Morten H Jensen1,2, Claus Dethlefsen3, Peter Vestergaard1,4,5, Ole Hejlesen2. 1. Steno Diabetes Center North Denmark, Aalborg University Hospital, Denmark. 2. Department of Health Science and Technology, Aalborg University, Denmark. 3. Biostatistics, Novo Nordisk A/S, Aalborg East, Denmark. 4. Department of Clinical Medicine, Aalborg University Hospital, Denmark. 5. Department of Endocrinology, Aalborg University Hospital, Denmark.
Abstract
BACKGROUND: Intensive insulin therapy has documented benefits but may also come at the expense of a higher risk of hypoglycemia. Hypoglycemia is associated with higher all-cause mortality and nocturnal hypoglycemia has been associated with the sudden dead-in-bed syndrome. This proof-of-concept study sought to investigate if nocturnal hypoglycemia can be predicted. METHOD: Continuous glucose monitoring, meal, insulin, and demographics data from 463 people with type 1 diabetes were obtained from a clinical trial. A total of 4721 nights without or with hypoglycemia (429) were available including data from three consecutive days before the night. Thirty-two features were calculated based on these data. Data were split into 20% participants for evaluation and 80% for training. The optimal feature subset was found from forward selection of the 80% participants with linear discriminant analysis as basis for the classifier. RESULTS: The forward selection resulted in a feature subset of four features. The evaluation resulted in an area under the receiver operating characteristics curve (ROC-AUC) of 0.79 leading to a sensitivity and a specificity of, e.g., 75% and 70%. CONCLUSIONS: It was possible to predict nocturnal hypoglycemic episodes with a ROC-AUC of 0.79. A warning at bedtime about nocturnal hypoglycemia could be of great help for people with diabetes to enable preventive actions. Further development of the proposed algorithm is needed for implementation in everyday practice.
BACKGROUND: Intensive insulin therapy has documented benefits but may also come at the expense of a higher risk of hypoglycemia. Hypoglycemia is associated with higher all-cause mortality and nocturnal hypoglycemia has been associated with the sudden dead-in-bed syndrome. This proof-of-concept study sought to investigate if nocturnal hypoglycemia can be predicted. METHOD:Continuous glucose monitoring, meal, insulin, and demographics data from 463 people with type 1 diabetes were obtained from a clinical trial. A total of 4721 nights without or with hypoglycemia (429) were available including data from three consecutive days before the night. Thirty-two features were calculated based on these data. Data were split into 20% participants for evaluation and 80% for training. The optimal feature subset was found from forward selection of the 80% participants with linear discriminant analysis as basis for the classifier. RESULTS: The forward selection resulted in a feature subset of four features. The evaluation resulted in an area under the receiver operating characteristics curve (ROC-AUC) of 0.79 leading to a sensitivity and a specificity of, e.g., 75% and 70%. CONCLUSIONS: It was possible to predict nocturnal hypoglycemic episodes with a ROC-AUC of 0.79. A warning at bedtime about nocturnal hypoglycemia could be of great help for people with diabetes to enable preventive actions. Further development of the proposed algorithm is needed for implementation in everyday practice.
Authors: Sophia Zoungas; Anushka Patel; John Chalmers; Bastiaan E de Galan; Qiang Li; Laurent Billot; Mark Woodward; Toshiharu Ninomiya; Bruce Neal; Stephen MacMahon; Diederick E Grobbee; Andre Pascal Kengne; Michel Marre; Simon Heller Journal: N Engl J Med Date: 2010-10-07 Impact factor: 91.245
Authors: Anushka Patel; Stephen MacMahon; John Chalmers; Bruce Neal; Laurent Billot; Mark Woodward; Michel Marre; Mark Cooper; Paul Glasziou; Diederick Grobbee; Pavel Hamet; Stephen Harrap; Simon Heller; Lisheng Liu; Giuseppe Mancia; Carl Erik Mogensen; Changyu Pan; Neil Poulter; Anthony Rodgers; Bryan Williams; Severine Bompoint; Bastiaan E de Galan; Rohina Joshi; Florence Travert Journal: N Engl J Med Date: 2008-06-06 Impact factor: 91.245
Authors: Thomas A Peyser; Andrew K Balo; Bruce A Buckingham; Irl B Hirsch; Arturo Garcia Journal: Diabetes Technol Ther Date: 2017-12-11 Impact factor: 6.118
Authors: Carlo B Giorda; Alessandro Ozzello; Sandro Gentile; Alberto Aglialoro; Anna Chiambretti; Fabio Baccetti; Francesco M Gentile; Giuseppe Lucisano; Antonio Nicolucci; Maria Chiara Rossi Journal: Acta Diabetol Date: 2015-02-12 Impact factor: 4.280
Authors: Darrell M Wilson; Peter M Calhoun; David M Maahs; H Peter Chase; Laurel Messer; Bruce A Buckingham; Tandy Aye; Paula K Clinton; Irene Hramiak; Craig Kollman; Roy W Beck Journal: Diabetes Technol Ther Date: 2015-03-11 Impact factor: 6.118
Authors: Rose A Gubitosi-Klug; Barbara H Braffett; Neil H White; Robert S Sherwin; F John Service; John M Lachin; William V Tamborlane Journal: Diabetes Care Date: 2017-05-26 Impact factor: 19.112
Authors: Piotr Witkowski; Louis H Philipson; Dixon B Kaufman; Lloyd E Ratner; Marwan S Abouljoud; Melena D Bellin; John B Buse; Fouad Kandeel; Peter G Stock; David C Mulligan; James F Markmann; Tomasz Kozlowski; Kenneth A Andreoni; Rodolfo Alejandro; David A Baidal; Mark A Hardy; Amittha Wickrema; Raghavendra G Mirmira; John Fung; Yolanda T Becker; Michelle A Josephson; Piotr J Bachul; Jordan S Pyda; Michael Charlton; J Michael Millis; Jason L Gaglia; Robert J Stratta; Jonathan A Fridell; Silke V Niederhaus; Rachael C Forbes; Kumar Jayant; R Paul Robertson; Jon S Odorico; Marlon F Levy; Robert C Harland; Peter L Abrams; Oyedolamu K Olaitan; Raja Kandaswamy; Jason R Wellen; Anthony J Japour; Chirag S Desai; Bashoo Naziruddin; Appakalai N Balamurugan; Rolf N Barth; Camillo Ricordi Journal: Am J Transplant Date: 2021-02-10 Impact factor: 8.086
Authors: Clara Mosquera-Lopez; Robert Dodier; Nichole S Tyler; Leah M Wilson; Joseph El Youssef; Jessica R Castle; Peter G Jacobs Journal: Diabetes Technol Ther Date: 2020-05-14 Impact factor: 6.118
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