Combining Information of Autonomic Modulation and CGM Measurements Enables Prediction and Improves Detection of Spontaneous Hypoglycemic Events

Abstract

Were it not for the risk of hypoglycemic episodes, patients with diabetes could have normal glucose levels over a lifetime of diabetes. Hypoglycemia often results in an increase physical as well as psychosocial morbidity, and is a risk factor for an increased mortality.1,2 Hypoglycemia is very common in patients with type 1 diabetes (T1D).3 Patients trying to improve or maintain a tight glycemic control suffer from innumerable episodes of asymptomatic hypoglycemia. Plasma glucose levels may be less than 60 mg/dl (3.3 mmol/l) 10% of the time, and on average, patients with T1D suffer from 2 weekly incidents of symptomatic hypoglycemia. 1,4,5 Accordingly, patients with diabetes experience thousands of hypoglycemic events over a lifetime. In addition, these patients have a 4.7-fold excess mortality risk compared to healthy subjects. 6 This explains why there is a considerable interest in using continuous glucose monitoring (CGM) devices to detect and warn diabetic patients about an Background: We have previously tested, in a laboratory setting, a novel algorithm that enables prediction of hypoglycemia. The algorithm integrates information of autonomic modulation, based on heart rate variability (HRV), and data based on a continuous glucose monitoring (CGM) device. Now, we investigate whether the algorithm is suitable for prediction of hypoglycemia and for improvement of hypoglycemic detection during normal daily activities.Methods: Twenty-one adults (13 men) with T1D prone to hypoglycemia were recruited and monitored with CGM and a Holter device while they performed normal daily activities. We used our developed algorithm (a pattern classification method) to predict spontaneous hypoglycemia based on CGM and HRV. We compared 3 different models; (i) a model containing raw data from the CGM device; (ii) a CGM* model containing data derived from the CGM device signal; and (iii) a CGM+HRV model-combining model (ii) with HRV data.Results: A total of 12 hypoglycemic events (glucose levels < 3.9 mmol/L, 70 mg/dL) and 237 euglycemic measurements were included. For a 20-minute prediction, model (i) resulted in a ROC AUC of 0.69. If a high sensitivity of 100% was chosen, the corresponding specificity was 69%. (ii) The CGM* model yielded a ROC AUC of 0.92 with a corresponding sensitivity of 100% and specificity of 71%. (iii) The CGM+HRV model yielded a ROC AUC of 0.96 with a corresponding sensitivity of 100% and specificity of 91%.Conclusions: Data shows that adding information of autonomic modulation to CGM measurements enables prediction and improves the detection of hypoglycemia.

Early Detection of Hypoglycemia in Type 1 Diabetes Using Heart Rate Variability Measured by a Wearable Device

“…We extend previously reported data on HRV responses to hypoglycemia (8)(9)(10) by showing that continuously derived HRV can be monitored by a wearable device in real-life situations. We also show that both patient-specific and situational factors modulate the effect of hypoglycemia on HRV profiles, which expands previous data on the impact of age and diabetes (duration) on HRV in general (11,12).…”

Use of Wearable Sensors and Biometric Variables in an Artificial Pancreas System

“…For a ten-minute prediction, the algorithm provided 79% sensitivity (true positive hypoglycemia rate) and 99% specificity (true negative hypoglycemia rate) for a total of 903 samples, detecting 16/16 hypoglycemic events with no false positives and a 22-min lead time compared to the CGM alone. In a follow-up study, researchers used this pattern-classification algorithm to predict hypoglycemia based on three different models: (i) a model containing raw CGM data; (ii) a model containing data derived from CGM signal; and (iii) a model containing data derived from CGM and HRV signals [8]. The algorithm was previously tested in a hospital setting where the subjects were bedridden and subjected to induced hypoglycemia, but in this study the twenty-one subjects were monitored while performing normal daily activities in order to predict spontaneous hypoglycemia.…”

Semantic representation and processing of hypoglycemic events derived from wearable sensor data

“…For this reason, alternative non-invasive techniques (i.e. not requiring the user to compromise her physical integrity) have been studied recently [7,31,3].…”