Increased Glucose Variability During Long-Term Therapeutic Hypothermia as a Predictor of Poor Neurological Outcomes and Mortality: A Retrospective Study

Machine Learning-Based Time in Patterns for Blood Glucose Fluctuation Pattern Recognition in Type 1 Diabetes Management: Development and Validation Study

BACKGROUND

Continuous glucose monitoring (CGM) for diabetes combines noninvasive glucose biosensors, continuous monitoring, cloud computing, and analytics to connect and simulate a hospital setting in a person's home. CGM systems inspired analytics methods to measure glycemic variability (GV), but existing GV analytics methods disregard glucose trends and patterns; hence, they fail to capture entire temporal patterns and do not provide granular insights about glucose fluctuations.

OBJECTIVE

This study aimed to propose a machine learning-based framework for blood glucose fluctuation pattern recognition, which enables a more comprehensive representation of GV profiles that could present detailed fluctuation information, be easily understood by clinicians, and provide insights about patient groups based on time in blood fluctuation patterns.

METHODS

Overall, 1.5 million measurements from 126 patients in the United Kingdom with type 1 diabetes mellitus (T1DM) were collected, and prevalent blood fluctuation patterns were extracted using dynamic time warping. The patterns were further validated in 225 patients in the United States with T1DM. Hierarchical clustering was then applied on time in patterns to form 4 clusters of patients. Patient groups were compared using statistical analysis.

RESULTS

In total, 6 patterns depicting distinctive glucose levels and trends were identified and validated, based on which 4 GV profiles of patients with T1DM were found. They were significantly different in terms of glycemic statuses such as diabetes duration (P=.04), glycated hemoglobin level (P<.001), and time in range (P<.001) and thus had different management needs.

CONCLUSIONS

The proposed method can analytically extract existing blood fluctuation patterns from CGM data. Thus, time in patterns can capture a rich view of patients' GV profile. Its conceptual resemblance with time in range, along with rich blood fluctuation details, makes it more scalable, accessible, and informative to clinicians.

Continuous glucose monitoring during therapeutic hypothermia for hypoxic ischaemic encephalopathy: a feasibility study

OBJECTIVES

Glucose dysregulation is common in infants with hypoxic ischaemic encephalopathy (HIE) and is likely to exacerbate cerebral injury. Infrequent measurement of glucose concentrations makes both identification and prevention of this risk challenging. Continuous glucose monitoring (CGM) has the potential to address both these challenges, but has not been explored in these infants. We aimed to evaluate the feasibility and potential impact of real-time CGM in term infants with HIE being treated with therapeutic hypothermia (TH).

DESIGN

Feasibility study.

SETTING

Tertiary-level neonatal unit, UK.

PATIENTS

Term infants with HIE undergoing TH.

INTERVENTION

A CGM sensor was inserted within 48 hours of birth and kept in situ for the first week of life. Clinical staff were blinded to the CGM recordings and clinical decisions were based on blood glucose assays.

MAIN OUTCOME MEASURES

(1) Accuracy of CGM values during and post TH, (2) Per cent of time spent outside the clinical range (2.6-10 mmol/L), (3) Episodes of hypoglycaemia and hyperglycaemia, (4) Adverse effects.

RESULTS

The accuracy of CGM values during TH were comparable to those when infants were normothermic. There was wide variation in per cent time outside the target range (2.6-10 mmol/L) between infants (median 5%, range 0%-34%). CGM identified 44% of infants with ≥1 episode of hypoglycaemia (<2.6 mmol/L) and 50% with ≥1 episode of hyperglycaemia (>10 mmol/L). No adverse events were observed.

CONCLUSIONS

This study demonstrates that CGM could be a useful adjunct for glucose monitoring in babies undergoing TH who are at risk of both hypoglycaemia and hyperglycaemia.