A Stacked Long Short-Term Memory Approach for Predictive Blood Glucose Monitoring in Women with Gestational Diabetes Mellitus

Abstract

Gestational diabetes mellitus (GDM) is a subtype of diabetes that develops during pregnancy. Managing blood glucose (BG) within the healthy physiological range can reduce clinical complications for women with gestational diabetes. The objectives of this study are to (1) develop benchmark glucose prediction models with long short-term memory (LSTM) recurrent neural network models using time-series data collected from the GDm-Health platform, (2) compare the prediction accuracy with published results, and (3) suggest an optimized clinical review schedule with the potential to reduce the overall number of blood tests for mothers with stable and within-range glucose measurements. A total of 190,396 BG readings from 1110 patients were used for model development, validation and testing under three different prediction schemes: 7 days of BG readings to predict the next 7 or 14 days and 14 days to predict 14 days. Our results show that the optimized BG schedule based on a 7-day observational window to predict the BG of the next 14 days achieved the accuracies of the root mean square error (RMSE) = 0.958 ± 0.007, 0.876 ± 0.003, 0.898 ± 0.003, 0.622 ± 0.003, 0.814 ± 0.009 and 0.845 ± 0.005 for the after-breakfast, after-lunch, after-dinner, before-breakfast, before-lunch and before-dinner predictions, respectively. This is the first machine learning study that suggested an optimized blood glucose monitoring frequency, which is 7 days to monitor the next 14 days based on the accuracy of blood glucose prediction. Moreover, the accuracy of our proposed model based on the fingerstick blood glucose test is on par with the prediction accuracies compared with the benchmark performance of one-hour prediction models using continuous glucose monitoring (CGM) readings. In conclusion, the stacked LSTM model is a promising approach for capturing the patterns in time-series data, resulting in accurate predictions of BG levels. Using a deep learning model with routine fingerstick glucose collection is a promising, predictable and low-cost solution for BG monitoring for women with gestational diabetes.

Keywords: clinical machine learning; gestational diabetes; medical informatics; patient monitoring; pregnancy care.

Figure 1

Flowchart of participants, data cleaning and model preparation.

Figure 2

Distribution of BG readings for 7-days-predict-14-days (in the order of AB, AL, AD, BB, BL, BD left to right and then the first to the second row), as an exemplar.

Figure 3

LSTM prediction performance comparisons: (a) RMSE results of 7-days-predict-7-days vs. 7-days-predict-14 days, (b) MAE results of 7-days-predict-7-days vs. 7-days-predict-14-days, (c) RMSE results of 7-days-predict-14-days vs. 14-days-predict-14-days and (d) MAE results of 7-days-predict-14-days vs. 14-days-predict-14-days.

Figure 4

Model development pipeline and the architecture of three-layer stacked LSTM.