Exploring the usability of a chatbot-based conversational dietary assessment tool among cardiovascular patients
Bibliographic record
Abstract
Abstract Funding Acknowledgements Type of funding sources: None. 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<0.05) and a significant decrease in time they spent reporting each item (mean 29.69s, p<0.01). Participants explained that while getting familiar with the chatbot, they found it increasingly easier to report more items if needed, and the self-reporting became less time-consuming. During the interview, the participants shared their enthusiasm about using the chatbot for food tracking and praised its simplicity and learnability. Meanwhile, they gave suggestions to improve the chatbot: 1) involving their partners when using the chatbot; 2) knowing the dietary behaviour of their peers; 3) receiving recognition with anonymous competitions. 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.030 | 0.082 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".