An AI-Based Module for Interstitial Glucose Forecasting enabling a "Do-It-Yourself" Application for People with Type 1 Diabetes

Antonio J. Rodríguez-Almeida^1*Guillermo V. Socorro Marrero¹Carmelo Betancort²Garlene Zamora-Zamorano³Alejandro Deniz²María L. Álvarez Malé³Eirik Årsand^4,5Cristina Soguero-Ruiz⁶Ana M. Wägner^2,3Conceiçao Granja^5,7Gustavo M. Callico¹Himar Fabelo^1,8,9*

• ¹Institute for Applied Microelectronics, University of Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Spain
• ²Endocrinology and Nutrition Department, Complejo Hospitalario Universitario Insular Materno-Infantil, Las Palmas de Gran Canaria, Spain
• ³Instituto de Investigaciones Biomédicas y Sanitarias, University of de Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Spain
• ⁴Department of Computer Science, University of Tromsø – The Arctic University of Norway, Tromsø, Norway
• ⁵Norwegian Centre for E-health Research, University Hospital of North-Norway, Tromsø, Norway
• ⁶Department of Theory of Signal and Communications and Telematic Systems and Computing, Rey Juan Carlos University, Madrid, Asturias, Spain
• ⁷Faculty of Nursing and Health Sciences, Nord University, Bodø, Nordland, Norway
• ⁸Fundación Canaria Instituto de Investigación Sanitaria de Canarias, FIISC, Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Spain
• ⁹Research Unit, University Hospital of Gran Canaria Dr. Negrin, Las Palmas de Gran Canaria, Spain

Diabetes mellitus (DM) is a chronic condition defined by increased blood glucose that affects more than 500 million adults. Type 1 diabetes (T1D) needs to be treated with insulin. Keeping glucose within the desired range is challenging. Despite the advances in the mHealth field, the appearance of the do-it-yourself (DIY) tools, and the progress in glucose level prediction based on deep learning (DL), these tools fail to engage the users in the long-term. This limits the benefits that they could have on the daily T1D self-management, specifically by providing an accurate prediction of their short-term glucose level. This work proposed a DL-based DIY framework for interstitial glucose prediction using continuous glucose monitoring (CGM) data to generate one personalized DL model per user, without using data from other people. The DIY module reads the CGM raw data (as it would be uploaded by the potential users of this tool), and automatically prepares them to train and validate a DL model to perform glucose predictions up to one hour ahead. For training and validation, one year of CGM data collected from 29 subjects with T1D were used. Results showed prediction performance comparable to the state-of-the-art, using only CGM data. To the best of our knowledge, this work is the first one in providing a DL-based DIY approach for fully personalized glucose prediction. Moreover, this framework is open source and has been deployed in Docker, enabling its standalone use, its integration on a smartphone application, or the experimentation with novel DL architectures.