AI Text Messaging for Cardiovascular Disease

Recruiting at 2 trial locations

Overseen By Lisa Sandy, MA

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: University of Colorado, Denver

Disqualifiers: No cellphone, Hospice, Non-English/Spanish, others

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

Compensation: Varies

Number of Visits: 12

2100 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial explores how well three types of text messaging can manage cardiovascular disease risk factors in underserved communities. The study tests simple text messages, interactive chatbot messages, and chatbot messages with added pharmacist support to determine which method best aids adherence to lifestyle changes and medications. The goal is to improve health outcomes for individuals with high blood pressure, diabetes, or high cholesterol, particularly those struggling with medication adherence. Participants should have one of these conditions at a risky level and have recently faced challenges in refilling prescriptions. The findings could guide better patient involvement in managing chronic cardiovascular diseases. As an unphased trial, this study offers participants the chance to contribute to innovative solutions for managing cardiovascular health in underserved communities.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. However, since the study focuses on improving medication adherence, it is likely that you will continue your current medications.

Is there any evidence suggesting that this trial's strategies are likely to be safe?

Research shows that AI text messaging, including simple texts, interactive chatbot messages, and those with pharmacist support, is generally safe for people. Current studies have not identified any major negative effects from these methods. These tools aim to help people manage their heart health by sending reminders and tips to their phones.

Evidence from earlier studies indicates that people find AI health reminders easy to use. Many appreciate the convenience of receiving health prompts in this manner. Although this approach is not a medication or medical procedure, it helps improve health habits and outcomes by encouraging actions like checking blood pressure or making healthier lifestyle choices.

Overall, these digital tools are designed to help people manage their health and are considered safe. They offer a modern way to support individuals, especially those in underserved communities, in maintaining better health without causing harm. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about this trial because it explores innovative ways to support people with cardiovascular disease using AI-driven text messaging. Unlike standard care, which typically involves medication and lifestyle changes, this approach leverages technology to engage patients in their own care. The first arm uses generic text messages from trusted sources to remind patients of tasks like checking their blood pressure. The second arm goes a step further with an interactive AI chatbot that uses natural language processing to create personalized and engaging conversations, encouraging patients to take active steps in managing their health. The third arm combines this AI chatbot with proactive pharmacist management, offering a more comprehensive approach by addressing individual risk factors through direct communication. This trial aims to find out if these tech-driven strategies can enhance patient autonomy and improve cardiovascular health outcomes.

What evidence suggests that this trial's strategies could be effective for improving cardiovascular risk factors in patients facing health disparities?

Research has shown that AI text messaging, such as interactive chatbot messages, can help manage heart health risks. For example, one study found that these chatbots increased awareness and knowledge about heart health, potentially leading to better self-care. Another study suggested that AI messaging encouraging heart-healthy habits could help control risk factors.

In this trial, participants may receive either generic text messages or interactive AI chatbot text messaging. Some participants will also receive proactive pharmacist management alongside the AI chatbot messaging. Research has demonstrated that pharmacists play a key role in reducing heart health risks. This method combines mobile technology and expert support to focus on lifestyle changes and adherence to medication plans, aiming to improve overall heart health. ^{5 6 7 8 9}

Who Is on the Research Team?

Michael Ho, MD, PhD

Principal Investigator

University of Colorado, Denver

Are You a Good Fit for This Trial?

This trial is for patients with cardiovascular risk factors who face health disparities, such as ethnic minorities, those with limited English proficiency, and low-income individuals. The study aims to improve self-management of chronic diseases in these groups.

Inclusion Criteria

The risk factor is at poor or intermediate health levels as defined by LE8 (e.g., BP>140/90 mm Hg)

I have been late refilling my heart risk medication in the last 6 months.

I have been diagnosed with hypertension, diabetes, or high cholesterol.

Exclusion Criteria

Patients who do not have a cellphone

I am enrolled in hospice or palliative care.

Enrolled in another clinical trial if denoted in the EHR

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Development and Pilot

Development of AI chatbot infrastructure and pilot study to assess feasibility

12 months

Stakeholder meetings and pilot study sessions

Randomized Intervention

Conduct a pragmatic patient-level randomized intervention of 3 text messaging delivery strategies for self-management support of CV risk factors

36 months

Regular virtual interactions via text messaging

Follow-up

Participants are monitored for changes in Life's Essential 8 health score and other secondary outcomes

12 months

Data collection at baseline and 12 months

What Are the Treatments Tested in This Trial?

Interventions

• AI Text Messaging

Trial Overview The trial compares three strategies to reduce cardiovascular disease risks: generic text messages, interactive AI chatbot messaging, and chatbot messages plus proactive pharmacist support. It uses the AHA's Life's Essential 8 metrics for evaluation.

How Is the Trial Designed?

Group I: Generic text messages Active Control 1 Intervention

The information content for these messages will be derived from trusted sources of medical information and contain links to websites such as American Heart Association. An example of such a message would be: Remember to take your blood pressure today! You can find more information from the American Heart Association by clicking here. Patients will be able to return texts with questions which will be addressed by the study team, including a clinical pharmacist if needed.

Group II: Interactive AI chatbot text messaging Active Control 1 Intervention

This AI system will utilize NLP and ML to facilitate bi-directional system-patient dialogue with messages that incorporate content utilizing tailoring, behavioral nudges and persuasive messaging as described above. An example message would be: Make a promise to yourself to check your blood pressure today! Your goal is to have the top number at 120 or lower and the bottom number at 80 or lower. Each message will end with a question for the participant that will encourage engagement with the AI conversational chatbot that allows greater opportunity to use theoretical content to engage patient autonomy, competence and relatedness, the mechanisms through which we will impact behaviors.

Group III: Interactive AI chatbot text messaging + proactive pharmacist management Active Control 2 Interventions

The AI chatbot will be the same as arm 2 (Interactive AI chatbot text messaging alone). In this arm, however, pharmacists will review patient's baseline LE8 risk factors and proactively contact patients via telephone and/or the EHR patient portal to address any risk factor that is in poor/intermediate health categories. The investigators are proposing proactive pharmacist involvement as a population-based approach to address patients with uncontrolled CV risk factors.

Who Is Running the Clinical Trial?

University of Colorado, Denver

Lead Sponsor

Trials

1,842

Recruited

3,028,000+

National Heart, Lung, and Blood Institute (NHLBI)

Collaborator

Trials

3,987

Recruited

47,860,000+

Published Research Related to This Trial

In a study of 246 adults at moderate-high cardiovascular risk, text message support did not significantly reduce the number of patients with three or more uncontrolled cardiovascular risk factors (CVRFs) after 6 months, indicating limited overall impact on multiple risk factors.

However, participants receiving text message support were less likely to be physically inactive and showed a higher rate of reducing their uncontrolled CVRFs compared to the control group, suggesting that while the intervention may not have drastically changed the overall risk factor profile, it did encourage positive behavior changes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Text messages for primary prevention of cardiovascular disease: The TextMe2 randomized clinical trial. Klimis, H., Thiagalingam, A., McIntyre, D., et al.[2021]

A systematic review of 50 studies suggests that conversational agents, like chatbots and avatars, can effectively improve weight-related behaviors such as diet and physical activity, which are important for managing cardiometabolic risk factors.

While patients showed interest and acceptable adherence to using these virtual agents, more rigorous randomized controlled trials are needed to confirm their effectiveness, especially for conditions like diabetes and hypertension.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Conversational Agents and Avatars for Cardiometabolic Risk Factors and Lifestyle-Related Behaviors: Scoping Review. Lyzwinski, LN., Elgendi, M., Menon, C.[2023]

Using animated avatars in a computer-based tool to communicate cardiovascular risk significantly improved participants' intention to make lifestyle changes, compared to using voice alone.

In a study with 41 male participants at intermediate to high cardiovascular risk, the avatar approach also enhanced the intention to follow medical treatments, indicating its potential effectiveness in promoting healthier behaviors.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The Communication of Global Cardiovascular Risk by Avatars. Ruiz, JG., Andrade, AD., Karanam, C., et al.[2018]

Text messaging can be an effective tool to improve medication refill behavior among patients with chronic conditions, as it can be easily delivered at scale and tailored to individual needs.

Patients preferred personalized, positively framed messages that evoke social support, suggesting that the design of these messages is crucial for enhancing medication adherence and improving chronic care outcomes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Nudge me: tailoring text messages for prescription adherence through N-of-1 interviews. Waughtal, J., Luong, P., Sandy, L., et al.[2022]

A randomized study demonstrated that a technology-assisted pharmacist intervention effectively improved physician adherence to medication guidelines for coronary heart disease (CHD) secondary prevention.

Patients in the intervention group had a higher proportion of being discharged on appropriate secondary prevention medications, indicating the intervention's efficacy in enhancing treatment compliance.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Improving adherence to coronary heart disease secondary prevention medication guidelines at a community hospital. Bailey, TC., Noirot, LA., Gage, BF., et al.[2018]

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]

A study evaluating ChatGPT's ability to provide health advice on cardiovascular diseases found that while its responses were generally above average, they varied widely in quality, with some being dangerously incorrect or incomplete.

The quality of ChatGPT's responses improved with higher health literacy prompts, and surprisingly, responses in lower-resource languages were often of better quality, raising concerns about the potential for health inequalities if such AI systems are widely used for medical advice.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Heart-to-heart with ChatGPT: the impact of patients consulting AI for cardiovascular health advice. Lautrup, AD., Hyrup, T., Schneider-Kamp, A., et al.[2023]

A study validated expert-developed text messages aimed at improving medication adherence by addressing barriers like disease beliefs and forgetfulness, with 40 participants initially grouping 32 messages into various categories.

After refining the messages, a second group of 37 participants successfully categorized 36 messages into 5 distinct groups, confirming the effectiveness of the message structure for future research on enhancing adherence to anti-hypertensive medications.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Confirming the theoretical structure of expert-developed text messages to improve adherence to anti-hypertensive medications. Farris, KB., Salgado, TM., Batra, P., et al.[2019]

Citations

1. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC12526652/

AI HeartBot to Increase Women's Awareness and ... This study aimed to evaluate the potential efficacy of HeartBot to increase women's awareness and knowledge of heart attack symptoms and care- ...

2. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC12538107/

Human-Delivered Conversation Versus AI Chatbot ... This study aims to evaluate and explore the potential efficacy of human-delivered conversations versus AI chatbot conversations in increasing ...

3. ahajournals.org ahajournals.org/doi/10.1161/CIRCOUTCOMES.119.005616

Effect of Text Messaging on Risk Factor Management in ... Text messages supporting secondary prevention among patients with coronary heart disease did not lead to a greater reduction in blood pressure ...

4. dcricollab.dcri.duke.edu dcricollab.dcri.duke.edu/sites/NIHKR/KR/Chat%204%20Heart%20Health%20Study%20Snapshot.pdf

Using AI Text Messaging to Improve the American Heart ... The goal of Chat 4 Heart Health is to improve control of risk factors for cardiovascular disease using a multilevel intervention that leverages mobile phone– ...

5. centerwatch.com centerwatch.com/clinical-trials/listings/NCT06324981/using-ai-text-messaging-to-improve-ahas-lifes-essential-8-health-behaviors?state=CO&city=Wheatridge

Using AI Text Messaging to Improve AHA's Life's Essential ... Patients with CV disease risk factors will be randomized to 1 of 3 automated communication approaches: 1) generic text messages; 2) interactive ...

6. trialx.com trialx.com/clinical-trials/listings/316015/using-ai-text-messaging-to-improve-ahas-lifes-essential-8-health-behaviors/

Using AI Text Messaging to Improve AHA's Life's Essential 8 ... The three different strategies are: 1) text messages, 2) interactive chatbot messages, and 3) chatbot messages with proactive pharmacist support. To measure ...

7. rethinkingclinicaltrials.org rethinkingclinicaltrials.org/demonstration-projects/using-artificially-intellegent-text-messaging-technology-to-improve-aha-le8-health-behaviors/

UH3 Project: Using Artificially Intelligent Text Messaging ... The goal of Chat 4 Heart Health is to improve control of risk factors for cardiovascular disease using a multilevel intervention that leverages mobile phone– ...

8. cdn.clinicaltrials.gov cdn.clinicaltrials.gov/large-docs/81/NCT06324981/Prot_000.pdf

Study Protocol “Using artificially intelligent text messaging ... Our goal is to improve control of cardiovascular (CV) disease risk factors using a multilevel intervention leveraging cellphone-based text ...

9. dcricollab.dcri.duke.edu dcricollab.dcri.duke.edu/sites/NIHKR/KR/Chat%204%20Heart%20Health%20Ethics%20and%20Regulatory%20Discussion.pdf

Chat 4 Heart Health Ethics and Regulatory Discussion generic and AI chatbot text message and proactive pharmacist support interventions. PRISM includes the RE-. AIM outcomes identified above and ...