Ignite Creation Date:
2025-12-24 @ 12:11 PM
Ignite Modification Date:
2025-12-30 @ 2:48 AM
Study NCT ID:
NCT07300761
Status:
NOT_YET_RECRUITING
Last Update Posted:
2025-12-24
First Post:
2025-11-25
Is NOT Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
AI-Integrated Mobile Education and Self-Management in Hemodialysis
Sponsor:
Ataturk University
Organization:
Study Overview
Official Title:
A Randomized Controlled Trial to Evaluate the Effect of an Artificial Intelligence-Supported Mobile Education Application on Self-Care Behaviors, Arteriovenous Fistula Care, and Biochemical Parameters in Hemodialysis Patients
Status:
NOT_YET_RECRUITING
Status Verified Date:
2025-12
Last Known Status:
None
Delayed Posting:
No
If Stopped, Why?:
Not Stopped
Has Expanded Access:
False
If Expanded Access, NCT#:
N/A
Has Expanded Access, NCT# Status:
N/A
Acronym:
AI-MOBI-HEMODI
Brief Summary:
This randomized controlled trial aims to evaluate the effectiveness of an Artificial Intelligence-supported mobile education application designed to enhance self-care behaviors, arteriovenous fistula (AVF) care practices, and key biochemical parameters among adult hemodialysis (HD) patients. Chronic Kidney Disease (CKD) and its most common renal replacement therapy, hemodialysis, impose a substantial physical, psychological, and socioeconomic burden on patients. HD patients frequently experience fatigue, pain, cramping, sleep disturbances, thirst and fluid restriction challenges, dietary limitations, AVF-related complications, and emotional distress. These difficulties highlight the importance of strengthening patients' self-care abilities and promoting active involvement in disease management.
Despite the prevalence of mobile health (mHealth) technologies in chronic disease management, existing applications for HD patients remain limited, and none have integrated personalized artificial intelligence-based educational support. The absence of AI-driven patient education represents a significant gap in nursing science and digital health innovation. This project addresses that gap by developing and testing a structured, evidence-based mobile education program supported by artificial intelligence, designed specifically for HD patients.
The study will enroll 76 eligible hemodialysis patients from Bitlis State Hospital and Bitlis Tatvan State Hospital. Participants will be randomly assigned to either the intervention group or the control group using simple randomization. The intervention group will receive access to the AI-supported mobile application for six weeks, which includes modules on kidney function, CKD and treatment options, symptom management, dietary adherence, fluid management, treatment adherence, and AVF care. Each module incorporates written content, videos, visuals, voice-supported reading features, and an integrated "Ask a Question" function allowing patients to communicate directly with the research team. The control group will receive routine clinical care without additional intervention.
The artificial intelligence component will assist with content personalization, monitoring of patient engagement, data storage, automated reminders for non-active users, and supportive feedback based on learning progress and biochemical trends. The development of the mobile application will be guided by expert opinions from nephrology specialists, dialysis nurses, academicians, and dietitians. Readability of educational materials will be assessed using the Ateşman Readability Formula. A pilot study will be conducted prior to the trial to evaluate usability using the Web Analysis and Measurement Inventory (WAMMI).
Data collection will include a Patient Identification Form, the Hemodialysis Arteriovenous Fistula Self-Care Behavior Scale, the Hemodialysis Self-Management Scale, and a Biochemical Parameters Tracking Form. Pre-test data will be collected before the intervention; post-test data will be collected at the end of the six-week intervention period. Biochemical parameters will include BUN, creatinine, albumin, potassium, phosphorus, hemoglobin, uric acid levels, Kt/V, and dry weight, obtained from routine clinical records without additional blood sampling.
The primary outcomes will assess changes in self-care and self-management behaviors based on validated scales. Secondary outcomes will examine changes in biochemical parameters between the intervention and control groups. Data analysis will be performed using SPSS, employing descriptive statistics, normality testing, and appropriate statistical comparison tests, with significance set at p \< 0.05.
Ethical approval will be obtained from the appropriate institutional ethics committee, and written informed consent will be secured from all participants. Data confidentiality will be ensured using encrypted login systems and secure storage processes.
This trial is expected to contribute significantly to the scientific literature by being the first AI-supported mobile education intervention tailored for hemodialysis patients. Anticipated benefits include improved self-care behaviors, increased patient autonomy, reduced AVF complications, better adherence to dietary and fluid restrictions, and improved biochemical outcomes. Broader impacts of the project include the potential reduction of hospitalization rates, decreased healthcare costs, increased quality of life for HD patients, and the establishment of a digital model that can be adapted for other chronic disease populations.
Ultimately, this study aims to demonstrate that integrating artificial intelligence with mobile health education can create a transformative approach to patient empowerment, clinical care, and chronic disease management within the field of nephrology and nursing.
Despite the prevalence of mobile health (mHealth) technologies in chronic disease management, existing applications for HD patients remain limited, and none have integrated personalized artificial intelligence-based educational support. The absence of AI-driven patient education represents a significant gap in nursing science and digital health innovation. This project addresses that gap by developing and testing a structured, evidence-based mobile education program supported by artificial intelligence, designed specifically for HD patients.
The study will enroll 76 eligible hemodialysis patients from Bitlis State Hospital and Bitlis Tatvan State Hospital. Participants will be randomly assigned to either the intervention group or the control group using simple randomization. The intervention group will receive access to the AI-supported mobile application for six weeks, which includes modules on kidney function, CKD and treatment options, symptom management, dietary adherence, fluid management, treatment adherence, and AVF care. Each module incorporates written content, videos, visuals, voice-supported reading features, and an integrated "Ask a Question" function allowing patients to communicate directly with the research team. The control group will receive routine clinical care without additional intervention.
The artificial intelligence component will assist with content personalization, monitoring of patient engagement, data storage, automated reminders for non-active users, and supportive feedback based on learning progress and biochemical trends. The development of the mobile application will be guided by expert opinions from nephrology specialists, dialysis nurses, academicians, and dietitians. Readability of educational materials will be assessed using the Ateşman Readability Formula. A pilot study will be conducted prior to the trial to evaluate usability using the Web Analysis and Measurement Inventory (WAMMI).
Data collection will include a Patient Identification Form, the Hemodialysis Arteriovenous Fistula Self-Care Behavior Scale, the Hemodialysis Self-Management Scale, and a Biochemical Parameters Tracking Form. Pre-test data will be collected before the intervention; post-test data will be collected at the end of the six-week intervention period. Biochemical parameters will include BUN, creatinine, albumin, potassium, phosphorus, hemoglobin, uric acid levels, Kt/V, and dry weight, obtained from routine clinical records without additional blood sampling.
The primary outcomes will assess changes in self-care and self-management behaviors based on validated scales. Secondary outcomes will examine changes in biochemical parameters between the intervention and control groups. Data analysis will be performed using SPSS, employing descriptive statistics, normality testing, and appropriate statistical comparison tests, with significance set at p \< 0.05.
Ethical approval will be obtained from the appropriate institutional ethics committee, and written informed consent will be secured from all participants. Data confidentiality will be ensured using encrypted login systems and secure storage processes.
This trial is expected to contribute significantly to the scientific literature by being the first AI-supported mobile education intervention tailored for hemodialysis patients. Anticipated benefits include improved self-care behaviors, increased patient autonomy, reduced AVF complications, better adherence to dietary and fluid restrictions, and improved biochemical outcomes. Broader impacts of the project include the potential reduction of hospitalization rates, decreased healthcare costs, increased quality of life for HD patients, and the establishment of a digital model that can be adapted for other chronic disease populations.
Ultimately, this study aims to demonstrate that integrating artificial intelligence with mobile health education can create a transformative approach to patient empowerment, clinical care, and chronic disease management within the field of nephrology and nursing.
Detailed Description:
This project is a Randomized Controlled Interventional Thesis study designed to bridge a critical gap in chronic disease management literature: the lack of personalized, technology-supported education for Hemodialysis (HD) patients.Study Rationale and ObjectivesWhile HD treatment is life-saving, patients face multiple, complex issues, including AVF complications, fluid restriction difficulties, and emotional distress, all requiring high levels of patient self-care and self-management. Existing mobile health (mHealth) applications for HD patients are limited and typically lack personalized features.The core objective is to test the central hypothesis (H1) that an AI-supported mobile education program will have a statistically significant positive effect on patients' self-management scores, AVF self-care behavior scores, and objectively measured biochemical parameters (including creatinine, albumin, and KT/V) compared to routine care.Methodology and Unique Intervention FeaturesThe study follows a strict four-stage methodological plan:Content Design and Validation: The mobile application content is developed based on current literature and then rigorously validated by expert consensus (involving at least ten specialists, including nephrologists, dialysis nurses, and dietitians). Content readability is verified using the Ateşman formula to ensure patient comprehension. Pilot Study and Usability: A preliminary pilot study is conducted with a small group (excluded from the main study) to assess the application's usability and acceptability using the WAMMI (Website Analysis and Measurement Inventory) scale before the main intervention begins.Randomized Intervention: Seventy-six eligible patients are randomly assigned to either the Intervention Group (receiving the mobile education for 6 weeks) or the Control Group (receiving only routine care).Outcome Measurement and AnalysisPrimary outcomes focus on patient behavior and knowledge, measured by pre- and post-tests (after 6 weeks) using validated instruments: the Hemodialysis Self-Management Scale and the AVF Self-Care Behavior Assessment Scale. Secondary outcomes are clinical, measured by tracking biochemical parameters (BUN, creatinine, albumin, etc.) obtained directly from the patient's hospital records, thus avoiding additional invasive procedures. Data analysis will be conducted using SPSS, with a significance level set at p \< 0.05.Expected Impact and Value AddedSuccessful completion is expected to demonstrate significant clinical and economic value by:Improving patient quality of life and autonomy.Reducing the incidence of complications (e.g., AVF failure) and subsequently lowering hospital readmission rates.Providing a cost-effective, sustainable model for chronic disease education that can reduce the financial burden on health institutions and social security.Contributing a novel, evidence-based technological solution to the field of nursing and mHealth literature.
Study Oversight
Has Oversight DMC:
False
Is a FDA Regulated Drug?:
False
Is a FDA Regulated Device?:
False
Is an Unapproved Device?:
None
Is a PPSD?:
None
Is a US Export?:
None
Is an FDA AA801 Violation?: