Logo PTI Logo rice

Proceedings of the 2022 Seventh International Conference on Research in Intelligent and Computing in Engineering

Annals of Computer Science and Information Systems, Volume 33

Development of Ensemble Tree Models for Generalized Blood Glucose Level Prediction

, , ,

DOI: http://dx.doi.org/10.15439/2022R36

Citation: Proceedings of the 2022 Seventh International Conference on Research in Intelligent and Computing in Engineering, Vu Dinh Khoa, Shivani Agarwal, Gloria Jeanette Rincon Aponte, Nguyen Thi Hong Nga, Vijender Kumar Solanki, Ewa Ziemba (eds). ACSIS, Vol. 33, pages 55–61 ()

Full text

Abstract. Type-1 diabetes (T1D) patients must carefully monitor their insulin doses to avoid serious health complications. An effective regimen can be designed by predicting accurate blood glucose levels (BGLs). Several physiological and data-driven models for BGL prediction have been designed. However, less is known on the combination of different traditional machine learning (ML) algorithms for BGL prediction. Furthermore, most of the available models are patient-specific. This research aims to evaluate several traditional ML algorithms and their novel combinations for generalized BGL prediction. The data of forty T1D patients were generated using the Automated Insulin Dosage Advisor (AIDA) simulator. The twenty-four hour time-series contained samples at fifteen-minute intervals. The training data was obtained by joining eighty percent of each patient's time-series, and the remaining twenty percent time-series was joined to obtain the testing data. The models were trained using multiple patients' data so that they could make predictions for multiple patients. The traditional non-ensemble algorithms: linear regression (LR), support vector regression (SVR), k-nearest neighbors (KNN), multi-layer perceptron (MLP), decision tree (DCT), and extra tree (EXT) were evaluated for forecasting BGLs of multiple patients. A new ensemble, called the Tree-SVR model, was developed. The BGL predictions from the DCT and the EXT models were fed as features into the SVR model to obtain the final outcome. The ensemble approach used in this research was based on the stacking technique. The Tree-SVR model outperformed the non-ensemble models (LR, SVR, KNN, MLP, DCT, and EXT) and other novel Tree variants (Tree-LR, Tree-MLP, and Tree-KNN). This research highlights the utility of designing ensembles using traditional ML algorithms for generalized BGL prediction.

References

  1. IDF Diabetes Atlas, 9th edition (2019). http://www/diabetesatlas.org
  2. Iván Contreras, Silvia Oviedo, Martina Vettoretti, Roberto Visentin, and Josep Vehı́. 2017. Personalized blood glucose prediction: A hybrid approach using grammatical evolution and physiological models. PLOS ONE 12 (11 2017), e0187754. https://doi.org/10.1371/journal.pone.0187754
  3. Gavin Robertson, Eldon Lehmann, William Sandham, and David Hamil ton. 2011. Blood Glucose Prediction Using Artificial Neural Networks Trained with the AIDA Diabetes Simulator: A Proof-of-Concept Pilot Study. J. Electrical and Computer Engineering 2011 (05 2011). https://doi.org/10.1155/2011/681786
  4. E. D. Lehmann and T. Deutsch. 1992. A physiological model of glucoseinsulin interaction in type 1 diabetes mellitus. Journal of biomedical engineering 14 3 (1992), 235–42.
  5. S. M. Lynch and B. W. Bequette. 2001. Estimation-based model predictive control of blood glucose in type I diabetics: a simulation study. Proceedings of the IEEE 27th Annual Northeast Bioengineering Conference (Cat. No.01CH37201) (2001),79–80.
  6. T. Hamdi, J. Ben Ali, N. Fnaiech, V. Di Costanzo, F. Fnaiech, E. Moreau, and J.Ginoux. 2017. Artificial neural network for blood glucose level prediction. In 2017 International Conference on Smart, Monitored and Controlled Cities (SM2C). 91–95. https://doi.org/10.1109/SM2C.2017.8071825
  7. Scott Pappada, Brent Cameron, and Paul Rosman. 2008. Development of a neural network for prediction of glucose in type I diabetes patients. Journal of diabetes science and technology 2 (09 2008), 792–801. https://doi.org/10.1177/193229680800200507
  8. Sandham WA, Nikoletou D, Hamilton DJ, Patterson K, Japp A, MacGregor C. Blood glucose prediction for diabetes therapy using a recurrent artificial neural network. In: Proceedings, EUSIPCO-98, IX European Signal Processing Conference, Rhodes Is-land, Greece, 1998; Vol. 11: pp. 673-676.
  9. W. A. Sandham, D. J. Hamilton, A. Japp and K. Patterson, “Neural network and neuro-fuzzy systems for improving diabetes therapy,” Proceed- ings of the 20th Annual Inter-national Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286), Hong Kong, China, 1998, pp. 1438-1441 vol.3, http://dx.doi.org/10.1109/IEMBS.1998.747154.
  10. John Martinsson, Alexander Schliep, Björn Eliasson, and Olof Mogren. 2020. Blood Glucose Prediction with Variance Estimation Using Recurrent Neural Networks. Journal of Healthcare Informatics Research 4 (03 2020). https://doi.org/10.1007/s41666-019-00059-y
  11. Muhammad Asad, Usman Qamar, Babar Zeb, Aimal Khan, and Younas Khan. 2019. Blood Glucose Level Prediction with Minimal Inputs Using Feedforward Neural Network for Diabetic Type 1 Patients (ICMLC ’19). Association for Computing Machinery, New York, NY, USA, 182–185. https://doi.org/10.1145/3318299.3318354
  12. Taisa Kushner, Marc D. Breton, and Sriram Sankaranarayanan. Multi-Hour Blood Glucose Prediction in Type 1 Diabetes: A Patient-Specific Approach Using Shallow Neural Network Models.Diabetes Technology & Therapeutics.Dec 2020.883-891.
  13. Mario Munoz-Organero. 2020. Deep Physiological Model for Blood Glucose Prediction in T1DM Patients. Sensors 20 (07 2020), 3896. https://doi.org/10.3390/s20143896
  14. Rabby, M.F., Tu, Y., Hossen, M.I. et al. Stacked LSTM based deep recurrent neural network with kalman smoothing for blood glucose prediction. BMC Med Inform Decis Mak 21, 101 (2021). https://doi.org/10.1186/s12911-021-01462-5
  15. Kim, Dae-Yeon &Choi, Dong-Sik & Kang, Ah & Woo, Jiyoung & Han, Yechan & Chun, Sung Wan & Kim, Jaeyun. (2022). Intelligent Ensemble Deep Learning System for Blood Glucose Prediction Using Genetic Algorithms. Complexity. 2022. 1-10. http://dx.doi.org/10.1155/2022/7902418.
  16. Zhu, T., Li, K., Chen, J. et al. Dilated Recurrent Neural Networks for Glucose Forecasting in Type 1 Diabetes. J Healthc Inform Res 4, 308–324 (2020). https://doi.org/10.1007/s41666-020-00068-2
  17. Ning Li, Jianyong Tuo, Youqing Wang, Menghui Wang, Prediction of blood glucose concentration for type 1 diabetes based on echo state networks embedded with incremental learning, Neurocomputing, Volume 378, 2020, Pages 248-259, ISSN 0925-2312, https://doi.org/10.1016/j.neucom.2019.10.003
  18. W. Wang, M. Tong and M. Yu, “Blood Glucose Prediction With VMD and LSTM Optimized by Improved Particle Swarm Optimization,” in IEEE Access, vol. 8, pp. 217908-217916, 2020, http://dx.doi.org/10.1109/ACCESS.2020.3041355.
  19. Zhu, T; Yao, X; Li, K; Herrero, P; Georgiou, P; (2020) Blood glucose prediction for type 1 diabetes using generative adversarial networks. In: Bach, K and Bunescu, R and Marling, C and Wiratunga, N, (eds.) Proceedings of the 5th International Workshop on Knowledge Discovery in Healthcare Data co-located with 24th European Conference on Artificial Intelligence (ECAI 2020). (pp. pp. 90-94). : Santiago de Compostela, Spain
  20. Khaoula Assadi, Takoua Hamdi, F. Fnaiech, J. M. Ginoux, and E. Moreau. 2017. Estimation of blood glucose levels techniques. 2017 International Conference on Smart, Monitored and Controlled Cities (SM2C) (2017), 75–80.
  21. Enric Monte-Moreno. 2011. Non-invasive estimate of blood glucose and blood pressure from a photoplethysmograph by means of machine learning techniques.Artificial intelligence in medicine 53 (06 2011), 127–38. https://doi.org/10.1016/j.artmed.2011.05.001
  22. Takoua Hamdi, Jaouher Ben Ali, Véronique Di Costanzo, Farhat Fnaiech, Eric Moreau, and Jean-Marc Ginoux. 2018. Accurate prediction of continuous blood glucose based on support vector regression and differential evolution algorithm. Biocybernetics and Biomedical Engineering 38, 2 (2018), 362 – 372. https://doi.org/10.1016/j.bbe.2018.02.005
  23. Eleni Georga, Vasilios Protopappas, Diego Ardigò, Michela Marina, Ivana Zavaroni, Demosthenes Polyzos, and Dimitrios Fotiadis. 2012. Multivariate Prediction of Subcutaneous Glucose Concentration in Type 1 Diabetes Patients Based on Support Vector Regression. IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society 17 (09 2012). https://doi.org/10.1109/TITB.2012.2219876
  24. K. Plis, Razvan C. Bunescu, C. Marling, J. Shubrook, and F. Schwartz. 2014. A Machine Learning Approach to Predicting Blood Glucose Levels for Diabetes Management. In AAAI Workshop: Modern Artificial Intelligence for Health Analytics.
  25. R. Bunescu, N. Struble, C. Marling, J. Shubrook, and F. Schwartz. 2013. Blood Glucose Level Prediction Using Physiological Models and Support Vector Regression. In 2013 12th International Conference on Machine Learning and Applications, Vol. 1. 135–140. https://doi.org/10.1109/ICMLA.2013.30
  26. Natalia Mordvanyuk, F. Torrent-Fontbona, and B. López. 2017. Prediction of Glucose Level Conditions from Sequential Data. In CCIA. .
  27. Maged, Youssef & Atia, Ayman. (2022). The Prediction Of Blood Glucose Level By Using The ECG Sensor of Smartwatches. 406-411. http://dx.doi.org/10.1109/MIUCC55081.2022.9781730.
  28. Kyriaki Saiti, Martin Macaš, Lenka Lhotská, Kateřina Štechová, Pavlı́na Pithová, Ensemble methods in combination with compartment models for blood glucose level prediction in type 1 diabetes mellitus,Computer Methods and Programs in Biomedicine, Volume 196, 2020, 105628, ISSN 0169-2607, https://doi.org/10.1016/j.cmpb.2020.105628
  29. Ma, Ning et al. “Online Blood Glucose Prediction Using Autoregressive Moving Average Model with Residual Compensation Network.” KDH@ECAI (2020)
  30. Xie, Jinyu & Wang, Qian. (2020). Benchmarking Machine Learning Algorithms on Blood Glucose Prediction for Type I Diabetes in Comparison With Classical Time-Series Models. IEEE Transactions on Biomedical Engineering. PP. 10.1109/TBME.2020.2975959.
  31. AIDA, http://www.2aida.org/
  32. James Moody. What does RMSE really mean?,
  33. Fabian Pedregosa, Gael Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, Edouard Duchesnay, and Gilles Louppe. 2012. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12 (01 2012).
  34. Keras webpage https://keras.io/guides/sequential model/
  35. Wikipedia contributors. 2020. Hyperparameter (machine learning) — Wikipedia, The Free Encyclopedia. https://en.wikipedia.org/w/index. php?title=Hyperparameter (machine learning)&oldid=984957886
  36. Scikit-learn webpage https://scikit-learn.org/stable/modules/generated/sklearn.linear model.LinearRegression.html
  37. Scikit-learn webpage https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsRegressor.html
  38. Towards Data Science webpage https://towardsdatascience.com/support-vector-machine-introduction-to-machine-learning-algorithms
  39. Scikit-learn webpage https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVR.html
  40. Wikipedia webpage https://en.wikipedia.org/wiki/Multilayer perceptron
  41. Machine learning mastery webpage https://machinelearningmastery. com/neural-networks-crash-course/
  42. Keras webpage https://keras.io/api/optimizers/adam/
  43. Keras webpage https://keras.io/api/layers/initializers/
  44. Keras webpage https://keras.io/api/layers/regularizers/
  45. Dr. Saed Sayad. Decision Tree - Regression, https://www.saedsayad.com/decision tree reg.htm
  46. scikit-learn developers.sklearn.tree.DecisionTreeRegressor, https://scikit-learn.org/stable/modules/generated/sklearn.tree.DecisionTreeRegressor.html
  47. scikit-learn developers. sklearn.tree.ExtraTreeRegressor, https://scikit-learn.org/stable/modules/generated/sklearn.tree.ExtraTreeRegressor.html
  48. Medium webpage https://medium.com/@supun.setunga/stacking-in-machine-learning-357db1cfc3a
  49. George Seif. 2018. https://towardsdatascience.com/three-reasons-that-you-should-not-use-deep-learning-15bec517b622