Dataset Information

Prediction of Hypoglycemia During Aerobic Exercise in Adults With Type 1 Diabetes.

ABSTRACT: BACKGROUND:Fear of exercise related hypoglycemia is a major reason why people with type 1 diabetes (T1D) do not exercise. There is no validated prediction algorithm that can predict hypoglycemia at the start of aerobic exercise. METHODS:We have developed and evaluated two separate algorithms to predict hypoglycemia at the start of exercise. Model 1 is a decision tree and model 2 is a random forest model. Both models were trained using a meta-data set based on 154 observations of in-clinic aerobic exercise in 43 adults with T1D from 3 different studies that included participants using sensor augmented pump therapy, automated insulin delivery therapy, and automated insulin and glucagon therapy. Both models were validated using an entirely new validation data set with 90 exercise observations collected from 12 new adults with T1D. RESULTS:Model 1 identified two critical features predictive of hypoglycemia during exercise: heart rate and glucose at the start of exercise. If heart rate was greater than 121 bpm during the first 5 min of exercise and glucose at the start of exercise was less than 182 mg/dL, it predicted hypoglycemia with 79.55% accuracy. Model 2 achieved a higher accuracy of 86.7% using additional features and higher complexity. CONCLUSIONS:Models presented here can assist people with T1D to avoid exercise related hypoglycemia. The simple model 1 heuristic can be easily remembered (the 180/120 rule) and model 2 is more complex requiring computational resources, making it suitable for automated artificial pancreas or decision support systems.

SUBMITTER: Reddy R

PROVIDER: S-EPMC6955453 | biostudies-literature | 2019 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of Hypoglycemia During Aerobic Exercise in Adults With Type 1 Diabetes.

Reddy Ravi R Resalat Navid N Wilson Leah M LM Castle Jessica R JR El Youssef Joseph J Jacobs Peter G PG

Journal of diabetes science and technology 20190117 5

<h4>Background</h4>Fear of exercise related hypoglycemia is a major reason why people with type 1 diabetes (T1D) do not exercise. There is no validated prediction algorithm that can predict hypoglycemia at the start of aerobic exercise.<h4>Methods</h4>We have developed and evaluated two separate algorithms to predict hypoglycemia at the start of exercise. Model 1 is a decision tree and model 2 is a random forest model. Both models were trained using a meta-data set based on 154 observations of i ...[more]

PMID: 30650997

Similar Datasets

Project description:ImportanceIntensive glucose-lowering treatment among patients with non-insulin-requiring type 2 diabetes may increase the risk of hypoglycemia.ObjectivesTo estimate the prevalence of intensive treatment and the association between intensive treatment, clinical complexity, and incidence of severe hypoglycemia among adults with type 2 diabetes who are not using insulin.Design, setting, and participantsRetrospective analysis of administrative, pharmacy, and laboratory data from the OptumLabs Data Warehouse from January 1, 2001, through December 31, 2013. The study included nonpregnant adults 18 years or older with type 2 diabetes who achieved and maintained a hemoglobin A1c (HbA1c) level less than 7.0% without use of insulin and had no episodes of severe hypoglycemia or hyperglycemia in the prior 12 months.Main outcomes and measuresRisk-adjusted probability of intensive treatment and incident severe hypoglycemia, stratified by patient clinical complexity. Intensive treatment was defined as use of more glucose-lowering medications than recommended by practice guidelines at specific index HbA1c levels. Severe hypoglycemia was ascertained by ambulatory, emergency department, and hospital claims for hypoglycemia during the 2 years after the index HbA1c test. Patients were categorized as having high vs low clinical complexity if they were 75 years or older, had dementia or end-stage renal disease, or had 3 or more serious chronic conditions.ResultsOf 31 542 eligible patients (median age, 58 years; interquartile range, 51-65 years; 15 483 women [49.1%]; 18 188 white [57.7%]), 3910 (12.4%) had clinical complexity. The risk-adjusted probability of intensive treatment was 25.7% (95% CI, 25.1%-26.2%) in patients with low clinical complexity and 20.8% (95% CI, 19.4%-22.2%) in patients with high clinical complexity. In patients with low clinical complexity, the risk-adjusted probability of severe hypoglycemia during the subsequent 2 years was 1.02% (95% CI, 0.87%-1.17%) with standard treatment and 1.30% (95% CI, 0.98%-1.62%) with intensive treatment (absolute difference, 0.28%; 95% CI, -0.10% to 0.66%). In patients with high clinical complexity, intensive treatment significantly increased the risk-adjusted probability of severe hypoglycemia from 1.74% (95% CI, 1.28%-2.20%) with standard treatment to 3.04% (95% CI, 1.91%-4.18%) with intensive treatment (absolute difference, 1.30%; 95% CI, 0.10%-2.50%).Conclusions and relevanceMore than 20% of patients with type 2 diabetes received intensive treatment that may be unnecessary. Among patients with high clinical complexity, intensive treatment nearly doubles the risk of severe hypoglycemia.

Dataset Information

Prediction of Hypoglycemia During Aerobic Exercise in Adults With Type 1 Diabetes.

Publications

Prediction of Hypoglycemia During Aerobic Exercise in Adults With Type 1 Diabetes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets