Prediction of Nocturnal Hypoglycemia in Adults with Type 1 Diabetes under Multiple Daily Injections Using Continuous Glucose Monitoring and Physical Activity Monitor

被引:48
作者
Bertachi, Arthur [1 ,2 ]
Vinals, Clara [3 ]
Biagi, Lyvia [1 ,2 ]
Contreras, Ivan [1 ]
Vehi, Josep [1 ,4 ]
Conget, Ignacio [3 ,4 ]
Gimenez, Marga [3 ,4 ]
机构
[1] Univ Girona, Inst Informat & Applicat, Girona 17003, Spain
[2] Fed Univ Technol Parana UTFPR, BR-85053525 Guarapuava, Brazil
[3] Hosp Clin Barcelona, Diabet Unit, Endocrinol & Nutr Dept, E-08036 Barcelona, Spain
[4] Ctr Invest Biomed Red Diabet & Enfermedades Metab, Barcelona 08036, Spain
关键词
artificial neural network; hypoglycemia; machine learning; support vector machine; type; 1; diabetes; multiple daily injections; continuous glucose monitoring; INSULIN PUMP THERAPY; GLYCEMIC CONTROL; CHILDREN; ADOLESCENTS; INTENSITY; IMPACT;
D O I
10.3390/s20061705
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
(1) Background: nocturnal hypoglycemia (NH) is one of the most challenging side effects of multiple doses of insulin (MDI) therapy in type 1 diabetes (T1D). This work aimed to investigate the feasibility of a machine-learning-based prediction model to anticipate NH in T1D patients on MDI. (2) Methods: ten T1D adults were studied during 12 weeks. Information regarding T1D management, continuous glucose monitoring (CGM), and from a physical activity tracker were obtained under free-living conditions at home. Supervised machine-learning algorithms were applied to the data, and prediction models were created to forecast the occurrence of NH. Individualized prediction models were generated using multilayer perceptron (MLP) and a support vector machine (SVM). (3) Results: population outcomes indicated that more than 70% of the NH may be avoided with the proposed methodology. The predictions performed by the SVM achieved the best population outcomes, with a sensitivity and specificity of 78.75% and 82.15%, respectively. (4) Conclusions: our study supports the feasibility of using ML techniques to address the prediction of nocturnal hypoglycemia in the daily life of patients with T1D on MDI, using CGM and a physical activity tracker.
引用
收藏
页数:11
相关论文
共 43 条
[1]   Hypoglycaemia, cardiovascular disease, and mortality in diabetes: epidemiology, pathogenesis, and management [J].
Amiel, Stephanie A. ;
Frier, Brian M. ;
Heller, Simon R. ;
McCrimmon, Rory J. ;
Khunti, Kamlesh ;
Aschner, Pablo ;
Childs, Belinda ;
Cryer, Philip E. ;
Gonder-Frederick, Linda ;
Seaquist, Elizabeth R. ;
de Galan, Bastiaan E. ;
Jones, Timothy ;
Zoungas, Sophia ;
Leiter, Lawrence A. ;
Luo, Yingying ;
Pedersen-Bjergaard, Ulrik .
LANCET DIABETES & ENDOCRINOLOGY, 2019, 7 (05) :385-396
[2]  
[Anonymous], 2017, ATTD 2017 10 INT C A
[3]  
[Anonymous], 2009, Neural networks and learning machines
[4]   Nocturnal Hypoglycemia and Physical Activity in Children With Diabetes: New Insights by Continuous Glucose Monitoring and Accelerometry [J].
Bachmann, Sara ;
Hess, Melanie ;
Martin-Diener, Eva ;
Denhaerynck, Kris ;
Zumsteg, Urs .
DIABETES CARE, 2016, 39 (07) :E95-E96
[5]   The use and efficacy of continuous glucose monitoring in type 1 diabetes treated with insulin pump therapy: a randomised controlled trial [J].
Battelino, T. ;
Conget, I. ;
Olsen, B. ;
Schuetz-Fuhrmann, I. ;
Hommel, E. ;
Hoogma, R. ;
Schierloh, U. ;
Sulli, N. ;
Bolinder, J. .
DIABETOLOGIA, 2012, 55 (12) :3155-3162
[6]   Sample size planning for classification models [J].
Beleites, Claudia ;
Neugebauer, Ute ;
Bocklitz, Thomas ;
Krafft, Christoph ;
Popp, Juergen .
ANALYTICA CHIMICA ACTA, 2013, 760 :25-33
[7]   A New Blood Glucose Control Scheme for Unannounced Exercise in Type 1 Diabetic Subjects [J].
Beneyto, Aleix ;
Bertachi, Arthur ;
Bondia, Jorge ;
Vehi, Josep .
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2020, 28 (02) :593-600
[8]   Novel glucose-sensing technology and hypoglycaemia in type 1 diabetes: a multicentre, non-masked, randomised controlled trial [J].
Bolinder, Jan ;
Antuna, Ramiro ;
Geelhoed-Duijvestijn, Petronella ;
Kroeger, Jens ;
Weitgasser, Raimund .
LANCET, 2016, 388 (10057) :2254-2263
[9]   Blood Glucose Level Prediction using Physiological Models and Support Vector Regression [J].
Bunescu, Razvan ;
Struble, Nigel ;
Marling, Cindy ;
Shubrook, Jay ;
Schwartz, Frank .
2013 12TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2013), VOL 1, 2013, :135-140
[10]   A Review of Predictive Low Glucose Suspend and Its Effectiveness in Preventing Nocturnal Hypoglycemia [J].
Chen, Ethan ;
King, Fraya ;
Kohn, Michael A. ;
Spanakis, Elias K. ;
Breton, Marc ;
Klonoff, David C. .
DIABETES TECHNOLOGY & THERAPEUTICS, 2019, 21 (10) :602-609