AI-Assisted Telehealth for Chronic Conditions

Overseen By Mohanraj Thirumalai, PhD

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: University of Alabama at Birmingham

Disqualifiers: Cognitive impairment, Depression, Cardiac event, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

Duration: 24 weeks

212 Participants Needed

Trial Summary

Do I need to stop my current medications for the trial?

The trial information does not specify whether you need to stop taking your current medications. It's best to discuss this with the trial coordinators or your doctor.

What data supports the effectiveness of the treatment AI4CHRON?

Research shows that AI tools, like conversational agents and virtual assistants, are promising for helping people manage chronic conditions by improving self-care and patient satisfaction. These tools have been found helpful and easy to use, which suggests that AI4CHRON could be effective in supporting chronic disease management. ^{1 2 3 4 5}

Is AI-Assisted Telehealth for Chronic Conditions safe for humans?

The UC HAT system, a type of AI-assisted telehealth, was well-received by patients with ulcerative colitis, with 70% feeling safer using it and 90% willing to use it in the future, suggesting it is generally safe for human use. ^{1 6 7 8 9}

How is the AI4CHRON treatment different from other treatments for chronic conditions?

AI4CHRON is unique because it uses artificial intelligence to help patients manage their chronic conditions through a telehealth platform, offering personalized predictions and follow-up care, which can reduce the need for frequent doctor visits and lower healthcare costs. ^{2 4 10 11 12}

What is the purpose of this trial?

The purpose of this study to pilot test an accessible and inclusive artificial intelligence (AI)-assisted, individualized, family-focused lifestyle modification intervention (AI4CHRON) for health-related quality of life for adults with impaired mobility and chronic medical conditions.

Eligibility Criteria

This trial is for adults over 18 with heart disease, chronic lung disease, or Type 2 diabetes who also live with a permanent physical disability like spina bifida. Participants must be able to communicate and read in English and have access to a smartphone or computer.

Inclusion Criteria

I have a smartphone or computer.

I can speak and read English.

I live with a permanent physical disability like spina bifida or MS.

Exclusion Criteria

Current enrollment in any structured intervention

I have a visual or hearing impairment.

I have significant memory or thinking problems.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Treatment

Participants engage in a lifestyle modification intervention with AI assistance for health-related quality of life

24 weeks

Telehealth sessions as per group assignment

Follow-up

Participants are monitored for safety and effectiveness after treatment

4 weeks

Treatment Details

Interventions

• AI4CHRON

Trial Overview The study tests an AI-assisted telehealth platform designed for people with chronic diseases and impaired mobility. It compares four approaches: two without scheduled coaching calls (with gamified or independent rewards) and two with calls (also with gamified or independent rewards).

Participant Groups

Group I: Scheduled Coaching Calls & Independent rewards (No Gamification) Experimental Treatment 1 Intervention

Group II: Scheduled Coaching Calls & Gamified Rewards Experimental Treatment 1 Intervention

Group III: No Scheduled Coaching Calls & Independent Rewards (No Gamification) Experimental Treatment 1 Intervention

Group IV: No Scheduled Coaching Call & Gamified Rewards Experimental Treatment 1 Intervention

Who Is Running the Clinical Trial?

University of Alabama at Birmingham

Lead Sponsor

Trials

1,677

Recruited

2,458,000+

Findings from Research

In a study involving 200 patients with acute decompensated heart failure, an avatar-based app aimed at improving patient education showed that only 36 high-risk patients were randomized to use it, highlighting challenges in engaging elderly and critically ill patients with technology.

Despite the potential of AI-based education to enhance self-care and quality of life, only 20% of enrolled patients completed the program, indicating significant barriers to effective use and engagement in this demographic.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

An m-Health intervention to improve education, self-management, and outcomes in patients admitted for acute decompensated heart failure: barriers to effective implementation. Zisis, G., Carrington, MJ., Oldenburg, B., et al.[2023]

The CC-Guardian AI system, developed for managing congenital cataract, shows high sensitivity and specificity in predicting complications and scheduling follow-ups, indicating its effectiveness in real-world applications.

By integrating this AI with a smartphone app and a cloud platform, the system not only detects complications earlier but also reduces socioeconomic burdens compared to traditional monitoring methods.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Artificial intelligence manages congenital cataract with individualized prediction and telehealth computing. Long, E., Chen, J., Wu, X., et al.[2023]

A new AI-driven clinical decision support system (CDSS) was developed using data from 27,904 diabetes patients, which predicts the effectiveness of different treatment strategies to help achieve care goals.

This CDSS was successfully integrated with the Epic electronic health record (EHR) system, demonstrating improved prediction accuracy over previous methods and the potential for application in other chronic conditions.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Leveraging Artificial Intelligence to Improve Chronic Disease Care: Methods and Application to Pharmacotherapy Decision Support for Type-2 Diabetes Mellitus. Tarumi, S., Takeuchi, W., Chalkidis, G., et al.[2021]

A review of 26 studies on conversational agents (CAs) in healthcare for chronic conditions shows that users generally find these tools helpful, satisfying, and easy to use, indicating promising acceptance for self-management.

Despite positive user feedback, there is a significant gap in reliable evidence regarding the efficacy of AI-enabled CAs due to insufficient reporting on their technical implementation, which limits the ability to compare their effectiveness.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

A Systematic Review on Healthcare Artificial Intelligent Conversational Agents for Chronic Conditions. Bin Sawad, A., Narayan, B., Alnefaie, A., et al.[2022]

The study successfully co-designed an autonomous virtual agent to support self-management for patients with chronic obstructive pulmonary disease (COPD), focusing on key scenarios like crisis support and emotional well-being, based on input from both patients and health professionals.

Participants found the virtual agent acceptable and engaging, particularly appreciating its potential to assist individuals living alone, highlighting the importance of integrating mental health support into chronic disease management.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

A Virtual Agent to Support Individuals Living With Physical and Mental Comorbidities: Co-Design and Acceptability Testing. Easton, K., Potter, S., Bec, R., et al.[2022]

The study analyzed 16,453 lines of dialog from 424 patients with inflammatory bowel diseases (IBD) to explore the feasibility of using natural language processing (NLP) for categorizing patient communications, demonstrating that NLP can effectively categorize patient data into relevant categories such as symptoms, medications, and appointments.

The categorization algorithm showed a high agreement with independent physician evaluations, with 95% of cases having minor or no differences, indicating that NLP can reliably assist in developing chatbots for chronic disease management, potentially improving patient monitoring and education.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

An Exploration Into the Use of a Chatbot for Patients With Inflammatory Bowel Diseases: Retrospective Cohort Study. Zand, A., Sharma, A., Stokes, Z., et al.[2020]

The 'Nurse Chatbot' aims to enhance patient access to healthcare information and support chronic disease management, potentially addressing the global shortage of healthcare providers by utilizing artificial intelligence.

The development of the 'Nurse Chatbot' is designed to be scalable and customizable, promoting effective communication and patient satisfaction while also considering ethical and safety issues in its implementation.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Network Diffusion and Technology Acceptance of A Nurse Chatbot for Chronic Disease Self-Management Support : A Theoretical Perspective. Hernandez, JPT.[2019]

A study involving 54 participants found that 29% of the actions suggested by conversational assistants for medical problems could potentially lead to patient harm, with 16% of those actions posing a risk of death.

Only 43% of the medical queries were successfully completed, highlighting the unreliability of conversational assistants for providing safe and actionable medical information, emphasizing the need for users to consult healthcare providers for medical advice.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Patient and Consumer Safety Risks When Using Conversational Assistants for Medical Information: An Observational Study of Siri, Alexa, and Google Assistant. Bickmore, TW., Trinh, H., Olafsson, S., et al.[2019]

A study involving 10 adult patients with ulcerative colitis showed high acceptance of the home automated telemanagement (UC HAT) system, with 90% of participants willing to use it in the future, indicating its potential for improving patient engagement and adherence to treatment.

Patients found the UC HAT system easy to use and reported that it could enhance monitoring of their symptoms and side effects, suggesting that it may lead to better clinical outcomes and increased patient satisfaction in managing ulcerative colitis.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Home telemanagement for patients with ulcerative colitis (UC HAT). Cross, RK., Cheevers, N., Finkelstein, J.[2021]

The SENSING-AI project aims to develop an artificial intelligence-driven digital health solution to support the self-management of patients with long COVID-19 and assist healthcare professionals in managing their care, utilizing data from 10 patients for training predictive algorithms.

By collecting psychometric and biometric data through wearable devices and validated questionnaires, the project seeks to improve patient outcomes and provide timely clinical decision support, highlighting the importance of innovative digital health solutions in managing the aftermath of the COVID-19 pandemic.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

An Artificial Intelligence-Driven Digital Health Solution to Support Clinical Management of Patients With Long COVID-19: Protocol for a Prospective Multicenter Observational Study. Fuster-Casanovas, A., Fernandez-Luque, L., Nuñez-Benjumea, FJ., et al.[2022]

The use of the AI-powered telehealth platform, Laura Digital Emergency Room, in Brazil facilitated around 130,000 interactions and helped triage 24,162 patients during the COVID-19 pandemic, effectively classifying most patients with mild to moderate symptoms.

This approach demonstrated that AI can enhance healthcare accessibility and safety, potentially reducing the burden on Brazil's public health system, which serves 75% of the population, especially during a crisis like the pandemic.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

COVID-19 in Brazil-Preliminary Analysis of Response Supported by Artificial Intelligence in Municipalities. Morales, HMP., Guedes, M., Silva, JS., et al.[2021]

The study involved 1,667 patients over a 24-month period and developed an AI-assisted telecare platform that effectively predicts acute exacerbation events for chronic diseases, achieving an average accuracy of 88.46%.

By integrating real-time monitoring of lifestyle and environmental factors, the platform demonstrated that these factors are strongly linked to health outcomes, outperforming traditional questionnaire-based data in predicting future health issues.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

A Precision Health Service for Chronic Diseases: Development and Cohort Study Using Wearable Device, Machine Learning, and Deep Learning. Wu, CT., Wang, SM., Su, YE., et al.[2022]

References

1. England pubmed.ncbi.nlm.nih.gov

An m-Health intervention to improve education, self-management, and outcomes in patients admitted for acute decompensated heart failure: barriers to effective implementation. [2023]

2. England pubmed.ncbi.nlm.nih.gov

Artificial intelligence manages congenital cataract with individualized prediction and telehealth computing. [2023]

3. Germany pubmed.ncbi.nlm.nih.gov

Leveraging Artificial Intelligence to Improve Chronic Disease Care: Methods and Application to Pharmacotherapy Decision Support for Type-2 Diabetes Mellitus. [2021]

4. Switzerland pubmed.ncbi.nlm.nih.gov

A Systematic Review on Healthcare Artificial Intelligent Conversational Agents for Chronic Conditions. [2022]

5. Canada pubmed.ncbi.nlm.nih.gov

A Virtual Agent to Support Individuals Living With Physical and Mental Comorbidities: Co-Design and Acceptability Testing. [2022]

6. Canada pubmed.ncbi.nlm.nih.gov

An Exploration Into the Use of a Chatbot for Patients With Inflammatory Bowel Diseases: Retrospective Cohort Study. [2020]

7. Japan pubmed.ncbi.nlm.nih.gov

Network Diffusion and Technology Acceptance of A Nurse Chatbot for Chronic Disease Self-Management Support : A Theoretical Perspective. [2019]

8. Canada pubmed.ncbi.nlm.nih.gov

Patient and Consumer Safety Risks When Using Conversational Assistants for Medical Information: An Observational Study of Siri, Alexa, and Google Assistant. [2019]

9. United States pubmed.ncbi.nlm.nih.gov

Home telemanagement for patients with ulcerative colitis (UC HAT). [2021]

10. Canada pubmed.ncbi.nlm.nih.gov

An Artificial Intelligence-Driven Digital Health Solution to Support Clinical Management of Patients With Long COVID-19: Protocol for a Prospective Multicenter Observational Study. [2022]

11. Switzerland pubmed.ncbi.nlm.nih.gov

COVID-19 in Brazil-Preliminary Analysis of Response Supported by Artificial Intelligence in Municipalities. [2021]

12. United States pubmed.ncbi.nlm.nih.gov

A Precision Health Service for Chronic Diseases: Development and Cohort Study Using Wearable Device, Machine Learning, and Deep Learning. [2022]