Digital Solutions to Diagnose and Manage Postbariatric Hypoglycemia

Abstract

Postbariatric hypoglycemia (PBH) is an increasingly recognized late metabolic complication of bariatric surgery, characterized by low blood glucose levels 1-3 h after a meal, particularly if the meal contains rapid-acting carbohydrates. PBH can often be effectively managed through appropriate nutritional measures, which remain the cornerstone treatment today. However, their implementation in daily life continues to challenge both patients and health care providers. Emerging digital technologies may allow for more informed and improved decision-making through better access to relevant data to manage glucose levels in PBH. Examples include applications for automated food analysis from meal images, digital receipts of purchased food items or integrated platforms allowing the connection of continuously measured glucose with food and other health-related data. The resulting multi-dimensional data can be processed with artificial intelligence systems to develop prediction algorithms and decision support systems with the aim of improving glucose control, safety, and quality of life of PBH patients. Digital innovations, however, face trade-offs between user burden vs. amount and quality of data. Further challenges to their development are regulatory non-compliance regarding data ownership of the platforms acquiring the required data, as well as user privacy concerns and compliance with regulatory requirements. Through navigating these trade-offs, digital solutions could significantly contribute to improving the management of PBH.

Keywords: Roux-en-Y gastric bypass; bariatric surgery; decision support systems; diet records; dumping syndromes; mobile applications; postbariatric hypoglycemia; postprandial hypoglycemia.

Figure 1

Origin of postbariatric hypoglycemia. Interaction between dietary intake and hypoglycemic events in patients with postbariatric hypoglycemia (left) and a section from a CGM profile showing postprandial hypoglycemia followed by rebound hypoglycemia caused by the correction of the primary hypoglycemia (right).

Figure 2

Technical flow of the SNAQ app. The app automatically segments pictures of meals into meal components and recognizes the food of the components. If the picture is taken with a depth-sensing camera of newer smartphones, it creates a depth map to estimate the volume of each meal component. From the volume and the food recognition, it can calculate the weight of each meal component. By using a food composition database, the macronutrient composition of the meal is calculated and displayed to the user with the corresponding CGM data. Screenshots kindly provided by SNAQ.

Figure 3

Output of image-based automated food assessment and corresponding glucose profiles. The SNAQ app allows for automated analysis of meal macronutrients from photographed meals. Pairing with a continuous glucose monitor combines the meal information with the corresponding postprandial glucose profile.

Figure 4

Mobile application using digital receipts to optimize diet. The app screenshots provide insights into the functionalities of the app: daily overall nutritional value of purchased food (e.g., using the Nutri-Score) (left); food categories for individualized goal setting (center); food recommendations based on individual food purchase history and goal setting. The app currently exists only in German.

Figure 5

Digital platform for multi-level data integration. The platform gathers data from multiple sources, such as manual input, continuous glucose monitoring sensors and health data from smartwatches. Custom algorithms and personalized data visualization (e.g., blinding data for specific classes of patients) allow for tailoring the functionalities to individual needs. The dashboard allows the healthcare professional to monitor data acquisition in real time and optimize treatment.

Figure 6

Browser dashboard summary view. The browser dashboard for the healthcare professional provides an overview of patient characteristics, settings for data collection, data view and notifications. It further displays summary statistics of continuous glucose monitoring data.

Figure 7

Browser dashboard daily view. The browser dashboard further allows for day-by-day review of glucose trajectories that are displayed in combination with other types of data collected such as self-measured blood glucose (SMBG), step counts from activity trackers, and physical activity logs and meal logs entered by the user.

Figure 8

Ambulatory glucose profile. The dashboard includes a standardized visual report once the software has sufficient numbers of days of data collection. It shows a median glucose control line; the 25th−75th percentiles, which represents 50% of the glucose readings over the analysis time period; and the 5th−95th percentiles, which helps identifying outliers that are contributing to the median results.