Ravi Reddy1, Navid Resalat1, Leah M Wilson2, Jessica R Castle2, Joseph El Youssef1,2, Peter G Jacobs1. 1. 1 Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR, USA. 2. 2 Department of Medicine, Division of Endocrinology, Harold Schnitzer Diabetes Health Center Oregon, Health & Science University, Portland, OR, USA.
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.
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.
Entities:
Keywords:
artificial pancreas; exercise; hypoglycemia; machine learning; type 1 diabetes
Authors: Peter G Jacobs; Navid Resalat; Joseph El Youssef; Ravi Reddy; Deborah Branigan; Nicholas Preiser; John Condon; Jessica Castle Journal: J Diabetes Sci Technol Date: 2015-10-05
Authors: Mark D DeBoer; Daniel R Cherñavvsky; Katarina Topchyan; Boris P Kovatchev; Gary L Francis; Marc D Breton Journal: Pediatr Diabetes Date: 2016-10-13 Impact factor: 4.866
Authors: Heidi Tikkanen-Dolenc; Johan Wadén; Carol Forsblom; Valma Harjutsalo; Lena M Thorn; Markku Saraheimo; Nina Elonen; Milla Rosengård-Bärlund; Daniel Gordin; Heikki O Tikkanen; Per-Henrik Groop Journal: Diabetologia Date: 2016-12-24 Impact factor: 10.122
Authors: Marc D Breton; Sue A Brown; Colleen Hughes Karvetski; Laura Kollar; Katarina A Topchyan; Stacey M Anderson; Boris P Kovatchev Journal: Diabetes Technol Ther Date: 2014-04-04 Impact factor: 6.118
Authors: S Franc; A Daoudi; A Pochat; M-H Petit; C Randazzo; C Petit; M Duclos; A Penfornis; E Pussard; D Not; E Heyman; F Koukoui; C Simon; G Charpentier Journal: Diabetes Obes Metab Date: 2015-10-08 Impact factor: 6.577
Authors: Elena Daskalaki; Anne Parkinson; Nicola Brew-Sam; Md Zakir Hossain; David O'Neal; Christopher J Nolan; Hanna Suominen Journal: J Med Internet Res Date: 2022-04-08 Impact factor: 7.076
Authors: Omar Diouri; Monika Cigler; Martina Vettoretti; Julia K Mader; Pratik Choudhary; Eric Renard Journal: Diabetes Metab Res Rev Date: 2021-03-24 Impact factor: 4.876