participation.

Related clinical trials

Published trials that share one or more normalized conditions with this study.