Blood glucose prediction model for type 1 diabetes based on artificial neural network with time-domain features

• Autorzy: Alfian Ganjar , Syafrudin Muhammad , Anshari Muhammad , Benes Filip , Atmaji Fransiskus Tatas Dwi , Fahrurrozi Imam , Hidayatullah Ahmad Fathan , Rhee Jongtae

Identyfikatory

DOI

10.1016/j.bbe.2020.10.004

• Języki publikacji: EN

Abstrakty

EN

Predicting future blood glucose (BG) levels for diabetic patients will help them avoid potentially critical health issues. We demonstrate the use of machine learning models to predict future blood glucose levels given a history of blood glucose values as the single input parameter. We propose an Artificial Neural Network (ANN) model with time-domain attributes to predict blood glucose levels 15, 30, 45 and 60 min in the future. Initially, the model's features are selected based on the previous 30 min of BG measurements before a trained model is generated for each patient. These features are combined with time-domain attributes to give additional inputs to the proposed ANN. The prediction model was tested on 12 patients with Type 1 diabetes (T1D) and the results were compared with other data-driven models including the Support Vector Regression (SVR), K-Nearest Neighbor (KNN), C4.5 Decision Tree (DT), Random Forest (RF), Adaptive Boosting (AdaBoost) and eXtreme Gradient Boosting (XGBoost) models. Our results show that the proposed BG prediction model that is based on an ANN outperformed all other models with an average Root Mean Square Error (RMSE) of 2.82, 6.31, 10.65 and 15.33 mg/dL for Prediction Horizons (PHs) of 15, 30, 45 and 60 min, respectively. Our testing showed that combining time-domain attributes into the input data resulted in enhanced performance of majority of prediction models. The implementation of proposed prediction model allows patients to obtain future blood glucose levels, so that the preventive alerts can be generated before critical hypoglycemic/ hyperglycemic events occur.

Słowa kluczowe

EN

type 1 diabetes; blood glucose; prediction model; artificial neural network; time domain features; machine learning

PL

cukrzyca typu 1; glikemia; model predykcyjny; sieć neuronowa sztuczna; uczenie maszynowe

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 4
• Strony: 1586--1599
• Opis fizyczny: Bibliogr. 73 poz., rys., tab., wykr.

Twórcy

autor

Alfian Ganjar

• Industrial Artificial Intelligence (AI) Research Center, Nano Information Technology Academy, Dongguk University, Seoul, Korea

autor

Syafrudin Muhammad

• Department of Industrial and Systems Engineering, Dongguk University, Seoul, Korea

autor

Anshari Muhammad

• School of Business & Economics, Universiti Brunei Darussalam, Gadong BE1410, Brunei

autor

Benes Filip

• Department of Economics and Control Systems, Faculty of Mining and Geology, VSB–Technical University of Ostrava, Czech Republic

autor

Atmaji Fransiskus Tatas Dwi

• Industrial and System Engineering School, Telkom University, Bandung, Indonesia

autor

Fahrurrozi Imam

• Departemen Teknik Elektro dan Informatika, Sekolah Vokasi, Universitas Gadjah Mada, Yogyakarta, Indonesia

autor

Hidayatullah Ahmad Fathan

• Department of Informatics, Universitas Islam Indonesia, Yogyakarta, Indonesia

autor

Rhee Jongtae

• Department of Industrial and Systems Engineering, Dongguk University, Seoul, Korea

Bibliografia

• [1] Association AD. Standards of medical care in diabetes-2009. Diabet Retin 2010;29(1):1–36. http://dx.doi.org/10.1142/9789814304443_0001.
• [2] Association AD. Introduction: Standards of medical care in Diabetesd 2018. Diabetes Care 2018;41:S1–2. http://dx.doi.org/10.2337/dc18-SINT01.
• [3] Arboix A, Rivas A, García-Eroles L, de Marcos L, Massons J, Oliveres M. Cerebral infarction in diabetes: Clinical pattern, stroke subtypes, and predictors of in-hospital mortality. BMC Neurol 2005;5. http://dx.doi.org/10.1186/1471-2377-5-9.
• [4] Hankey GJ, Anderson NE, Ting RD, Veillard AS, Romo M, Wosik M, et al. Rates and predictors of risk of stroke and its subtypes in diabetes: a prospective observational study. J Neurol Neurosurg Psychiatry 2013;84:281–7. http://dx.doi.org/10.1136/jnnp-2012-303365.
• [5] Tun NN, Arunagirinathan G, Munshi SK, Pappachan JM. Diabetes mellitus and stroke: a clinical update. World J Diabetes 2017;8:235. http://dx.doi.org/10.4239/wjd.v8.i6.235.
• [6] Silverstein J, Klingensmith G, Copeland K, Plotnick L, Kaufman F, Laffel L, et al. Care of children and adolescents with type 1 diabetes: a statement of the American Diabetes Association. Diabetes Care 2005;28:186–212. http://dx.doi.org/10.2337/diacare.28.1.186.
• [7] Goldstein DE, Little RR, Lorenz RA, Malone JI, Nathan D, Peterson CM, et al. Tests of glycemia in diabetes. Diabetes Care 2004;27:1761–73. http://dx.doi.org/10.2337/diacare.27.7.1761.
• [8] Klein R, Klein BEK, Moss SE, Cruickshanks KJ. Relationship of hyperglycemia to the long-term incidence and progression of diabetic retinopathy. Arch Intern Med 1994;154:2169–78. http://dx.doi.org/10.1001/archinte.1994.00420190068008.
• [9] Mohamed S, Murray JC, Dagle JM, Colaizy T. Hyperglycemia as a risk factor for the development of retinopathy of prematurity. BMC Pediatr 2013;13:78. http://dx.doi.org/10.1186/1471-2431-13-78.
• [10] Schrijvers BF, De Vriese AS, Flyvbjerg A. From hyperglycemia to diabetic kidney disease: the role of metabolic, hemodynamic, intracellular factors and growth factors/cytokines. Endocr Rev 2004;25:971–1010. http://dx.doi.org/10.1210/er.2003-0018.
• [11] Alicic RZ, Rooney MT, Tuttle KR. Diabetic kidney disease: challenges, progress, and possibilities. Clin J Am Soc Nephrol 2017;12:2032–45. http://dx.doi.org/10.2215/CJN.11491116.
• [12] Selvin E, Marinopoulos S, Berkenblit G, Rami T, Brancati FL, Powe NR, et al. Meta-analysis: glycosylated hemoglobin and cardiovascular disease in diabetes mellitus. Ann Intern Med 2004;141:421. http://dx.doi.org/10.7326/0003-4819-141-6-200409210-00007.
• [13] Ormazabal V, Nair S, Elfeky O, Aguayo C, Salomon C, Zuñiga FA. Association between insulin resistance and the development of cardiovascular disease. Cardiovasc Diabetol 2018;17:122. http://dx.doi.org/10.1186/s12933-018-0762-4.
• [14] Turchin A, Matheny ME, Shubina M, Scanlon SV, Greenwood B, Pendergrass ML. Hypoglycemia and clinical outcomes in patients with diabetes hospitalized in the general ward. Diabetes Care 2009;32:1153–7. http://dx.doi.org/10.2337/dc08-2127.
• [15] Nirantharakumar K, Marshall T, Kennedy A, Narendran P, Hemming K, Coleman JJ. Hypoglycaemia is associated with increased length of stay and mortality in people with diabetes who are hospitalized. Diabet Med 2012;29:e445–8. http://dx.doi.org/10.1111/dme.12002.
• [16] Akirov A, Grossman A, Shochat T, Shimon I. Mortality among hospitalized patients with hypoglycemia: insulin related and noninsulin related. J Clin Endocrinol Metab 2017;102:416–24. http://dx.doi.org/10.1210/jc.2016-2653.
• [17] Benjamin EM. Self-monitoring of blood glucose: the basics. Clin Diabetes 2002;20:45–7. http://dx.doi.org/10.2337/diaclin.20.1.45.
• [18] Patton SR, Clements MA. Continuous Glucose Monitoring Versus Self-monitoring of Blood Glucose in Children with Type 1 Diabetes- Are there Pros and Cons for Both? US Endocrinol 2012;8:27–9.
• [19] Bruen D, Delaney C, Florea L, Diamond D. Glucose sensing for diabetes monitoring: recent developments. Sensors (Switzerland) 2017;17:1866. http://dx.doi.org/10.3390/s17081866.
• [20] Cappon G, Acciaroli G, Vettoretti M, Facchinetti A, Sparacino G. Wearable continuous glucose monitoring sensors: a revolution in diabetes treatment. Electron 2017;6:65. http://dx.doi.org/10.3390/electronics6030065.
• [21] Chen C, Zhao XL, Li ZH, Zhu ZG, Qian SH, Flewitt AJ. Current and emerging technology for continuous glucose monitoring. Sensors (Switzerland) 2017;17:182. http://dx.doi.org/10.3390/s17010182.
• [22] Marvicsin D, Jennings P, Ziegler-Bezaire D. What Is New in Diabetes Technology? J Nurse Pract 2017;13:205–9. http://dx.doi.org/10.1016/j.nurpra.2016.12.025.
• [23] Acciaroli G, Vettoretti M, Facchinetti A, Sparacino G. Calibration of minimally invasive continuous glucose monitoring sensors: state-of-the-art and current perspectives. Biosensors 2018;8:24. http://dx.doi.org/10.3390/bios8010024.
• [24] Olczuk D, Priefer R. A history of continuous glucose monitors (CGMs) in self-monitoring of diabetes mellitus. Diabetes Metab Syndr Clin Res Rev 2018;12:181–7. http://dx.doi.org/10.1016/j.dsx.2017.09.005.
• [25] Oviedo S, Vehí J, Calm R, Armengol J. A review of personalized blood glucose prediction strategies for T1DM patients. Int J Numer Method Biomed Eng 2017;33:e2833. http://dx.doi.org/10.1002/cnm.2833.
• [26] Woldaregay AZ, Årsand E, Walderhaug S, Albers D, Mamykina L, Botsis T, et al. Data-driven modeling and prediction of blood glucose dynamics: machine learning applications in type 1 diabetes. Artif Intell Med 2019;98: 109–34. http://dx.doi.org/10.1016/j.artmed.2019.07.007.
• [27] Weng CH, Huang TCK, Han RP. Disease prediction with different types of neural network classifiers. Telemat Informatics 2016;33:277–92. http://dx.doi.org/10.1016/j.tele.2015.08.006.
• [28] Zheng T, Xie W, Xu L, He X, Zhang Y, You M, et al. A machine learning-based framework to identify type 2 diabetes through electronic health records. Int J Med Inform 2017;97:120–7. http://dx.doi.org/10.1016/j.ijmedinf.2016.09.014.
• [29] Zhou L, Siddiqui T, Seliger SL, Blumenthal JB, Kang Y, Doerfler R, et al. Text preprocessing for improving hypoglycemia detection from clinical notes – a case study of patients with diabetes. Int J Med Inform 2019;129:374–80. http://dx.doi.org/10.1016/j.ijmedinf.2019.06.020.
• [30] Kate RJ, Pearce N, Mazumdar D, Nilakantan V. A continual prediction model for inpatient acute kidney injury. Comput Biol Med 2020;116103580. http://dx.doi.org/10.1016/j.compbiomed.2019.103580.
• [31] Kop R, Hoogendoorn M, ten TeijeA, Büchner FL, Slottje P, Moons LMG, et al. Predictive modeling of colorectal cancer using a dedicated pre-processing pipeline on routine electronic medical records. Comput Biol Med 2016;76:30–8. http://dx.doi.org/10.1016/j.compbiomed.2016.06.019.
• [32] Richter AN, Khoshgoftaar TM. Efficient learning from big data for cancer risk modeling: a case study with melanoma. Comput Biol Med 2019;110:29–39. http://dx.doi.org/10.1016/j.compbiomed.2019.04.039.
• [33] Ye C, Li J, Hao S, Liu M, Jin H, Zheng L, et al. Identification of elders at higher risk for fall with statewide electronic health records and a machine learning algorithm. Int J Med Inform 2020;137104105. http://dx.doi.org/10.1016/j.ijmedinf.2020.104105.
• [34] Pappada SM, Cameron BD, Rosman PM, Bourey RE, Papadimos TJ, Olorunto W, et al. Neural network-based real-time prediction of glucose in patients with insulin-dependent diabetes. Diabetes Technol Ther 2011;13:135–41. http://dx.doi.org/10.1089/dia.2010.0104.
• [35] Daskalaki E, Prountzou A, Diem P, Mougiakakou SG. Real- Time adaptive models for the personalized prediction of glycemic profile in type 1 diabetes patients. Diabetes Technol Ther 2012;14:168–74. http://dx.doi.org/10.1089/dia.2011.0093.
• [36] Zecchin C, Facchinetti A, Sparacino G, Cobelli C. Jump neural network for online short-time prediction of blood glucose from continuous monitoring sensors and meal information. Comput Methods Programs Biomed 2014;113:144–52. http://dx.doi.org/10.1016/j.cmpb.2013.09.016.
• [37] Bertachi A, Biagi L, Contreras I, Luo N, Vehí J. Prediction of blood glucose levels and nocturnal hypoglycemia using physiological models and artificial neural networks CEUR workshop proc, vol. 2148. 2018.
• [38] Zarkogianni K, Mitsis K, Litsa E, Arredondo MT, Fico G, Fioravanti A, et al. Comparative assessment of glucose prediction models for patients with type 1 diabetes mellitus applying sensors for glucose and physical activity monitoring. Med Biol Eng Comput 2015;53:1333–43. http://dx.doi.org/10.1007/s11517-015-1320-9.
• [39] Georga EI, Protopappas VC, Ardigò D, Marina M, Zavaroni I, Polyzos D, et al. Multivariate prediction of subcutaneous glucose concentration in type 1 diabetes patients based on support vector regression. IEEE J Biomed Heal Informatics 2013;17:71–81. http://dx.doi.org/10.1109/TITB.2012.2219876.
• [40] Xie J, Wang Q. Benchmark machine learning approaches with classical time series approaches on the blood glucose level prediction challenge CEUR workshop proc, vol. 2148. 2018.
• [41] Georga EI, Protopappas VC, Polyzos D, Fotiadis DI. Evaluation of short-term predictors of glucose concentration in type 1 diabetes combining feature ranking with regression models. Med Biol Eng Comput 2015;53:1305–18. http://dx.doi.org/10.1007/s11517-015-1263-1.
• [42] Midroni C, Leimbigler PJ, Baruah G, Kolla M, Whitehead AJ, Fossat Y. Predicting glycemia in type 1 diabetes patients: experiments with XGBoost CEUR workshop proc, vol. 2148. 2018.
• [43] Sparacino G, Zanderigo F, Corazza S, Maran A, Facchinetti A, Cobelli C. Glucose concentration can be predicted ahead in time from continuous glucose monitoring sensor time-series. IEEE Trans Biomed Eng 2007;54:931–7. http://dx.doi.org/10.1109/TBME.2006.889774.
• [44] Pérez-Gandía C, Facchinetti A, Sparacino G, Cobelli C, Gómez EJ, et al. Artificial neural network algorithm for online glucose prediction from continuous glucose monitoring. Diabetes Technol Ther 2010;12:81–8. http://dx.doi.org/10.1089/dia.2009.0076.
• [45] Wang Y, Wu X, Mo X. A novel adaptive-weighted-average framework for blood glucose prediction. Diabetes Technol Ther 2013;15:792–801. http://dx.doi.org/10.1089/dia.2013.0104.
• [46] Ben Ali J, Hamdi T, Fnaiech N, Di Costanzo V, Fnaiech F, Ginoux JM. Continuous blood glucose level prediction of Type 1 Diabetes based on Artificial Neural Network. Biocybern Biomed Eng 2018;38:828–40. http://dx.doi.org/10.1016/j.bbe.2018.06.005.
• [47] Hamdi T, Ben Ali J, Di Costanzo V, Fnaiech F, Moreau E, Ginoux JM. Accurate prediction of continuous blood glucose based on support vector regression and differential evolution algorithm. Biocybern Biomed Eng 2018;38: 362–72. http://dx.doi.org/10.1016/j.bbe.2018.02.005.
• [48] Martinsson J, Schliep A, Eliasson B, Mogren O. Blood glucose prediction with variance estimation using recurrent neural networks. Int J Healthc Inf Syst Inform 2020;4:1–18. http://dx.doi.org/10.1007/s41666-019-00059-y.
• [49] Figo D, Diniz PC, Ferreira DR, Cardoso JMP. Preprocessing techniques for context recognition from accelerometer data. Pers Ubiquitous Comput 2010;14:645–62. http://dx.doi.org/10.1007/s00779-010-0293-9.
• [50] Xiang J, Zhong Y. A novel personalized diagnosis methodology using numerical simulation and an intelligent method to detect faults in a shaft. Appl Sci (Basel) 2016;6:414. http://dx.doi.org/10.3390/app6120414.
• [51] Yan X, Jia M. A novel optimized SVM classification algorithm with multi-domain feature and its application to fault diagnosis of rolling bearing. Neurocomputing 2018;313:47–64. http://dx.doi.org/10.1016/j.neucom.2018.05.002.
• [52] Park D, Kim S, An Y, Jung JY. Lired: A light-weight real-time fault detection system for edge computing using LSTM recurrent neural networks. Sensors (Switzerland) 2018;18:2110. http://dx.doi.org/10.3390/s18072110.
• [53] Zhang Y, Jia Y, Wu W, Cheng Z, Su X, Lin A. A diagnosis method for the compound fault of gearboxes based on multi-feature and bp-adaboost. Symmetry (Basel) 2020;12:461. http://dx.doi.org/10.3390/sym12030461.
• [54] Alfian G, Syafrudin M, Yoon B, Rhee J. False positive RFID detection using classification models. Appl Sci (Basel) 2019;9:1154. http://dx.doi.org/10.3390/app9061154.
• [55] Alfian G, Syafrudin M, Farooq U, Ma'arif MR, Syaekhoni MA, Fitriyani NL, et al. Improving efficiency of RFID-based traceability system for perishable food by utilizing IoT sensors and machine learning model. Food Control 2020;110107016. http://dx.doi.org/10.1016/j.foodcont.2019.107016.
• [56] Li F, Shirahama K, Nisar MA, Köping L, Grzegorzek M. Comparison of feature learning methods for human activity recognition using wearable sensors. Sensors (Switzerland) 2018;18:679. http://dx.doi.org/10.3390/s18020679.
• [57] Rosati S, Balestra G, Knaflitz M. Comparison of different sets of features for human activity recognition by wearable sensors. Sensors (Switzerland) 2018;18:4189. http://dx.doi.org/10.3390/s18124189.
• [58] Lima WS, Souto E, El-Khatib K, Jalali R, Gama J. Human activity recognition using inertial sensors in a smartphone: an overview. Sensors (Switzerland) 2019;19:3213. http://dx.doi.org/10.3390/s19143213.
• [59] Ahmed N, Rafiq JI, Islam MR. Enhanced human activity recognition based on smartphone sensor data using hybrid feature selection model. Sensors (Switzerland) 2020;20:317. http://dx.doi.org/10.3390/s20010317.
• [60] Zhu Q, Chen Z, Masood MK, Soh YC. Occupancy estimation with environmental sensing via non-iterative LRF feature learning in time and frequency domains. Energy Build 2017;141:125–33. http://dx.doi.org/10.1016/j.enbuild.2017.01.057.
• [61] Khan NA, Ali S. A new feature for the classification of non- stationary signals based on the direction of signal energy in the time–frequency domain. Comput Biol Med 2018;100:10–6. http://dx.doi.org/10.1016/j.compbiomed.2018.06.018.
• [62] 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;52:12329–36. http://dx.doi.org/10.1021/ie3034015.
• [63] Bontempi G, Ben Taieb S, Le Borgne YA, et al. Machine learning strategies for time series forecasting. In: van der Aalst W, Mylopoulos J, Rosemann M, Shaw MJ, Szyperski C, editors. Lect Notes bus Inf Process, vol. 138. LNBIP, Berlin, Heidelberg: Springer Berlin Heidelberg; 2013. p. 62–77. http://dx.doi.org/10.1007/978-3-642-36318-4_3.
• [64] Ben Taieb S, Bontempi G, Atiya AF, Sorjamaa A. A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition. Expert Syst Appl 2012;39:7067–83. http://dx.doi.org/10.1016/j.eswa.2012.01.039.
• [65] Alfian G, Syafrudin M, Rhee J, Anshari M, Mustakim M, Fahrurrozi I. Blood Glucose Prediction Model for Type 1 Diabetes based on Extreme Gradient Boosting. IOP Conf Ser Mater Sci Eng 2020;803012012. http://dx.doi.org/10.1088/1757-899X/803/1/012012.
• [66] Han J, Kamber M, Pei J. Data mining: concepts and techniques; 2012. http://dx.doi.org/10.1016/C2009-0-61819-5.
• [67] Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature 1986;323:533–6. http://dx.doi.org/10.1038/323533a0.
• [68] Jiménez ÁB, Lázaro JL, Dorronsoro JR. Finding optimal model parameters by discrete grid search. In: Kacprzyk J, Corchado E, Corchado JM, Abraham A, editors. Adv Soft comput, vol. 44. Berlin, Heidelberg: Springer Berlin Heidelberg; 2007. p. 120–7. http://dx.doi.org/10.1007/978-3-540-74972-1_17.
• [69] DirecNet Dataset. Evaluation of Counter-regulatory Hormone Responses during Hypoglycemia and the Accuracy of Continuous Glucose Monitors in Children with T1DM. https://public.jaeb.org/direcnet/stdy/167.
• [70] Savitzky A, Golay MJE. Smoothing and differentiation of data by simplified least squares procedures. Anal Chem 1964;36:1627–39. http://dx.doi.org/10.1021/ac60214a047.
• [71] Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: Machine learning in Python. J Mach Learn Res 2011;12:2825–30.
• [72] Del FaveroS, Facchinetti A, Cobelli C. A glucose-specific metric to assess predictors and identify models. IEEE Trans Biomed Eng 2012;59:1281–90. http://dx.doi.org/10.1109/TBME.2012.2185234.
• [73] Mhaskar HN, Pereverzyev SV, van der Walt MD. A deep learning approach to diabetic blood glucose prediction. Front Appl Math Stat 2017;3. http://dx.doi.org/10.3389/fams.2017.00014.