Improving blood glucose level predictability using machine learning.
blood glucose predictability
supervised machine learning
type-1 diabetes
Journal
Diabetes/metabolism research and reviews
ISSN: 1520-7560
Titre abrégé: Diabetes Metab Res Rev
Pays: England
ID NLM: 100883450
Informations de publication
Date de publication:
11 2020
11 2020
Historique:
received:
15
09
2019
revised:
12
05
2020
accepted:
18
05
2020
pubmed:
24
5
2020
medline:
12
10
2021
entrez:
24
5
2020
Statut:
ppublish
Résumé
This study was designed to improve blood glucose level predictability and future hypoglycemic and hyperglycemic event alerts through a novel patient-specific supervised-machine-learning (SML) analysis of glucose level based on a continuous-glucose-monitoring system (CGM) that needs no human intervention, and minimises false-positive alerts. The CGM data over 7 to 50 non-consecutive days from 11 type-1 diabetic patients aged 18 to 39 with a mean HbA1C of 7.5% ± 1.2% were analysed using four SML models. The algorithm was constructed to choose the best-fit model for each patient. Several statistical parameters were calculated to aggregate the magnitudes of the prediction errors. The personalised solutions provided by the algorithm were effective in predicting glucose levels 30 minutes after the last measurement. The average root-mean-square-error was 20.48 mg/dL and the average absolute-mean-error was 15.36 mg/dL when the best-fit model was selected for each patient. Using the best-fit-model, the true-positive-hypoglycemia-prediction-rate was 64%, whereas the false-positive- rate was 4.0%, and the false-negative-rate was 0.015%. Similar results were found even when only CGM samples below 70 were considered. The true-positive-hyperglycemia-prediction-rate was 61%. State-of-the-art SML tools are effective in predicting the glucose level values of patients with type-1diabetes and notifying these patients of future hypoglycemic and hyperglycemic events, thus improving glycemic control. The algorithm can be used to improve the calculation of the basal insulin rate and bolus insulin, and suitable for a closed loop "artificial pancreas" system. The algorithm provides a personalised medical solution that can successfully identify the best-fit method for each patient.
Substances chimiques
Biomarkers
0
Blood Glucose
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
e3348Informations de copyright
© 2020 John Wiley & Sons Ltd.
Références
Colberg SR, Laan R, Dassau E, Kerr D. Physical activity and type 1 diabetes: time for a rewire? J Diabetes Sci Technol. 2015;9:609-618.
Pérez-Gandía C, Facchinetti A, Sparacino G, et al. A dynamic risk measure from continuous glucose monitoring data. Diabetes Technol Ther. 2011;13:843-852.
Magni P, Bellazzi R. A stochastic model to assess the variability of blood glucose time series in diabetic patients self-monitoring. IEEE Trans Biomed Eng. 2006;53:977-985.
Briegel T, Tresp V. A nonlinear state space model for the blood glucose metabolism of a diabetic (Ein Nichtlineares Zustandsraummodell Für Den Blutglukosemetabolismus Eines Diabetikers). At-Automatisierungstechnik Methoden Und Anwendungen Der Steuerungs-, Regelungs-Und Informationstechnik. 2002;50:228.
Gani A, Gribok AV, Lu Y, Ward WK, Vigersky RA, Reifman J. Universal glucose models for predicting subcutaneous glucose concentration in humans. IEEE Trans Inf Technol Biomed. 2010;14:157-165.
Gani A, Gribok AV, Rajaraman S, Ward WK, Reifman J. Predicting subcutaneous glucose concentration in humans: data-driven glucose modelling. IEEE Trans Biomed Eng. 2009;56:246-254.
Mhaskar HN, Pereverzyev SV, der Walt V, Maria D. A deep learning approach to diabetic blood glucose prediction. Front Appl Math Stat. 2017;3:14.
Lynch SM, Bequette BW, Estimation-based model predictive control of blood glucose in type I diabetics: a simulation study. Paper presented at: Proceedings of the IEEE 27th Annual Northeast Bioengineering Conference (Cat. No.01CH37201), 2001
Ozyetkin MM, Nath N, Tatlicioglu E, Dawson DM, A new robust nonlinear control algorithm for the regulation of blood glucose in diabetic patients. Paper presented at: IEEE International Conference on Control Applications, 2012
Wang Q, Molenaar P, Harsh S, et al. Personalised state-space modelling of glucose dynamics for type 1 diabetes using continuously monitored glucose, insulin dose, and meal intake: an extended Kalman filter approach. J Diabetes Sci Technol. 2014;8:2.
De Nicolao G, Magni L, Dalla Man C, Cobelli C, Modelling and Control of Diabetes: Towards the Artificial Pancreas. Paper presented at: Proceedings of the 18th World Congress of the International Federation of Automatic Control, 2011
Del Favero S, Place J, Kropff J, et al. Multicenter outpatient dinner/overnight reduction of hypoglycemia and increased time of glucose in target with a wearable artificial pancreas using modular model predictive control in adults with type 1 diabetes. Diabetes Obes Metab. 2015;17:468-476.
Cobelli C, Dalla Man C, Sparacino G, Magni L, De Nicolao G, Kovatchev B. Diabetes: models, signals, and control. IEEE Rev Biomed Eng. 2009;2:54-96.
Lunze K, Singh T, Walter M, Brendel MD, Leonhardt S. Blood glucose control algorithms for type 1 diabetic patients: a methodological review. Biomed Signal Process Control. 2013;8(2):107-119.
Patek SD, Breton MD, Chen Y, Solomon C, Kovatchev B. Linear quadratic Gaussian-based closed-loop control of type 1 diabetes. J Diabetes Sci Technol. 2007;1:6.
Turksoy K, Bayrak ES, Quinn L, Littlejohn E, Rollins D, Cinar A. Hypoglycemia early alarm systems based on multivariable models. Ind Eng Chem Res. 2013;52(35):12329-12336.
Yu X, Turksoy K, Rashid M, et al. Model-fusion-based online glucose concentration predictions in people with type 1 diabetes. Control Eng Pract. 2018;71:129-141.
Turksoy K, Quinn L, Littlejohn E, Cinar A. Multivariable adaptive identification and control for artificial pancreas systems. IEEE Trans Biomed Eng. 2014;6(3):883-891.
Pappada SM, Cameron BD, Rosman PM, et al. Neural network-based real-time prediction of glucose in patients with insulin-dependent diabetes. Diabetes Technol Ther. 2011;13(2):135-141.
Pérez-Gandía C, Facchinetti A, Sparacino G, et al. Artificial neural network algorithm for online glucose prediction from continuous glucose monitoring. Diabetes Technol Ther. 2010;12(1):81-88.
Bunescu R, Struble N, Marling C, Shubrook J, Schwartz F. Blood glucose level prediction using physiological models and support vector regression. Paper presented at: Machine learning and applications (ICMLA), 12th international conference on IEEE, 2013, pp. 135-140
Reymann MP, Dorschky E, Groh BH, Martindale C, Blank P, Eskofier BM. Blood glucose level prediction based on support vector regression using mobile platforms. Paper presented at: Engineering in medicine and biology society (EMBC), 2016 IEEE 38th Annual International Conference of the IEEE, 2016, pp. 2990-2993
Plis K, Bunescu RC, Marling C, Shubrook J, Schwartz F. A machine learning approach to predicting blood glucose levels for diabetes management. Paper presented at: AAAI Workshop: Modern Artificial Intelligence for Health Analytics, 2014, pp. 35-39
Kotsiantis SB, Zaharakis I, Pintelas P. Supervised machine learning: a review of classification techniques. Emerging Artif Intell Appl Comput Eng. 2007;160:3-24.
Vovk V. Kernel Ridge Regression. Empirical Inference. Springer; 2013:105-116.
Getoor L, Taskar B. Introduction to Statistical Relational Learning. Cambridge, Massachusetts: MIT Press; 2007.
Vapnik V. The Nature of Statistical Learning Theory. Springer Science & Business Media; 2013.
Clarke WL, Cox D, Gonder-Frederick AL, Carter W, Pohl SLA. Evaluating clinical accuracy of Systems for Self-Monitoring of blood glucose. Diabetes Care. 1987;10:662-668.
Paul SK, Samanta M. Predicting upcoming glucose levels in patients with type 1 diabetes using a generalised autoregressive conditional heteroscedasticity modelling approach. Int J Stat Med Res. 2015;4:188-198.
Patton AJ. Volatility forecast comparison using imperfect volatility proxies. J Econ. 2011;160:246-256.
Hyndman RJ, Koehler AB. Another look at measures of forecast accuracy. Int J Forecast. 2006;22:679-688.
Zisser H, Dassau E, Lee JJ, Harvey RA, Bevier W, Doyle FJ III. Clinical results of an automated artificial pancreas using technosphere inhaled insulin to mimic first-phase insulin secretion. J Diabetes Sci Technol. 2015;9:564-572.
Zisser H, Renard E, Kovatchev B, et al. Multicenter closed-loop insulin delivery study points to challenges for keeping blood glucose in a safe range by a control algorithm in adults and adolescents with type 1 diabetes from various sites. Diabetes Technol Ther. 2014;16:613-622.
Oron T, Farfel A, Muller I, et al. A remote monitoring system for artificial pancreas support is safe, reliable, and user friendly. Diabetes Technol Ther. 2014;16:699-705.
Dassau E, Cameron F, Lee H, et al. Real-time hypoglycemia prediction suite using continuous monitoring a safety net for the artificial pancreas. Diabetes Care. 2010;33:1249-1254.
Georga EI, Principe JC, Rizos EC, Fotiadis DI, Kernel-based adaptive learning improves accuracy of glucose predictive modelling in type 1 diabetes: a proof-of-concept study. Paper presented at: Conference Proceedings of IEEE Eng Med Biol Soc 2017; pp. 2765-2768