ISSN 1470-3947 (print) | ISSN 1479-6848 (online)

Endocrine Abstracts (2019) 63 P527 | DOI: 10.1530/endoabs.63.P527

Artificial intelligence for the remote evaluation of gestational diabetes using a smartphone application (Sinedie[Copy]): Study design.

Lara Albert1, David Subías1, Laia Casamitjana1, Isabel Mazarico1, Estefanía Caballero-Ruiz2, Gema García-Sáez2, Pablo Martín-Redondo2, Elena Hernando2 & Mercedes Rigla1

1Endocrinology and Nutrition Department, Parc Taulí Hospital Universitari, Institut d’Investigació i Innovació Parc Taulí I3PT, Universitat Autònoma de Barcelona, Sabadell, Spain; 2Bioengineering and Telemedicine Group, Centro de Tecnología Biomédica, ETSI de Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain.

Background: Gestational diabetes (GD) prevalence is increasing as the obesity epidemic continues. Its management involves hospital visits every 1–2 weeks. In 2016 our team developed a web-based telemedicine platform (SineDie©). This tool operated as a clinical decision support system designed to manage the treatment of patients with GD. SineDie© automatically prescribed diet recommendations and identified the necessity of insulin treatment. We realized a randomized clinical trial that showed a 27.4% reduction of the time devoted by clinicians to patients’ evaluation and the face-to-face visits per patient were reduced by 88.6%. The program detected all situations that required a therapy adjustment and all the generated recommendations were safe (Caballero-Ruiz E et al. Int J Med Inform 2017). Since today most people use smartphones and in order to enable the use of the tool, we have developed the mobile version. The aim of this communication is to present the app SineDie© and the ongoing clinical study design.

Methods: SineDie©app has been developed by the UPM bioengineering and telemedicine group and the Hospital Parc Taulí endocrinology department. The application can be installed in Android smartphones. SineDie©uses artificial intelligence to automatically classify and analyze the data, making therapy adjustment recommendations. The pregnant woman enters diet transgressions, exercise and ketonuria in the app. Blood glucose values are transferred from the glucometer (Accu-Check® Aviva Connect/Contour® next ONE) to the application with Bluetooth® connectivity. SineDie© analyzes the data introduced and, if necessary, makes dietary changes with an automatic notification to the patient. Recommendations regarding insulin treatment are notified through the professional version of the app SineDie© to the physicians, who decide to accept them or not. The system allows checking number of connections and the time spent for each user. The study, recently initiated, is a randomized trial 2:1 (SineDie© intervention versus standard care) that will include 84 patients. The goals are to evaluate the effectiveness and safety of the intervention and its impact in the professionals’ workload, as well as patients’ compliance and satisfaction.

Results and conclusions: The app SineDie© may be a good tool to prevent unnecessary hospital visits while keeping the best quality healthcare.