Integrated care for pregnant women with Type one diabetes using wearable technology

Conference: BIBE 2019 - The Third International Conference on Biological Information and Biomedical Engineering
06/20/2019 - 06/22/2019 at Hangzhou, China

Proceedings: BIBE 2019

Pages: 5Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Adams, Dawn; Zheng, Huiru (Computer Science and Informatics, Ulster University, Jordanstown Campus, Northern Ireland, England)
Sinclair, Marlene; McCullough, Julie (Maternal, Foetal and Infant Research Centre, Faculty of Life and Health Sciences, Ulster University, England)
Murphy, Marie (Sport & Exercise Sciences Research Institute, Ulster University, England)

This paper presents a study into the use of wearable technologies by pregnant women with Type one diabetes (T1D). The World Health Organisation estimates the incidence of T1D globally to be more than 422 million. Wearable technologies can potentially improve decisions around self-management by providing regular feedback on physiological processes. Informed decisions and choices to support self-management of this condition during pregnancy, ultimately enhance pregnancy outcomes. The wearable technologies under consideration include the FreeStyle LibreTM interstitial glucose monitor, Fitbit activity tracker, and blood pressure monitoring for home use. In addition to these devices participants in this research area will be required to maintain a food diary. Physical activity (PA) is recommended during pregnancy to maintain normal blood pressure (BP), physical health and as a preventative measure against deep venous thromboembolism (DVT). Self-reporting of food intake is known to be problematic and is often underestimated. To facilitate assessment of portion sizes participants will be asked to use mobile phone cameras to visually record the type and quantity of food eaten. The collated data will be processed via statistical analysis and computational analysis before providing feedback using machine learning algorithms to inform decisions around the need for insulin or carbohydrate to maintain euglycaemia.