JMIR Publications

ABSTRACT

Background:

Patient education and self-management support are critical for atrial fibrillation (AF) management. Conversational artificial intelligence (AI) has the potential to provide interactive and personalised support but has not been evaluated in patients with AF.

Objective:

This study aimed to evaluate the feasibility of a conversational AI intervention to support patients with AF post-discharge.

Methods:

Single-blinded, 4:1-parallel-RCT with process evaluation of feasibility and engagement. The primary outcome was the change in Atrial Fibrillation Effect on QualiTy-of-life (AFEQT) questionnaire total score between groups. AF patients (18 years and older) were recruited post-discharge from Westmead Hospital (Sydney, Australia) cardiology services and randomised to receive either the intervention or usual care. The six-month intervention comprised of fully automated conversational AI phone calls (with speech recognition and natural language processing) that regularly assessed patient health and symptoms, and provided self-management support and education. These phone calls were supplemented with an online survey (sent via text message or email) containing replicated call content when participants could not be reached after three call attempts. If participant responses were concerning (e.g., poor overall health, low medication confidence, high symptom burden), they would be followed up with an ad hoc phone call and directed to clinical care if required. A semi-personalised online education website was also available as part of the intervention and participants were encouraged weekly (nudges delivered via text messages or emails) to visit it.

Results:

A total of 103 patients (mean age, 63.7 years [SD 11.2]; 70% male) were randomised (82 intervention); the target sample size was 385. The difference in the AFEQT total score was non-significant (adjusted mean difference 2.08, 95% CI: -7.79 to 11.96, p=0.464). An exploratory pre-post comparison demonstrated improvement in total AFEQT score in the intervention group (baseline: 70.3, 95% CI: 63.0 to 77.5; six months: 74.9, 95% CI: 64.4 to 85.5; p=0.337). Intervention satisfaction (88.4%) and engagement (average of 4.12 of 7 outreaches completed) were high.

Conclusions:

This proof-of-concept study demonstrates the feasibility of conversational AI in supporting patients with chronic conditions post-discharge. Intervention participants had improvement in their AF- quality of life, though the forced shortening of the evaluation was unable to demonstrate a significant difference between groups. Clinical Trial: Australian New Zealand Clinical Trials Registry [ACTRN12621000174886]; www.anzctr.org.au