Voice-Based Platform for Chronic Health Management

Overseen By Klaren Pe-Romashko, MS

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: University of Wisconsin, Madison

Disqualifiers: Psychotic disorder, Acute medical problem, Impairments, others

Compensation: Varies

Number of Visits: 6

Duration: 12 months

502 Participants Needed

Trial Summary

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. It seems focused on testing a voice-based health management platform, so it's likely you can continue your usual medications.

What data supports the effectiveness of the treatment Elder Tree?

Research shows that voice-based platforms and conversational agents can be helpful for managing chronic conditions, as they are generally well-received by users and can improve the efficiency of health coaching. However, there is still limited evidence on their direct effectiveness for specific health outcomes. ^{1 2 3 4 5}

Is the voice-based platform for chronic health management safe for humans?

There is no specific safety data available for the voice-based platform, but similar telemonitoring systems have been used safely for monitoring vaccine side effects and symptoms in chronic disease patients. ^{6 7 8 9 10}

How is the Elder Tree treatment different from other treatments for chronic health management?

The Elder Tree treatment is unique because it uses a voice-based platform to manage chronic health conditions, making it accessible and easy to use for older adults who may have difficulty with more complex technology. This approach leverages the widespread familiarity and simplicity of telephones and mobile phones to provide personalized health and wellness care, which is different from traditional methods that may rely on in-person visits or more complicated digital interfaces. ^{1 2 4 11 12}

What is the purpose of this trial?

Multiple chronic conditions (MCCs) are costly and pervasive among older adults. MCCs account for 90% of Medicare spending, and 65% of Medicare beneficiaries have 3 or more chronic conditions; 23% have 5 or more. MCCs are often addressed in primary care, where time pressures force a focus on medication and lab results rather than self-management skills. Patients often struggle with treatment adherence and the emotional and physical burdens of self-management and health tracking. Chronic conditions reduce quality of life (QOL) and increase loneliness, which exacerbate those conditions. The primary purpose of this study is to investigate whether a voice-based platform is better for delivering an electronic health intervention to older adults than a text/typing-based platform. We have an evidence-based electronic health intervention (Elder Tree, ET) that has been shown to improve quality of life, physical and socio-emotional health outcomes for older adults with multiple chronic conditions when delivered via a text/typing-based system. The current project would test whether such patients would benefit even more if ET were delivered via a voice-based system (vs. the text-based system) because they would use it more consistently. ET is an existing intervention providing tools, motivation, and support on a computer platform to help older adults manage their health.

Research Team

David H Gustafson, PhD

Principal Investigator

University of Wisconsin, Madison

Eligibility Criteria

This trial is for people aged 60 or older who have at least five chronic health conditions, with hypertension, high cholesterol, obesity, prediabetes/diabetes, or depression being among them. Participants must be willing to share their medical records and allow communication with their primary care provider.

Inclusion Criteria

I am 60 years old or older.

Allow researchers to share information with the patient's primary care provider

Be willing to share medical record data about healthcare use (30-day hospital readmissions and ER, urgent care, primary care, and specialty care visits)

Exclusion Criteria

Report no current psychotic disorder that would prevent participation

Not report impairments preventing use of a computer or tablet (e.g. blind, deaf)

I do not need to be in the hospital right now for a sudden illness.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Treatment

Participants receive the ElderTree intervention via either a voice-based or text-based platform to manage chronic health conditions

12 months

Regular use of the platform is encouraged

Follow-up

Participants are monitored for changes in function, disability, and other health outcomes

6 months

Assessments at 6, 12, and 18 months

Treatment Details

Interventions

• Elder Tree

Trial Overview The study compares two ways of delivering a health management program called Elder Tree (ET) to seniors with multiple chronic illnesses: one using voice commands through a smart system (ET-Voice), and the other via text on a laptop (ET-Text).

Participant Groups

Group I: Experimental group (ET-Voice) Experimental Treatment 1 Intervention

Participants will receive ElderTree on a smart system.

Group II: Control group (ET-Text) Placebo Group 1 Intervention

Participants will receive ElderTree on a laptop.

Who Is Running the Clinical Trial?

University of Wisconsin, Madison

Lead Sponsor

Trials

1,249

Recruited

3,255,000+

National Heart, Lung, and Blood Institute (NHLBI)

Collaborator

Trials

3,987

Recruited

47,860,000+

Findings from Research

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 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]

A significant 86% of the 111 diabetes patients experienced at least one adverse event (AE) or potential adverse event (PotAE) over a 9-month period, highlighting the prevalence of safety issues in chronic disease management.

The majority of AEs (63%) were related to medication management, and 77% of events involved patient actions, indicating that enhancing patient self-management and communication with healthcare providers is crucial for preventing these events.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

What happens between visits? Adverse and potential adverse events among a low-income, urban, ambulatory population with diabetes. Sarkar, U., Handley, MA., Gupta, R., et al.[2021]

In a study reviewing 1289 charts of older adults with cardiovascular diagnoses, 50% had triggers indicating potential adverse drug events (ADEs), with 232 of these triggers confirmed as ADEs, highlighting the prevalence of medication-related issues in this population.

Only nine out of 39 triggers were highly predictive of ADEs, accounting for 94.4% of the detected events, suggesting that a more streamlined trigger tool could be developed to improve the identification of ADEs in primary care settings.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Experience with a trigger tool for identifying adverse drug events among older adults in ambulatory primary care. Singh, R., McLean-Plunckett, EA., Kee, R., et al.[2022]

The FDA's ASTER pilot study demonstrated that electronic health record (EHR)-triggered adverse event reports can provide valuable postmarketing safety information, particularly for known adverse drug events (ADEs).

However, the quality of the reports varied, with many lacking critical details such as informative descriptions and relevant laboratory data, highlighting the need for improved data quality to enhance the utility of EHR-triggered ADE reporting.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Quality assessment of spontaneous triggered adverse event reports received by the Food and Drug Administration. Brajovic, S., Piazza-Hepp, T., Swartz, L., et al.[2012]

References

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

Interactive voice response systems in the diagnosis and management of chronic disease. [2006]

2. Switzerland pubmed.ncbi.nlm.nih.gov

Adaptive Health Coaching Technology for Tailored Interventions. [2021]

3. Switzerland pubmed.ncbi.nlm.nih.gov

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

4. Netherlands pubmed.ncbi.nlm.nih.gov

Evaluation of a virtual coaching system eHealth intervention: A mixed methods observational cohort study in the Netherlands. [2022]

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

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

6. England pubmed.ncbi.nlm.nih.gov

What happens between visits? Adverse and potential adverse events among a low-income, urban, ambulatory population with diabetes. [2021]

7. England pubmed.ncbi.nlm.nih.gov

Experience with a trigger tool for identifying adverse drug events among older adults in ambulatory primary care. [2022]

8. England pubmed.ncbi.nlm.nih.gov

Feasibility of telemonitoring for active surveillance of influenza vaccine safety in the primary care setting in The Netherlands. [2009]

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

Screening for Adverse Drug Events: a Randomized Trial of Automated Calls Coupled with Phone-Based Pharmacist Counseling. [2020]

10. England pubmed.ncbi.nlm.nih.gov

Quality assessment of spontaneous triggered adverse event reports received by the Food and Drug Administration. [2012]

11. Netherlands pubmed.ncbi.nlm.nih.gov

Preliminary evaluations of a spoken web enabled care management platform. [2017]

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

FrailSafe: An ICT Platform for Unobtrusive Sensing of Multi-Domain Frailty for Personalized Interventions. [2021]