JMIR Publications

ABSTRACT

Background:

Medical staff often conduct assessments, such as food intake and nutrient sufficiency ratios, to accurately evaluate patients’ food consumption. However, visual estimations to measure food intake are difficult to perform with numerous patients. Hence, the clinical environment requires a simple and accurate method to measure dietary intake.

Objective:

We aimed to develop a food intake estimation system via an artificial intelligence (AI) model to estimate leftover food. The accuracy of the AI’s estimation was compared with that of visual estimation for liquid foods served to hospitalized patients.

Methods:

The estimations were evaluated by a dietitian who looked at the food photo (image visual estimation) and visual measurement evaluation by a nurse who looked directly at the food (direct visual estimation) based on actual measurements. In total, 300 dishes of liquid food (100 dishes of thin rice gruel, 100 of vegetable soup, 31 of fermented milk, and 18, 12, 13, and 26 of peach, grape, orange, and mixed juices, respectively) were used. The root-mean-square error (RMSE) and coefficient of determination (R2) were used as metrics to determine the accuracy of the evaluation process. Corresponding t-tests and Spearman's rank correlation coefficients were used to verify the accuracy of the measurements via each estimation method with weighing method.

Results:

The RMSE obtained via the AI estimation approach was 8.12 for energy. This tended to be smaller and larger than that obtained via the image visual estimation approach (8.49) and direct visual estimation approach (4.34), respectively. Additionally, the coefficient of determination (R2) tended to be larger and smaller for the AI estimation than for the image and direct visual estimations, respectively. There was no difference between the AI estimation (71.7±23.9 kcal, p=.817) and actual values with weighing method. However, the mean nutrient intake from the image visual estimation (75.5±23.2 kcal, p <.001) and direct visual estimation (73.1±26.4 kcal, p =.007) were significantly different from the actual values. Spearman's rank correlation coefficients were high for energy (ρ=0.89–0.97), protein (ρ=0.94–0.97), fat (ρ=0.91–0.94) and carbohydrate (ρ=0.89–0.97).

Conclusions:

The measurement from the food intake estimation system via an AI-based model to estimate leftover liquid food intake in patients showed a high correlation with the actual values with weighing method. Furthermore, it also showed a higher accuracy than the image visual estimation. The errors of the AI estimation method were within the acceptable range of the weighing method, which indicated that the AI-based food intake estimation system could be applied in clinical environments. However, its lower accuracy than the direct visual estimation was still an issue.