Forecasting of Glucose Levels and Hypoglycemic Events: Head-to-Head Comparison of Linear and Nonlinear Data-Driven Algorithms Based on Continuous Glucose Monitoring Data Only

Abstract

In type 1 diabetes management, the availability of algorithms capable of accurately forecasting future blood glucose (BG) concentrations and hypoglycemic episodes could enable proactive therapeutic actions, e.g., the consumption of carbohydrates to mitigate, or even avoid, an impending critical event. The only input of this kind of algorithm is often continuous glucose monitoring (CGM) sensor data, because other signals (such as injected insulin, ingested carbs, and physical activity) are frequently unavailable. Several predictive algorithms fed by CGM data only have been proposed in the literature, but they were assessed using datasets originated by different experimental protocols, making a comparison of their relative merits difficult. The aim of the present work was to perform a head-to-head comparison of thirty different linear and nonlinear predictive algorithms using the same dataset, given by 124 CGM traces collected over 10 days with the newest Dexcom G6 sensor available on the market and considering a 30-min prediction horizon. We considered the state-of-the art methods, investigating, in particular, linear black-box methods (autoregressive; autoregressive moving-average; and autoregressive integrated moving-average, ARIMA) and nonlinear machine-learning methods (support vector regression, SVR; regression random forest; feed-forward neural network, fNN; and long short-term memory neural network). For each method, the prediction accuracy and hypoglycemia detection capabilities were assessed using either population or individualized model parameters. As far as prediction accuracy is concerned, the results show that the best linear algorithm (individualized ARIMA) provides accuracy comparable to that of the best nonlinear algorithm (individualized fNN), with root mean square errors of 22.15 and 21.52 mg/dL, respectively. As far as hypoglycemia detection is concerned, the best linear algorithm (individualized ARIMA) provided precision = 64%, recall = 82%, and one false alarm/day, comparable to the best nonlinear technique (population SVR): precision = 63%, recall = 69%, and 0.5 false alarms/day. In general, the head-to-head comparison of the thirty algorithms fed by CGM data only made using a wide dataset shows that individualized linear models are more effective than population ones, while no significant advantages seem to emerge when employing nonlinear methodologies.

IoMT-Enabled Real-Time Blood Glucose Prediction With Deep Learning and Edge Computing

“…Although previous studies incorporated physiological measurements and daily activities as model input, such as carbohydrate intake [14], insulin injection [15], and exercise levels [26], prediction with CGM data only is a practical and valuable option in real-world scenarios [34]. On one hand, some physiological features require extra wearable devices (e.g., insulin pumps and wristbands) that are not widespread in T1D management systems [35] and would introduce artifact errors due to hardware issues, such as signal loss and drained battery.…”

Forecasting postbariatric hypoglycaemia in patients after Roux‐en‐Y gastric bypass using model‐based algorithms fed by continuous glucose monitoring data: A proof‐of‐concept study

“…Based on our previous work on the prediction of hypoglycaemia in T1D, 13 we considered the following three algorithms: an autoregressive model with recursive parameter estimation (AR1), 14 which represents a good example of consolidated adaptive method; an autoregressive integrated moving average (ARIMA) model, 13 which turned out to be the best linear predictor in T1D; and a feed‐forward neural network (NN), 15 as representative of non‐linear methodologies. These methods, besides being considered as state‐of‐art glucose predictive algorithms for T1D, were also shown to be the best performing for short‐term prediction when CGM data are the only available source of information 13 …”

“…For each raised PBH alarm, we counted: a true positive (TP) if a PBH event occurred in the following 45 min; a false positive (FP) if no PBH events occurred in the following 45 min. A false negative was counted when no alarms were generated despite the occurrence of a PBH event 13 . Based on TP, FP and false negative, the following aggregated metrics were calculated: precision (P), recall (R), F1 score (F1).…”

Sense and Learn: Recent Advances in Wearable Sensing and Machine Learning for Blood Glucose Monitoring and Trend-Detection

“…Their model provided early alarms with a 9.4% false rate at a sensitivity of 100%. Another recent study utilized CGM data to compare the 30 min prediction horizon performance of thirty linear and nonlinear algorithms ( Prendin et al, 2021 ). Individualized ARIMA was the best linear algorithm in terms of accuracy with an RMSE of 22.15 mg/dl and also in hypoglycemia detection with 64% precision and 82% recall.…”