JMIR Publications

ABSTRACT

Background:

Atrial fibrillation (AF) is an increasingly common chronic health condition in which integrated care, that is multidisciplinary and patient-centric, is recommended yet challenging to implement. Methods and analysis: CHAT-AF is a 6-month randomised controlled trial of adult patients with AF (n=385) allocated in a ratio 4:1 to AF-support or usual care. The primary outcome is AF-related quality of life, and secondary outcomes include cardiovascular risk factors, outcomes, and health care utilisation. The 4:1 allocation design enables a detailed examination of the feasibility, uptake, and process of implementation of AF-support. Participants with new or ongoing AF will be recruited from hospitals and specialist-led clinics in Sydney, Australia. ‘AF-Support’ has been co-designed with clinicians, researchers, information technologists and consumers. It comprises automated phone calls, text messages and emails, and an educational website. Automated calls will occur 7 times with the first call triggered to commence 24-48 hours after initiation. Calls follow a standard flow but are customised to vary depending on patient responses. Calls assess AF symptoms and participant responses will trigger different system responses based on pre-specified protocols including identification of red flags requiring escalation. Randomised trial data analysis will be according to the principle of intention-to-treat and qualitative data will be thematically analysed. Ethics approval was granted by the Western Sydney Local Health District (WSLHD) Human Ethics Research Committee (2020/ETH02546).

Objective:

The aim of CHAT-AF is to evaluate the feasibility and potential efficacy of a digital intervention (‘AF-Support’) comprising a pre-programmed set of automated phone calls (artificial intelligence conversational technology), texts and emails to support AF patients self-manage their condition and coordinate primary and secondary care follow-up.

Methods:

CHAT-AF is a 6-month randomised controlled trial of adult patients with AF (n=385) allocated in a ratio 4:1 to AF-support or usual care. The primary outcome is AF-related quality of life, and secondary outcomes include cardiovascular risk factors, outcomes, and health care utilisation. The 4:1 allocation design enables a detailed examination of the feasibility, uptake, and process of implementation of AF-support. Participants with new or ongoing AF will be recruited from hospitals and specialist-led clinics in Sydney, Australia. ‘AF-Support’ has been co-designed with clinicians, researchers, information technologists and consumers. It comprises automated phone calls, text messages and emails, and an educational website. Automated calls will occur 7 times with the first call triggered to commence 24-48 hours after initiation. Calls follow a standard flow but are customised to vary depending on patient responses. Calls assess AF symptoms and participant responses will trigger different system responses based on pre-specified protocols including identification of red flags requiring escalation. Randomised trial data analysis will be according to the principle of intention-to-treat and qualitative data will be thematically analysed.

Results:

To the best of our knowledge, this will be the first detailed evaluation of an artificial intelligence conversational technology to support AF integrated care. Results will include data on efficacy and valuable insights on the implementation, uptake, and overall acceptability of this multi-channel digital care package.

Conclusions:

This study will provide initial data on the efficacy of the ‘AF support’ program comprising a pre-programmed set of digital visits and conversational AI in supporting integrated care for AF patients and improving their quality of life. Clinical Trial: ACTRN12621000174886