Exploring the usability of a chatbot-based conversational dietary assessment tool among cardiovascular patients

Yunjie Liu, W.F. (Mayra) Goevaerts, Nicole Tenbült-van Limpt, Hareld M.C. Kemps, Willem Johan Kop, Max V. Birk, Yuan Lu

Research output: Contribution to conferenceAbstractProfessional


Background: Dietary intervention in cardiac rehabilitation (CR) plays an integral role in health promotion and improving the quality of life for those with cardiovascular diseases (CVDs). Innovative techniques offer great potential to deliver cost-effective dietary modifications by providing dietary intake self-tracking and personalized advice. Nevertheless, the time-consuming inconvenience of manual food logging has led to the development of conversational agents that alleviate the tracking burden and promote self-reflection. However, the usability of nutrition chatbots among CVD patients has not yet been investigated in clinical practice.

Purpose: This study aimed to examine the usability of a chatbot-based dietary assessment tool among CVD patients in a prospective observational trial and discuss the preliminary results.

Methods: In the clinical trial, patients who are scheduled for or recently have undergone specific surgical procedures are selected for participation. Data collection starts one week before the intervention and continues until one year after discharge. Participants collect self-reported food intake data via the chatbot several times per day for a maximum of 4 non-consecutive days every other week. Quarterly assessments are scheduled to gather feedback on the use of the system. This paper focuses on the data collected in the first quarter of this trial. The usability was measured through chatbot usage and qualitative input through interviews.

Results: Participant recruitment started in December 2021. Thirteen out of sixteen participants (1 female and 15 males, mean_age=62.6) completed their first quarter of the trial. We included 1267 valid data entry points by evaluating the reported items and participants' self-perceived tracking accuracy. The average response rate is 87.83%, with the average self-perceived accuracy as 8.05. Although there's no significant difference in the time they spent reporting each meal (mean 110.79s, p>0.05), we observed a significant increase in the number of reported items for each meal (mean 3.79, p
Conclusion: The chatbot was found efficient to use with reasonable high learnability among participants. With insights into the usability issues and patients' expectations from the chatbot, we will conduct further research on developing personalized recommendations.
Original languageEnglish
Publication statusAccepted/In press - 2023


Dive into the research topics of 'Exploring the usability of a chatbot-based conversational dietary assessment tool among cardiovascular patients'. Together they form a unique fingerprint.

Cite this