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

Ravi Reddy, Navid Resalat, Leah M. Wilson, Jessica Castle, Joseph El Youssef, Peter Jacobs

Research output: Contribution to journalArticle

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.

Original languageEnglish (US)
JournalJournal of diabetes science and technology
DOIs
StatePublished - Jan 1 2019

Fingerprint

Medical problems
Type 1 Diabetes Mellitus
Hypoglycemia
Exercise
Heart Rate
Artificial Pancreas
Insulin
Glucose
Decision Trees
Glucagon
Fear
Therapeutics
Decision trees
Decision support systems
Metadata
Pumps
Sensors

Keywords

  • artificial pancreas
  • exercise
  • hypoglycemia
  • machine learning
  • type 1 diabetes

ASJC Scopus subject areas

  • Internal Medicine
  • Endocrinology, Diabetes and Metabolism
  • Bioengineering
  • Biomedical Engineering

Cite this

Prediction of Hypoglycemia During Aerobic Exercise in Adults With Type 1 Diabetes. / Reddy, Ravi; Resalat, Navid; Wilson, Leah M.; Castle, Jessica; El Youssef, Joseph; Jacobs, Peter.

In: Journal of diabetes science and technology, 01.01.2019.

Research output: Contribution to journalArticle

@article{25ab540f35f84e6ea5c4223259ae841d,
title = "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.",
keywords = "artificial pancreas, exercise, hypoglycemia, machine learning, type 1 diabetes",
author = "Ravi Reddy and Navid Resalat and Wilson, {Leah M.} and Jessica Castle and {El Youssef}, Joseph and Peter Jacobs",
year = "2019",
month = "1",
day = "1",
doi = "10.1177/1932296818823792",
language = "English (US)",
journal = "Journal of diabetes science and technology",
issn = "1932-2968",
publisher = "Diabetes Technology Society",

}

TY - JOUR

T1 - Prediction of Hypoglycemia During Aerobic Exercise in Adults With Type 1 Diabetes

AU - Reddy, Ravi

AU - Resalat, Navid

AU - Wilson, Leah M.

AU - Castle, Jessica

AU - El Youssef, Joseph

AU - Jacobs, Peter

PY - 2019/1/1

Y1 - 2019/1/1

N2 - 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.

AB - 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.

KW - artificial pancreas

KW - exercise

KW - hypoglycemia

KW - machine learning

KW - type 1 diabetes

UR - http://www.scopus.com/inward/record.url?scp=85060758839&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060758839&partnerID=8YFLogxK

U2 - 10.1177/1932296818823792

DO - 10.1177/1932296818823792

M3 - Article

AN - SCOPUS:85060758839

JO - Journal of diabetes science and technology

JF - Journal of diabetes science and technology

SN - 1932-2968

ER -