Development and Evaluation of a Mobile Personalized Blood Glucose Prediction System for Patients With Gestational Diabetes Mellitus

Abstract

BackgroundPersonalized blood glucose (BG) prediction for diabetes patients is an important goal that is pursued by many researchers worldwide. Despite many proposals, only a few projects are dedicated to the development of complete recommender system infrastructures that incorporate BG prediction algorithms for diabetes patients. The development and implementation of such a system aided by mobile technology is of particular interest to patients with gestational diabetes mellitus (GDM), especially considering the significant importance of quickly achieving adequate BG control for these patients in a short period (ie, during pregnancy) and a typically higher acceptance rate for mobile health (mHealth) solutions for short- to midterm usage.ObjectiveThis study was conducted with the objective of developing infrastructure comprising data processing algorithms, BG prediction models, and an appropriate mobile app for patients’ electronic record management to guide BG prediction-based personalized recommendations for patients with GDM.MethodsA mobile app for electronic diary management was developed along with data exchange and continuous BG signal processing software. Both components were coupled to obtain the necessary data for use in the personalized BG prediction system. Necessary data on meals, BG measurements, and other events were collected via the implemented mobile app and continuous glucose monitoring (CGM) system processing software. These data were used to tune and evaluate the BG prediction model, which included an algorithm for dynamic coefficients tuning. In the clinical study, 62 participants (GDM: n=49; control: n=13) took part in a 1-week monitoring trial during which they used the mobile app to track their meals and self-measurements of BG and CGM system for continuous BG monitoring. The data on 909 food intakes and corresponding postprandial BG curves as well as the set of patients’ characteristics (eg, glycated hemoglobin, body mass index [BMI], age, and lifestyle parameters) were selected as inputs for the BG prediction models.ResultsThe prediction results by the models for BG levels 1 hour after food intake were root mean square error=0.87 mmol/L, mean absolute error=0.69 mmol/L, and mean absolute percentage error=12.8%, which correspond to an adequate prediction accuracy for BG control decisions.ConclusionsThe mobile app for the collection and processing of relevant data, appropriate software for CGM system signals processing, and BG prediction models were developed for a recommender system. The developed system may help improve BG control in patients with GDM; this will be the subject of evaluation in a subsequent study.

Effects of continuous care for patients with type 2 diabetes using mobile health application: A randomised controlled trial

“…The use of mobile health application system can promote the knowledge of self-monitoring of blood sugar, eating habits report, blood sugar control, and monitoring frequency and accuracy, so as to gradually improve patients' self-care ability. 24 In a previous study, a continuous application-based nursing approach significantly improved patients' overall self-care abilities. 25 It has also been reported that advantages of the application for continuous care include expansion of health education, provision of more options to the patient, and shortened intervals of intervention time between doctors and patients.…”

“…As reported previously, with the improvement of self‐management ability, the accuracy of self‐monitoring of blood glucose, the self‐reporting of eating habits, and blood sugar control are gradually improved. The use of mobile health application system can promote the knowledge of self‐monitoring of blood sugar, eating habits report, blood sugar control, and monitoring frequency and accuracy, so as to gradually improve patients' self‐care ability . In a previous study, a continuous application‐based nursing approach significantly improved patients' overall self‐care abilities .…”

“…Previous studies have shown a positive correlation between awareness levels and compliance among patients with diabetes; good disease awareness can improve a patient's treatment compliance, thus facilitating the patient's treatment . One study showed that the extended nursing model, based on applications, could effectively improve a patients' cognition of their own disease . Continuous care for patients with type 2 diabetes using mobile health application could provide diversified health education, stable follow‐up systems, and professional medical and resource supports, leading to improvements in patient cognition and improved self‐management …”

The Role of Glycemic Index and Glycemic Load in the Development of Real-Time Postprandial Glycemic Response Prediction Models for Patients with Gestational Diabetes

“…Neither of them assessed the effectiveness of PPGR prediction in GDM patients. We have developed a recommender system infrastructure that incorporates BG prediction models for GDM patients [13]. It is expected that integration of such models into an interactive mobile app will lead to the creation of personal recommendations for nutrition in real time to prevent hyperglycemia in patients with GDM.…”

“…We have developed algorithms for predicting the following PPGR parameters: BG 60 min after the start of food intake (BG60), peak BG value after food intake (BGMax), area under the glycemic curve 1 (AUC60) and 2 h (AUC120) after the start of the meal and peak BG, and incremental area under the glycemic curve 2 h after food intake (iAUC120) [13]. The accuracy of predicting the AUC60 and AUC120 was adequate, but the model for predicting BG60 was not accurate enough.…”