LAUSR

Objectives Self-monitoring daily dietary intake is recommended for weight loss, weight maintenance, and healthy eating. However, current tracking methods are often burdensome and result in short-term use. We conducted a pilot study to evaluate the accuracy of a new application designed to self-monitor dietary intake using natural spoken language (COCO; The Conversational Calorie Counter). Methods A total of 14 participants were recruited for the pilot study. They were instructed to record daily dietary intake using the COCO application for at least five consecutive days. Two unscheduled 24-hour dietary recalls were conducted between day 3 and day 5 as the reference method for evaluating total energy intake (TEI). The two-day energy estimates were averaged for each assessment method. Pearson's correlation coefficient was used to assess the validity of the COCO application. Estimates of TEI from COCO were compared to the 24-hour dietary recall by a paired samples t-test. Results Participants were primarily female (86%), with an average body mass index of 22.2 ± 1.8 kg/m2 (mean ± standard deviation). On average, participants consumed three daily meals and recorded dietary intake for six days using the COCO application. The average TEI was 1782 ± 773 kcal for all recorded days (range: 4 to 10). The mean TEI measured by 24-hour dietary recall was 1791 ± 862 kcal, and mean TEI measured by COCO for the corresponding days was 1818 ± 916 kcal. We observed a significant correlation between the assessment methods (r = 0.58; P = 0.03), and there was no significant difference in TEI estimates from COCO compared to the 24-hour recall (P = 0.90). Conclusions These results suggest that natural spoken language technology can be used in applications that facilitate self-monitoring of food intake to support weight management and the prevention of noncommunicable diseases. The significant correlation between estimates of TEI from COCO and the 24-hour dietary recall indicates the potential validity of this novel approach for capturing dietary data and assessing energy intake. Funding Sources Sponsored by the National Institutes of Health (R21HL118347), the U.S. Department of Agriculture with Tufts University (58-1950-4-003), Quanta Computing, Inc., and the Department of Defense (National Defense Science Engineering Graduate Fellowship Program).