Trial Review

Technical difficulties have been reported by some users of the search function and is being investigated by technical staff. Thank you for your patience and apologies for any inconvenience caused.

The safety and scientific validity of this study is the responsibility of the study sponsor and investigators. Listing a study does not mean it has been endorsed by the ANZCTR. Before participating in a study, talk to your health care provider and refer to this information for consumers
Trial registered on ANZCTR


Registration number
ACTRN12623000850673
Ethics application status
Approved
Date submitted
20/07/2023
Date registered
8/08/2023
Date last updated
8/08/2023
Date data sharing statement initially provided
8/08/2023
Type of registration
Prospectively registered

Titles & IDs
Public title
Conversational HeAlth supporT in Atrial Fibrillation Self-Management (CHAT-AF-S)
Scientific title
Effectiveness of a conversational Artificial Intelligence program to support patients with atrial fibrillation (AF) in optimising quality of life: the Conversational HeAlth supporT for AF Self-Management (CHAT-AF-S) multi-centre randomised controlled trial
Secondary ID [1] 310133 0
Nil known
Universal Trial Number (UTN)
Trial acronym
CHAT-AF-S
Linked study record
ACTRN12621000174886 was a pilot study evaluating a similar conversational Artificial Intelligence intervention.

Health condition
Health condition(s) or problem(s) studied:
Atrial Fibrillation 330694 0
Condition category
Condition code
Cardiovascular 327523 327523 0 0
Other cardiovascular diseases

Intervention/exposure
Study type
Interventional
Description of intervention(s) / exposure
The “CHAT-AF-S” intervention was co-designed by the investigator team, clinicians, patient engagement academic experts, behavioural scientists, consumers, and leverages results from previous CHAT-AF pilot (Australian New Zealand Clinical Trials Registry ACTRN12621000174886). The intervention consists of automated voice calls (with conversational artificial intelligence (AI) technology, including voice recognition and natural language understanding to evaluate participants’ verbal responses), accompanied by educational text messages.

The goal of the intervention is to support and monitor patients with atrial fibrillation (AF) by encouraging medication adherence, risk factor reduction and disease self-management by providing educational content related to AF. This program aims to also identify patients that might be at higher risk of having AF complications (e.g., have poor overall health, unsure if on blood thinner medications, are highly symptomatic and unable to manage their symptoms) by alerting the central clinical management team.

OUTREACHES

The intervention will consist of a total of six patient outreaches, delivered over the course of 3 months. The outreaches will occur at the following timepoints: 24 – 48 hours, 15 days, 30 days, 45 days, 60 days, and 75 days post-discharge from hospital services. All these outreaches will be automated following an algorithm.

The format of each outreach consists of:
1. Automated phone calls (conversational AI): The first point of contact is via an automated call. If participants are not reached in the first call attempt, the technology will call again in the next 24 hours (3 call attempts). During the automated phone call, patients can respond to queries using their voice (e.g. by saying “Yes”, “No” over the phone). Based on their responses to these queries, patients will receive information tailored to their individual needs (i.e., information on blood thinning medications, rhythm control medications, blood pressure control, General Practitioner visits, AF action plan, symptom management and triggers, sleep apnoea, weight loss, AF procedures).

2. Text message: after three failed call attempts a text message will be sent containing a link to a survey. This survey will have all the content addressed in the automated phone call, however in a written format, with options for patients to self-report using multiple choice answers instead of verbally.

Each outreach will cover different goals and AF-related information:
- Outreach 1 – assessment of overall health, blood thinner medicines, rhythm control medicines, understanding your AF type
- Outreach 2 – assessment of AF symptoms, blood pressure monitoring, blood pressure measuring techniques
- Outreach 3 –AF care team, AF action plan, medication adherence
- Outreach 4 – common triggers for AF, query AF symptoms management
- Outreach 5 – conditions that make AF hard to control, weight management, diet and exercise
- Outreach 6 – AF procedures and treatment options (cardioversion, ablation), stroke information
All outreaches will collect information about participant satisfaction with the call, by asking them to rate the outreach, on a scale of 1 to 5 – 1 being not helpful and 5 being very helpful.

ALERTS

Based on patient responses to the questions asked in the outreaches, certain answers will trigger an alert to the central clinical management team, these include:
- If participant reports that their overall health is 1 or 2 (out of 5) and wants to discuss this further
- If participant is NOT SURE that they are on blood thinner medications and wants to discuss this further
- If participant’s symptoms are SIGNIFICANTLY impacting their daily life and wants to discuss this further
- If participant is UNABLE to manage their symptoms and wants to discuss this further

These alerts will be sent directly to the central clinical management team based at the Westmead Applied Research Centre (Westmead Hospital), University of Sydney. Alerts will be followed up by a phone call from an appropriate member from the clinical research team within 1-2 business days, with escalation to a doctor when required.

EDUCATIONAL TEXT MESSAGES

In addition to these outreaches, educational text messages will be sent to intervention group participants with AF-related information. The topics of information will include blood thinning and rhythm control medication, stroke risk, high blood pressure and AF, managing medications, AF triggers (alcohol, caffeine, illness, sleep, stress, anxiety), sleep apnoea information, losing weight, cardioversions, cardiac ablation, pacemakers. Text messages will be brief and engaging, and some will include external links to online resources, videos, webpages (e.g. Heart Foundation). A total of 27 educational text messages (2-3 per week) will be sent over the 3-month intervention.

MONITORING OF INTERVENTION ADHERENCE
Intervention usage metrics will be automatically collected. A log report of the automated phone calls will contain details such as call answered/unanswered, call duration, and number of queries answered. An electronic log will record the time messages are sent and the status of the delivery (i.e. delivered or not delivered). A log of responses received from participants and when participants contact the study team, including the reason for contact and the method used will also be kept.
Intervention code [1] 326528 0
Treatment: Other
Intervention code [2] 326633 0
Behaviour
Comparator / control treatment
Control group will receive usual care from their nominated health professionals. In general, usual care of AF patients consists of post-discharge instructions from the Cardiologist regarding medications and lifestyle modifications, recommended General Practitioner follow-up to be organised by the patient, and additional Cardiologist appointments as needed.
Control group
Active

Outcomes
Primary outcome [1] 335384 0
Mean Atrial Fibrillation-related quality of life score, assessed via the Atrial Fibrillation Effect on QualiTy-of-life (AFEQT) questionnaire, at 3 months in intervention versus control group.
Timepoint [1] 335384 0
Baseline and 3 months post-randomisation
Secondary outcome [1] 424235 0
Mean Atrial Fibrillation knowledge score, assessed via the Jessa Atrial Fibrillation Knowledge Questionnaire (JAKQ), at 3 months in intervention versus control group.
Timepoint [1] 424235 0
Baseline and 3 months post-randomisation
Secondary outcome [2] 424236 0
Mean Confidence in self-management of Atrial Fibrillation score, assessed via the Confidence in Atrial fibriLlation Management (CALM) Scale, at 3 months in intervention versus control group.
Timepoint [2] 424236 0
Baseline and 3 months post-randomisation
Secondary outcome [3] 424421 0
Mean servings of vegetables consumed on average each day over the last month (self-reported using a validated questionnaire) at 3 months in intervention versus control group.
Timepoint [3] 424421 0
Baseline and 3 months post-randomisation
Secondary outcome [4] 424422 0
Mean servings of fruit consumed on average each day over the last month (self-reported using a validated questionnaire) at 3 months in intervention versus control group.
Timepoint [4] 424422 0
Baseline and 3 months post-randomisation
Secondary outcome [5] 424423 0
Mean minutes of physical activity in past week (Validated single-item physical activity question - Bauman AE, Richards JA. Understanding of the Single-Item Physical Activity Question for Population Surveillance. Journal of Physical Activity and Health. 2022 Sep 19;19(10):681-6.)
Timepoint [5] 424423 0
Baseline and 3 months post-randomisation
Secondary outcome [6] 424424 0
Proportion of non-smokers at 3 months (out of those who were identified as current smokers at baseline) using a study specific questionnaire.
Timepoint [6] 424424 0
Baseline and 3 months post-randomisation
Secondary outcome [7] 424425 0
Mean body mass index (calculated based on self-reported weight and height via study-specific questionnaire)
Timepoint [7] 424425 0
Baseline and 3 months post-randomisation
Secondary outcome [8] 424426 0
Proportion of participants drinking 1 or less alcoholic beverages per week (self-reported via study-specific questionnaire)
Timepoint [8] 424426 0
Baseline and 3 months post-randomisation
Secondary outcome [9] 424427 0
Composite outcome of emergency department presentations and unplanned cardiovascular hospitalisations (self-reported via study-specific questionnaire in past 3 months at baseline and at 3 months post-randomisation)
Timepoint [9] 424427 0
Baseline and 3 months post-randomisation
Secondary outcome [10] 424428 0
Mean Atrial Fibrillation treatment burden score, assessed via the Treatment Burden Questionnaire (TBQ), at 3 months in intervention versus control group.
Timepoint [10] 424428 0
Baseline and 3 months post-randomisation
Secondary outcome [11] 424429 0
Adherence to atrial fibrillation medication (proportion self-reported adherence nearly all of the time, assessed using study-specific questionnaire)
Timepoint [11] 424429 0
Baseline and 3 months post-randomisation

Eligibility
Key inclusion criteria
Patients will be eligible to participate if they (1) are 18 years old or above, (2) have a documented diagnosis of AF, (3) have a mobile phone that is able to receive calls, (4) are able to receive text messages and open weblinks embedded in them, and (5) are competent with English, as ascertained by the study researcher.
Minimum age
18 Years
Maximum age
No limit
Sex
Both males and females
Can healthy volunteers participate?
No
Key exclusion criteria
Participants will be excluded from the study if they (1) are on concurrent active intervention studies focused on atrial fibrillation education and self-management (2) have a concomitant illness, physical impairment or mental condition which in the opinion of the study team/primary care physician could interfere with the conduct of the study including outcome assessment (e.g. hearing impairment not corrected by a digital hearing aid), (3) are pregnant, (4) have a medical illness with anticipated life expectancy of < 3 years, and (5) are unable or unwilling to provide written consent.

Study design
Purpose of the study
Treatment
Allocation to intervention
Randomised controlled trial
Procedure for enrolling a subject and allocating the treatment (allocation concealment procedures)
Allocation concealment will be ensured utilising an electronic system (RedCap; Research Electronic Data Capture). A researcher will manage participant randomization within RedCap as they are recruited. The software will automatically allocate participants to the intervention or control group, according to the randomisation sequence generated in R (using the randomiseR package) and uploaded to RedCap.
Methods used to generate the sequence in which subjects will be randomised (sequence generation)
The randomisation sequence will be generated in R (using the randomiseR package) and uploaded to RedCap. Randomisation will be managed through REDCap, which will automatically allocate participants to the intervention or control group, according to the randomisation sequence. Randomisation will 1:1 (intervention: control) and will be stratified based on sex and site.
Masking / blinding
Blinded (masking used)
Who is / are masked / blinded?


The people assessing the outcomes
The people analysing the results/data
Intervention assignment
Parallel
Other design features
We will conduct an additional process evaluation and assess feasibility and implementation measures in the intervention group: Engagement (e.g., outreach completion rates), satisfaction with the intervention (e.g. satisfaction rates reported for each call, user experience survey), user experience, barriers and enablers to technology use and implementation (assessed through qualitative data captured from semi-structured interviews post-intervention). This is an additional evaluation and so these are not considered secondary trial outcomes.
Phase
Not Applicable
Type of endpoint/s
Efficacy
Statistical methods / analysis
Analyses will follow the intention-to-treat principle (i.e., patients will be analyzed within the group to which they were randomized). For the primary outcome, groups will be compared at 3 months using analysis of covariance (ANCOVA) adjusted for corresponding baseline values. Similarly, other continuous variable secondary outcomes will be adjusted using the corresponding baseline measures. For dichotomous outcomes, groups will be compared using a log-binomial regression also adjusting for corresponding baseline values as fixed effect. Continuous variables will be reported in means and SDs unless they are skewed where medians and interquartile range (IQR) will be used. Categorical variables will be reported as frequencies and/or percentages. All continuous data will be checked for normality before performing?parametric tests. Appropriate non-parametric tests will be used where data are not normally distributed. Effect estimates will be reported with 95% confidence intervals. A p-value <0.05 will be considered statistically significant. A statistical analysis plan will be finalised before data lock and unblinding.

Recruitment
Recruitment status
Not yet recruiting
Date of first participant enrolment
Anticipated
14/08/2023
Actual
Date of last participant enrolment
Anticipated
Actual
Date of last data collection
Anticipated
Actual
Sample size
Target
416
Accrual to date
Final
Recruitment in Australia
Recruitment state(s)
NSW
Recruitment postcode(s) [1] 40881 0
2145 - Westmead

Funding & Sponsors
Funding source category [1] 314293 0
Other Collaborative groups
Name [1] 314293 0
Digital Health CRC Limited ("DHCRC")
Country [1] 314293 0
Australia
Primary sponsor type
University
Name
University of Sydney
Address
83-117 Missenden Rd Camperdown NSW 2050 Australia Postal Address: PO Box M201 Missenden Rd NSW 2050 Australia
Country
Australia
Secondary sponsor category [1] 316262 0
None
Name [1] 316262 0
Address [1] 316262 0
Country [1] 316262 0

Ethics approval
Ethics application status
Approved
Ethics committee name [1] 313409 0
Western Sydney Local Health District Human Research Ethics Committee
Ethics committee address [1] 313409 0
Research Office Level 2 REN Building Westmead Hospital, Hawkesbury & Darcy Roads, Westmead NSW 2145
Ethics committee country [1] 313409 0
Australia
Date submitted for ethics approval [1] 313409 0
01/06/2023
Approval date [1] 313409 0
19/07/2023
Ethics approval number [1] 313409 0
2023/ETH00765

Summary
Brief summary
The aim of the study is to evaluate the efficacy and feasibility of a conversational artificial intelligence (AI) intervention comprising automated phone calls and text messages to improve quality of life and self-management of patients with atrial fibrillation (AF). The hypothesis is that this program will better support patients with AF, improving their quality of life and overall health management and risk factors.
Trial website
Trial related presentations / publications
Public notes

Contacts
Principal investigator
Name 128054 0
Prof Clara Chow
Address 128054 0
The University of Sydney, Faculty of Medicine and Health, Westmead Applied Research Centre, Level 5, Block K | Entrance 10, Westmead Hospital | Hawkesbury Road Westmead, NSW, 2145
Country 128054 0
Australia
Phone 128054 0
+61 2 86273580
Fax 128054 0
Email 128054 0
clara.chow@sydney.edu.au
Contact person for public queries
Name 128055 0
Dr Liliana Laranjo
Address 128055 0
The University of Sydney, Faculty of Medicine and Health, Westmead Applied Research Centre, Level 5, Block K | Entrance 10, Westmead Hospital | Hawkesbury Road Westmead, NSW, 2145
Country 128055 0
Australia
Phone 128055 0
+61 413461852
Fax 128055 0
Email 128055 0
liliana.laranjo@sydney.edu.au
Contact person for scientific queries
Name 128056 0
Dr Liliana Laranjo
Address 128056 0
The University of Sydney, Faculty of Medicine and Health, Westmead Applied Research Centre, Level 5, Block K | Entrance 10, Westmead Hospital | Hawkesbury Road Westmead, NSW, 2145
Country 128056 0
Australia
Phone 128056 0
+61 413461852
Fax 128056 0
Email 128056 0
liliana.laranjo@sydney.edu.au

Data sharing statement
Will individual participant data (IPD) for this trial be available (including data dictionaries)?
No
No/undecided IPD sharing reason/comment
Data sharing not permitted by ethics.


What supporting documents are/will be available?

No Supporting Document Provided



Results publications and other study-related documents

Documents added manually
No documents have been uploaded by study researchers.

Documents added automatically
No additional documents have been identified.