Development of Machine Learning Models for the Identification of Elevated Ketone Bodies During Hyperglycemia in Patients with Type 1 Diabetes.

Aims: Diabetic ketoacidosis (DKA) is a serious life-threatening condition caused by a lack of insulin, which leads to elevated plasma glucose and metabolic acidosis. Early identification of developing DKA is important to start treatment and minimize complications and risk of death. The aim of the present study is to develop and test prediction model(s) that gives an alarm about their risk of developing elevated ketone bodies during hyperglycemia. Methods: We analyzed data from 138 type 1 diabetes patients with measurements of ketone bodies and continuous glucose monitoring (CGM) data from over 30,000 days of wear time. We utilized a supervised binary classification machine learning approach to identify elevated levels of ketone bodies (≥0.6 mmol/L). Data material was randomly divided at patient level in 70%/30% (training/test) dataset. Logistic regression (LR) and random forest (RF) classifier were compared. Results: Among included patients, 913 ketone samples were eligible for modeling, including 273 event samples with ketone levels ≥0.6 mmol/L. An area under the receiver operating characteristic curve from the RF classifier was 0.836 (confidence interval [CI] 90%, 0.783-0.886) and 0.710 (CI 90%, 0.646-0.77) for the LR classifier. Conclusions: The novel approach for identifying elevated ketone levels in patients with type 1 diabetes utilized in this study indicates that CGM could be a valuable resource for the early prediction of patients at risk of developing DKA. Future studies are needed to validate the results.

Development and Validation of a Machine Learning Model to Predict Weekly Risk of Hypoglycemia in Patients with Type 1 Diabetes Based on Continuous Glucose Monitoring.

Aim: The aim of this study was to develop and validate a prediction model based on continuous glucose monitoring (CGM) data to identify a week-to-week risk profile of excessive hypoglycemia. Methods: We analyzed, trained, and internally tested two prediction models using CGM data from 205 type 1 diabetes patients with long-term CGM monitoring. A binary classification approach (XGBoost) combined with feature engineering deployed on the CGM signals was utilized to predict excessive hypoglycemia risk defined by two targets (time below range [TBR] >4% and the upper TBR 90th percentile limit) of TBR the following week. The models were validated in two independent cohorts with a total of 253 additional patients. Results: A total of 61,470 weeks of CGM data were included in the analysis. The XGBoost models had an area under the receiver operating characteristic curve (ROC-AUC) of 0.83-0.87 (95% confidence interval; 0.83-0.88) in the test dataset. The external validation showed ROC-AUCs of 0.81-0.90. The most discriminative features included the low blood glucose index, the glycemic risk assessment diabetes equation (GRADE), hypoglycemia, the TBR, waveform length, the coefficient of variation and mean glucose during the previous week. This highlights that the pattern of hypoglycemia combined with glucose variability during the past week contains information on the risk of future hypoglycemia. Conclusion: Prediction models based on real-world CGM data can be used to predict the risk of hypoglycemia in the forthcoming week. The models showed good performance in both the internal and external validation cohorts.

A novel approach for predicting acute hospitalizations among elderly recipients of home care? A model development study.

BACKGROUND: Frail elderly are at high risk of hospitalizations and have a complex pattern of risk factors that makes it hard to foresee potential needs for additional treatment and care. Machine learning algorithms are potentially well-suited to discover hidden patterns in registrations that are routinely made across sectors. OBJECTIVE: To investigate predictors and performance of machine learning algorithms designed to predict acute hospitalizations in elderly recipients of home care services. MATERIALS AND METHODS: A development study based on a retrospective social sector cohort with 1,282 participants was designed. Included subjects were aged 65 or older and received home care services in Aalborg Municipality at least once a week from 1/1-2016 to 31/12-2017. Data were collected from a newly developed triage tool in combination with administrative and clinical data routinely collected in the Danish healthcare and social care sector. 857 predictors were tested and evaluated based on the area under the precision-recall curve (PR-AUC). The data was divided into a 70/30 training and test split with 5-fold cross-validation. A sliding window approach combining random under-sampling with a boosting algorithm (RUSBoost) was applied with a standard logistic regression included for comparison. RESULTS: The logistic regression achieved a PR-AUC of 0.01 (CI 0.00; 0.01) while the PR-AUC was 0.71 (CI 0.56; 0.76) for the RUSBoost algorithm. Four of the five most important citizen-level features used to accurately predict an acute hospitalization was the total number of services provided by the municipality to the citizen, the number of personal care registrations as well as number of medication handlings and nutritional registrations. A final important predictor was the number of physical complaints derived from the triage tool. CONCLUSIONS: Municipalities routinely collect valuable administrative and clinical data that can be used for early prediction of acute hospitalizations. However, future studies are needed to validate the results.

Effect of 12-week continuous positive airway pressure therapy on glucose levels assessed by continuous glucose monitoring in people with type 2 diabetes and obstructive sleep apnoea; a randomized controlled trial.

Aim: Obstructive sleep apnoea (OSA) is frequent in type 2 diabetes (T2D). The aim was to investigate the effect of a 12-week treatment with continuous positive airway pressure (CPAP) on glycaemic control assessed by continuous glucose monitoring (CGM), HbA1c and fasting blood glucose in patients with T2D and newly detected OSA. Methods: In a randomized controlled multicentre study, 72 participants with T2D and moderate to severe OSA (78% male, age 62 ± 7, AHI 35 ± 15) were recruited from outpatient clinics in three Danish hospitals and were randomized to CPAP intervention or control. The main outcome was glycaemic control assessed by 6 days CGM at baseline and after 12-week therapy, as well as by HbA1c and fasting blood glucose. Results: No significant changes were found in average glucose levels, time in glucose range, time with hypoglycaemia, time with hyperglycaemia or coefficient of variability. HbA1c decreased 0.7 mmol/mol (0.07%; P = .8) in the CPAP group and increased 0.8 mmol/mol (0.08%; P = .6) in the control group (intergroup difference, P = .6). Fasting blood glucose increased by 0.2 mmol/L (P = .02) in the CPAP group and by 0.4 mmol/L (P = .01) in the control group (intergroup difference, P = .7). In a prespecified subgroup analysis comparing participants with high adherence (minimum usage of four hours/night for 70% of all nights) to CPAP to the control group, no significant changes were observed either, although these participants had a tendency towards better glycaemic indices. Conclusions: CPAP treatment for 12 weeks does not significantly change glycaemic control in patients with type 2 diabetes and OSA.

Proof of Concept HTML5 Webapp: Type 2 Diabetes risk stratification.

Proof of concept HTML5 webapp for use in a diabetes screening context is presented.

Glycemic variability is associated with reduced cardiac autonomic modulation in women with type 2 diabetes.

OBJECTIVE: To investigate the sex differences in cardiac autonomic modulation in patients with newly diagnosed type 2 diabetes and to determine whether cardiac autonomic modulation is associated with glycemic variability. RESEARCH DESIGN AND METHODS: We investigated a cohort consisting of 48 men and 39 women with non-insulin-treated type 2 diabetes and a known duration of diabetes <5 years. All patients were equipped with a continuous glucose monitoring sensor for 3 days, and the mean amplitude of glycemic excursions (MAGE) was calculated to obtain individual glycemic variability. Cardiac autonomic modulation was quantified by analysis of heart rate variability (HRV) in time and frequency domains and during cardiovascular reflex tests (response to standing [RS], deep breathing [expiration-inspiration], and Valsalva maneuver). RESULTS: Sex differences in age- and heart rate-adjusted HRV measures were observed in both active and passive tests. Low frequency (LF; P = 0.036), LF/high frequency (HF; P < 0.001), and RS (P = 0.006) were higher in men, whereas expiration-inspiration (P < 0.001), but not HF, was higher in women. In women, reduced cardiac autonomic modulation as assessed by the standard deviation of normal-to-normal intervals (P = 0.001), the root mean square of successive differences (P = 0.018), LF (P < 0.001), HF (P = 0.005), total power (P = 0.008), RS ratio (P = 0.027), and expiration-to-inspiration ratio (P = 0.006) was significantly associated with increased glycemic variability as assessed by MAGE. This was not the case in men. The association in women persisted in a multivariate regression analysis controlling for weight, mean heart rate, blood pressure (systolic), and triglycerides. CONCLUSIONS: In patients with newly diagnosed and well-controlled type 2 diabetes, increased glycemic variability was associated with reduced cardiac autonomic modulation in women but not in men.