Accuracy of Automatic Carbohydrate, Protein, Fat and Calorie Counting Based on Voice Descriptions of Meals in People with Type 1 Diabetes

Abstract

The aim of this work was to assess the accuracy of automatic macronutrient and calorie counting based on voice descriptions of meals provided by people with unstable type 1 diabetes using the developed expert system (VoiceDiab) in comparison with reference counting made by a dietitian, and to evaluate the impact of insulin doses recommended by a physician on glycemic control in the study’s participants. We also compared insulin doses calculated using the algorithm implemented in the VoiceDiab system. Meal descriptions were provided by 30 hospitalized patients (mean hemoglobin A1c of 8.4%, i.e., 68 mmol/mol). In 16 subjects, the physician determined insulin boluses based on the data provided by the system, and in 14 subjects, by data provided by the dietitian. On one hand, differences introduced by patients who subjectively described their meals compared to those introduced by the system that used the average characteristics of food products, although statistically significant, were low enough not to have a significant impact on insulin doses automatically calculated by the system. On the other hand, the glycemic control of patients was comparable regardless of whether the physician was using the system-estimated or the reference content of meals to determine insulin doses.

Agreement between an Image-Based Dietary Assessment Method and a Written Food Diary among Adolescents with Type 1 Diabetes

“…Novel automatic carbohydrate counting methods have already been developed; however, further research is needed to bring them into clinical practice [ 13 , 14 ]. Owing to the image-based method’s easiness and quickness, it could also benefit nutrition counselling among adolescents with T1D in general.…”

“…Using technology, such as smartphones and image-based methods, in dietary assessment could reduce the burden on adolescents and improve compliance with reporting their dietary habits [ 12 ]. Some image- or voice-based carbohydrate intake estimation methods have been developed among adults with diabetes; however, further development and validation of these are required [ 13 , 14 ].…”

Insulin in Type 1 and Type 2 Diabetes—Should the Dose of Insulin Before a Meal be Based on Glycemia or Meal Content?

“…There are some promising new applications of the emerging technologies in this field like the expert system using the automatic speech-to-text conversion, which is able to determine the caloricity, the content of carbohydrates, fat and protein in the meal in a fairly accurate way based on its voice description provided by the user. Such a system is an easy-to-use support tool in the type 1 diabetes treatment that makes it possible to improve the postprandial glycemic control [41,42]. This system can also be useful in people with type 2 diabetes to control the amount of food consumed or adjust insulin dosage.…”

Advancement in Dietary Assessment and Self-Monitoring Using Technology

“…Voice recordings can be used to add details to images which may often not be apparent and/or be used to collect information where an image of a food or drink maybe missed. An interesting study describes a voice operated app to determine the accuracy of automatic carbohydrate, protein, fat, and calorie counting based on the voice descriptions of meals in people with Type 1 Diabetes [20]. In 30 patients, insulin doses were estimated by a physician using dietary data obtained from VoiceDiab ( n = 16) and this was compared to dietary data provided by a dietitian ( n = 14).…”

“…In 30 patients, insulin doses were estimated by a physician using dietary data obtained from VoiceDiab ( n = 16) and this was compared to dietary data provided by a dietitian ( n = 14). No significant differences in insulin doses or glycaemic control were reported using either system [20].…”