Artificial Intelligence-Supported Mobile Application for Diabetes Self-Management

The Effect of Web-Based and Artificial Intelligence-Assisted Personalized Applications on Knowledge Levels Compliance with Treatment and Self-Management Among Diabetic Individuals

Patients in the AI-supported mobile application group will be able to log in with a username and password that will be defined specifically for them. Patients will be informed about how the application is used during their first interview. They will enter their personal and disease characteristics (age, gender, height, weight, HbA1C, HDL, LDL) into the application at the entrance. Other sections of the application will include exercise, nutrition, medication tracking, complication tracking and diabetic foot care sections. The person will be asked to enter relevant information in these fields according to their own life and condition (for example; how many times do you use insulin per day, what are your medication times, how do you spend your day in terms of exercise, how many meals do you eat, what is your diet, do you urinate frequently, are you extremely thirsty, are you hungry often, do you have numbness in your hands and feet, etc.). After the patient enters the necessary information, they will also be asked to enter their daily blood sugar measurement values into the system. Thus, the individual's hypo/hyperglycemia risk, risk analysis, nutrition recommendations, medication reminder system, exercise reminder and incentive warnings will be communicated to the individual thanks to the AI-based mobile application. The aim of this application is to reduce the risk of complications and improve the individual's quality of life by providing personalized recommendations for all the needs of the individual, including alarms and reminders, and to support patients to continue their diabetes education and disease management more actively.

Study Overview

• Status: Not yet recruiting
• Conditions: Diabetes Mellitus; Self-management; Artificial Intelligence (AI)
• Intervention / Treatment: Other: WEB based application; Other: artificial intelligence-supported mobile application

Detailed Description

pre-test post-test control group design

• Study Type: Interventional
• Enrollment (Estimated): 156
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Nilhan NŞ Töyer Şahin, PhD Student; Phone Number: +905333752295; Email: nilhantyr@gmail.com
• Study Contact Backup: Name: Seda SP PEHLİVAN, Associate Professor; Email: pehlivans@uludag.edu.tr

Study Locations

• Turkey
  • Başakşehir
    • İstanbul, Başakşehir, Turkey, 34480
      • Istanbul Basaksehir Cam and Sakura City Hospital
      • Contact: Muhittin BALTA General Hospital Deputy Chief Physician, Doctor; Phone Number: +90 212 909 60 00; Email: ist.camsakurash@saglik.gov.tr
      • Contact: Nilhan NS TÖYER ŞAHİN, PhD Student

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Having been diagnosed with diabetes for at least 1 year
• Being between the ages of 18-65
• Being open to verbal communication
• Being able to read and write and speak Turkish
• Having a smart android phone and being able to use mobile applications
• Being willing to participate in the study

Exclusion Criteria:

• Having a perception disorder and psychiatric disorder that prevents the patient from communicating,
• Having a condition that prevents them from using a smart phone (advanced retinopathy and neuropathy, internet problems)
• Being on intensive insulin treatment
• Having a condition that prevents them from continuing the application phase of the study
• Wanting to leave the study

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Supportive Care
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

3

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: WEB based application; The content plan for the web-based mobile application group will be prepared with technical support as specified. Patients will be able to log in to the mobile application with a username and password that will be defined specifically for them. Patients will be informed about how the website is used during the first meeting. They will be able to access all the information they need about diabetes with the web-based mobile application. Statistical data such as the frequency of individuals visiting the site, which sections they use more often and how much time they spend will be calculated.	Other: WEB based application; The content plan for the web-based mobile application group will be prepared with technical support as specified. Patients will be able to log in to the mobile application with a username and password that will be defined specifically for them. Patients will be informed about how the website is used during the first meeting. They will be able to access all the information they need about diabetes with the web-based mobile application. Statistical data such as the frequency of individuals visiting the site, which sections they use more often and how much time they spend will be calculated.
Experimental: artificial intelligence-supported mobile application; It is aimed that an artificial intelligence-based mobile application that includes information, nutrition, exercise programs, complications and medication tracking, personalized suggestions, alarms and reminders, which will enable diabetic individuals to follow their glucose targets, support patients in their diabetes education, awareness and disease management to continue more actively. In addition, it is aimed that patients can easily access information, prevent acute and chronic complications, present physical activity and nutrition suggestions in accordance with the person's lifestyle, follow up on medications with alarms and reminders, prevent the negative results of complications in advance, and improve individuals' diabetes-specific knowledge levels, compliance with treatment, self-management and care with information and guidance about foot care to reduce the risk of diabetic feet, which is particularly risky for diabetic patients.	Other: artificial intelligence-supported mobile application; It is aimed that an artificial intelligence-based mobile application that includes information, nutrition, exercise programs, complications and medication tracking, personalized suggestions, alarms and reminders, which will enable diabetic individuals to follow their glucose targets, support patients in their diabetes education, awareness and disease management to continue more actively. In addition, it is aimed that patients can easily access information, prevent acute and chronic complications, present physical activity and nutrition suggestions in accordance with the person's lifestyle, follow up on medications with alarms and reminders, prevent the negative results of complications in advance, and improve individuals' diabetes-specific knowledge levels, compliance with treatment, self-management and care with information and guidance about foot care to reduce the risk of diabetic feet, which is particularly risky for diabetic patients.
No Intervention: control group; No intervention will be applied to the control group, and they will receive routine clinical and outpatient training.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diabetes Self-Management Scale (DSMS)	Diabetes Self-Management Scale (DSMS): This scale was used to measure the behavioral component of individuals in the IMB model. This scale was developed by Schmitt et al. (2013) to examine the relationship between diabetes self-management and glycemic control in diabetic patients (Schmitt et al., 2013). The validity and reliability study of the Turkish Diabetes Self-Management Scale (DSMS) was conducted by Eroğlu and Sabuncu (2018) (Eroğlu and Sabuncu, 2018). The scale consists of 16 items and 4 sub-dimensions and is a 4-point Likert-type. The scale is answered as 3. It suits me very much, 2. It suits me a lot, 1. It suits me a little, 0. It does not suit me at all. Glucose Management subdimension: Items 1, 4, 6, 10, 12 (Items 4 and 12 are about medication use, items 1, 6, and 10 are about blood sugar monitoring). Diet Control subdimension: Items 2, 5, 9, 13. Physical Activity subdimension: Items 8, 11, 15. Use of Health Services subdimension: Items 3, 7, and 14. Item 16 is not includ	6 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Adult diabetes knowledge scale (ADSL)	Adult diabetes knowledge scale (ADSL): This scale was developed by Erenel Yavuz and Erol (2022) to measure the knowledge levels of adult individuals with diabetes (Erenel Yavuz and Erol, 2022). The scale consists of 5 sub-dimensions and 28 items: General Information About Diabetes (6 items), Blood Sugar Measurements and Values (5 items), Diabetes Risk Factors (4 items), Diabetes Symptoms (8 items), Diabetes Complications (5 items). The scale consists of two sets of items as true and false. Those who answer correctly in the yes/no/I don't know answer type questions are given 1 point, and those who don't know and those who answer incorrectly are given 0 points. The maximum score that can be obtained from the scale is 28, and the minimum score is 0. The Kuder-Richardson-20 reliability coefficient for the entire scale was found to be 0.94. Alpha values in the sub-dimensions are; General Information About Diabetes was found as 0.78, Blood Sugar Measurements and Values as 0.85, Diabet	6 months
Morisky Medication Adherence Scale (MMAS-8)	Morisky Medication Adherence Scale (MMAS-8) The MMAS-8 scale consists of 8 items. Each of the first 7 items has 2 possible responses (yes/no), while the 8th item is answered with a 5-point Likert scale. The possible total medication adherence score ranges between 0 and 8, and the higher the score, the better the adherence level. A total score < 6 is considered low adherence, while a total score of ≥ 6 but < 8 indicates moderate adherence, and a score of 8 indicates high adherence.	6 months

Collaborators and Investigators

• Sponsor: Uludag University

Study record dates

Study Major Dates

• Study Start (Estimated): April 1, 2025
• Primary Completion (Estimated): January 1, 2026
• Study Completion (Estimated): June 1, 2026

Study Registration Dates

• First Submitted: October 18, 2024
• First Submitted That Met QC Criteria: October 18, 2024
• First Posted (Actual): October 21, 2024

Study Record Updates

• Last Update Posted (Actual): March 25, 2025
• Last Update Submitted That Met QC Criteria: March 24, 2025
• Last Verified: March 1, 2025

More Information

Terms related to this study

• Keywords: self-management; artificial intelligence; diabetes mellitus; level of knowledge; compliance with Treatment
• Additional Relevant MeSH Terms: Endocrine System Diseases; Metabolic Diseases; Glucose Metabolism Disorders; Diabetes Mellitus
• Other Study ID Numbers: 2024-12/16

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No