What question did this study set out to answer?

The study aims to evaluate the effectiveness of an automated chatbot using motivational interviewing principles in improving lifestyle behaviors among adults at risk of NCDs.

May 27, 2026npj Digital Medicine1 citationsOpen Access

Motivational interviewing chatbot improves lifestyle in primary healthcare settings in a pragmatic randomised controlled trial

CWClive Ho Yin WongEducation University of Hong Kong MWMabel Ngai Kiu WongEducation University of Hong Kong WHWai Kai HouDepartment of Health

Key Points

The study aims to evaluate the effectiveness of an automated chatbot using motivational interviewing principles in improving lifestyle behaviors among adults at risk of NCDs.
Pragmatic, open-label, multicentre randomized controlled trial across three Hong Kong PHC facilities.
Randomized 627 adults aged 45–75 with or at risk of hypertension or diabetes to receive either the chatbot intervention plus usual care or usual care alone for 12 weeks.
Modified intention-to-treat analysis was performed with 460 participants.
Intervention group showed significant improvements in physical activity (576 MET-min/week), fruit/vegetable intake (0.27 portions/day), and committed action (0.95 a.u.) at 12 weeks (all p<0.05).
Effects were larger among adherent participants and sustained at 9-month follow-up.
Hypertensive participants experienced a systolic blood pressure reduction of −5.03 mmHg.

Abstract

Non-communicable diseases (NCDs) impose escalating demands on community-based primary healthcare (PHC) systems globally. Motivational interviewing (MI) is effective but difficult to scale due to resource and training constraints. We conducted the first pragmatic trial evaluating whether an automated chatbot operationalising MI principles could improve lifestyle behaviours when integrated into routine PHC settings. This pragmatic, open-label, multicentre randomised controlled trial across three Hong Kong PHC facilities randomised 627 adults aged 45–75 with or at risk of hypertension or diabetes. Participants received either a 12-week automated MI chatbot intervention plus usual care or usual care alone. Modified intention-to-treat analysis (n = 460) showed significant improvements in the intervention group compared to usual care in physical activity (576 MET-min/week), fruit/vegetable intake (0.27 portions/day), and committed action (0.95 a.u.) at 12 weeks. Larger effects among adherent participants suggested a dose–response relationship. Exploratory subgroup analyses showed strong effects among participants with low baseline physical activity (537 MET-min/week) and systolic blood pressure reductions among hypertensive participants (−5.03 mmHg). Effects were sustained at 9-month follow-up. No serious adverse events were reported. This scalable MI chatbot offers a pragmatic approach to NCD prevention in resource-constrained settings. Trial registration: ClinicalTrials.gov, NCT05949320, registered 29 June 2023.

Ask AI

Helpful

Bookmark

View Full Paper