摘要：Video observations have been widely used for providing ground truth for wearable systems for monitoring food intake in controlled laboratory conditions; however, video observation requires participants be confined to a defined space. The purpose of this analysis was to test an alternative approach for establishing activity types and food intake bouts in a relatively unconstrained environment. The accuracy of a wearable system for assessing food intake was compared with that from video observation, and inter-rater reliability of annotation was also evaluated. Forty participants were enrolled. Multiple participants were simultaneously monitored in a 4-bedroom apartment using six cameras for three days each. Participants could leave the apartment overnight and for short periods of time during the day, during which time monitoring did not take place. A wearable system (Automatic Ingestion Monitor, AIM) was used to detect and monitor participants’ food intake at a resolution of 30 s using a neural network classifier. Two different food intake detection models were tested, one trained on the data from an earlier study and the other on current study data using leave-one-out cross validation. Three trained human raters annotated the videos for major activities of daily living including eating, drinking, resting, walking, and talking. They further annotated individual bites and chewing bouts for each food intake bout. Results for inter-rater reliability showed that, for activity annotation, the raters achieved an average (±standard deviation (STD)) kappa value of 0.74 (±0.02) and for food intake annotation the average kappa (Light’s kappa) of 0.82 (±0.04). Validity results showed that AIM food intake detection matched human video-annotated food intake with a kappa of 0.77 (±0.10) and 0.78 (±0.12) for activity annotation and for food intake bout annotation, respectively. Results of one-way ANOVA suggest that there are no statistically significant differences among the average eating duration estimated from raters’ annotations and AIM predictions (p-value = 0.19). These results suggest that the AIM provides accuracy comparable to video observation and may be used to reliably detect food intake in multi-day observational studies.
