Tekrarlayan Sinir Ağlarıyla Akıllı Telefon Tabanlı Çoklu Parametrik Glikoz Tahmini

Abstract

Diabetes Mellitus, glikoz seviyelerindeki düzensizliğin kontrolsüz hücre çoğalması gibi işlevsel bozuklukları tetiklediği için pankreas kanseri gibi birçok ölümcül hastalığa neden olmaktadır. Glikozun düzensizliğindeki kritik seviyeler, insan yaşam kalitesi için önceden tespit edilmesi gereken hiperglisemi (yüksek kan şekeri) ve hipoglisemi (düşük kan şekeri) olarak sınıflandırılır. Bu anlamda, genellikle sadece glikoz verisini kullanarak tahmin gerçekleştiren yapay zeka (AI) tabanlı birçok araç geliştirilmiştir. Ancak bu çalışmada, glikoz tahmininde öngörülebilirliği artırmak için yapay zekanın bir alt kümesi olan tekrarlayan sinir ağında (RNN) çoklu parametre kullanılması önerilmiştir. Önerilen sistemde, çoklu parametreli tahminin neden olduğu karmaşık bellek işlemlerini üstesinden gelmek için uzun-kısa süreli bellek (LSTM) tabanlı bir RNN kullanılmıştır. OhioT1DM veri setindeki eğitim ve doğrulama sonuçları, önerilen sistemin çok düşük bir hatayla glikoz seviyesini tahmin ederek temel sistemlere göre avantajını göstermiştir. Sistemimiz daha sonra Bluetooth aracılığıyla sensörlerden gelen glikoz seviyelerini okuyabilen özel tasarladığımız Android uygulamamız BffDiabetes PRO ile entegre edilmiştir. BffDiabetes PRO, bir sonraki glikoz seviyesini tahmin etmek için mevcut glikoz seviyesini, akselerasyon ve temel cilt sıcaklığı gibi parametreleri bulut üzerinden sunucuya aktarır. Uygulama, tahmin edilen değeri, glikozun kritik seviyelere ulaşma eğiliminde olup olmadığını değerlendirir. Bu eğilimin tespit edilmesi durumunda BffDiabetes PRO gerekli önlemler için kullanıcıyı uyarı göndermektedir.

Keywords

• Yapay Zeka
• Tekrarlayan Sinir Ağları
• LSTM
• GRU
• Glikoz Tahmini
• Akıllı Telefon Uygulaması.

Smartphone-based Multi-parametric Glucose Prediction using Recurrent Neural Networks

Abstract

Diabetes Mellitus causes many deadly diseases, including pancreatic cancer as irregularity of glucose level triggers dysfunctions like unchecked cell growth. The critical stages in glucose irregularity are categorized as hyperglycemia (high blood glucose) and hypoglycemia (low blood glucose) which needs to be detected in advance for the quality of human life. In that sense, many tools have been developed based on artificial intelligence (AI) systems which mostly consider the glucose measurement as a prediction parameter. However, in this study, we propose to employ multi-parameter in glucose prediction based on a Recurrent Neural Network (RNN), a subset of AI, to enhance predictability. The proposed system utilizes a Long-Short Term Memory (LSTM) based RNN to handle complex memory operations caused by multi-parametric prediction. Training and validation scores on the OhioT1DM dataset show the advantage of our proposed system over the baseline systems for predicting glucose levels with a significantly reduced error. The system is later integrated with our custom-designed Android application, BffDiabetes PRO, capable of reading the glucose levels from the sensors via Bluetooth. The BffDiabetes PRO transfers the current glucose level, acceleration, and baseline skin temperature to the server via a cloud system to predict the next level. It receives the prediction result to evaluate whether the glucose level tends to reach the critical stages. In case of this tendency is detected, the BffDiabetes PRO alerts the user for necessary precautions.

Keywords

• Artificial Intelligence
• Recurrent Neural Networks
• LSTM
• GRU
• Glucose Prediction
• Smartphone Application

References

1. Amidi, A., & Amidi, S. (2020). CS 230 - Deep Learning / Recurrent Neural Networks cheatsheet. Retrieved from https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-recurrent-neural-networks
2. Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. J arXiv preprint arXiv.
3. Daniels, J., Herrero, P., & Georgiou, P. (2020). Personalised Glucose Prediction via Deep Multitask Networks. Paper presented at the KDH@ ECAI.
4. Dey, R., & Salem, F. M. (2017). Gate-variants of gated recurrent unit (GRU) neural networks. Paper presented at the 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS).
5. Doğan, V., & Kılıç, V. (2021). Akıllı Telefon Kullanarak Yapay Zeka Tabanlı Farenjit Tespiti: Artificial Intelligence Based Pharyngitis Detection Using Smartphone. J Sağlık Bilimlerinde Yapay Zeka Dergisi, 1(2), 14-19.
6. Gers, F. A., & Schmidhuber, E. (2001). LSTM recurrent networks learn simple context-free and context-sensitive languages. J IEEE Transactions on Neural Networks, 12(6), 1333-1340.
7. Hossain, M. Z., Sohel, F., Shiratuddin, M. F., & Laga, H. (2019). A comprehensive survey of deep learning for image captioning. J ACM Computing Surveys, 51(6), 1-36.
8. Kap, Ö., Kilic, V., Hardy, J. G., & Horzum, N. (2021). Smartphone-based colorimetric detection systems for glucose monitoring in the diagnosis and management of diabetes. J Analyst.

9. Kılıç, V. (2021). Yapay Zeka Tabanlı Akıllı Telefon Uygulaması ile Kan Şekeri Tahmini. J Avrupa Bilim ve Teknoloji Dergisi(26), 289-294.
10. Kriventsov, S., Lindsey, A., & Hayeri, A. (2020). The Diabits app for smartphone-assisted predictive monitoring of glycemia in patients with diabetes: retrospective observational study. J JMIR diabetes, 5(3), e18660.
11. Li, J., & Fernando, C. (2016). Smartphone-based personalized blood glucose prediction. J ICT Express, 2(4), 150-154.
12. Li, K., Liu, C., Zhu, T., Herrero, P., & Georgiou, P. (2019). GluNet: A deep learning framework for accurate glucose forecasting. J IEEE journal of biomedical health informatics, 24(2), 414-423.
13. Lillicrap, T. P., & Santoro, A. (2019). Backpropagation through time and the brain. J Current opinion in neurobiology, 55, 82-89.
14. Loye, G. (2019a). DEEP LEARNING Gated Recurrent Unit (GRU) With PyTorch. Retrieved from https://blog.floydhub.com/gru-with-pytorch/
15. Loye, G. (2019b). DEEP LEARNING Long Short-Term Memory: From Zero to Hero with PyTorch. Retrieved from https://blog.floydhub.com/long-short-term-memory-from-zero-to-hero-with-pytorch/
16. Marling, C., & Bunescu, R. (2020). The OhioT1DM dataset for blood glucose level prediction: Update 2020. Paper presented at the CEUR workshop proceedings.
17. Martinsson, J., Schliep, A., Eliasson, B., Meijner, C., Persson, S., & Mogren, O. (2018). Automatic blood glucose prediction with confidence using recurrent neural networks. Paper presented at the KHD@ IJCAI.
18. Martinsson, J., Schliep, A., Eliasson, B., & Mogren, O. (2020). Blood glucose prediction with variance estimation using recurrent neural networks. J Journal of Healthcare Informatics Research, 4(1), 1-18.
19. Mellitus, D. (2005). Diagnosis and classification of diabetes mellitus. J Diabetes care, 28(S37), S5-S10.
20. Mercan, Ö. B. (2020). Deep Learning based Colorimetric Classification of Glucose with Au-Ag nanoparticles using Smartphone. Paper presented at the 2020 Medical Technologies Congress (TIPTEKNO).
21. Mercan, Ö. B., Doğan, V., & Kılıç, V. (2020). Time Series Analysis based Machine Learning Classification for Blood Sugar Levels. Paper presented at the 2020 Medical Technologies Congress (TIPTEKNO).
22. Mercan, Ö. B., Kılıç, V., & Şen, M. (2021). Machine learning-based colorimetric determination of glucose in artificial saliva with different reagents using a smartphone coupled μPAD. J Sensors Actuators B: Chemical, 329, 129037.
23. Pedamallu, H. (2020). RNN vs GRU vs LSTM. Retrieved from https://medium.com/analytics-vidhya/rnn-vs-gru-vs-lstm-863b0b7b1573
24. Sak, H., Senior, A. W., & Beaufays, F. (2014). Long short-term memory recurrent neural network architectures for large scale acoustic modeling.
25. Shen, G., Tan, Q., Zhang, H., Zeng, P., & Xu, J. (2018). Deep learning with gated recurrent unit networks for financial sequence predictions. J Procedia computer science, 131, 895-903.
26. Strollo, F., Furia, A., Verde, P., Bellia, A., Grussu, M., Mambro, A., . . . Gentile, S. (2021). Technological innovation of Continuous Glucose Monitoring (CGM) as a tool for commercial aviation pilots with insulin-treated diabetes and stakeholders/regulators: A new chance to improve the directives? J diabetes research clinical practice, 172.
27. Sun, Q., Jankovic, M. V., Bally, L., & Mougiakakou, S. G. (2018). Predicting blood glucose with an lstm and bi-lstm based deep neural network. Paper presented at the 2018 14th Symposium on Neural Networks and Applications (NEUREL).
28. Sun, X., Rashid, M. M., Sevil, M., Hobbs, N., Brandt, R., Askari, M.-R., . . . Cinar, A. (2020). Prediction of Blood Glucose Levels for People with Type 1 Diabetes using Latent-Variable-based Model. Paper presented at the KDH@ ECAI.
29. Şahin, A., & Aydın, A. (2021). Personalized Advanced Time Blood Glucose Level Prediction. J Arabian Journal for Science Engineering, 1-12.
30. Tang, D., Qin, B., & Liu, T. (2015). Document modeling with gated recurrent neural network for sentiment classification. Paper presented at the Proceedings of the 2015 conference on empirical methods in natural language processing.