Journal of Digital Policy (디지털정책학회지)

The Society of Digital Policy and Management (한국디지털정책학회)
권호 표지
DOI QR코드

DOI QR Code

Blood glucose prediction using PPG and DNN in dogs - a pilot study

개의 PPG와 DNN를 이용한 혈당 예측 - 선행연구

  • 박철구 ((주)소프트웨어융합연구소) ;
  • 최상기 ((주)소프트웨어융합연구소)
  • Received : 2023.11.24
  • Accepted : 2023.12.28
  • Published : 2023.12.28
Download PDF
⟨ Previous Next ⟩

Abstract

This paper is a study to develop a deep neural network (DNN) blood glucose prediction model based on heart rate (HR) and heart rate variability (HRV) data measured by PPG-based sensors. MLP deep learning consists of an input layer, a hidden layer, and an output layer with 11 independent variables. The learning results of the blood glucose prediction model are MAE=0.3781, MSE=0.8518, and RMSE=0.9229, and the coefficient of determination (R2) is 0.9994. The study was able to verify the feasibility of glycemic control using non-blood vital signs using PPG-based digital devices. In conclusion, a standardized method of acquiring and interpreting PPG-based vital signs, a large data set for deep learning, and a study to demonstrate the accuracy of the method may provide convenience and an alternative method for blood glucose management in dogs.

논문은 PPG 기반 센서에서 측정한 심박수(HR), 심박변이도(HRV) 데이터를 기반으로 DNN(Deep Neural Network) 혈당예측 모델을 개발하는 연구이다. 혈당 예측은 다층퍼셉트론(MLP) 신경망을 이용하였다. DNN 심층학습은 11의 독립변수가 있는 입력층, 은닉층, 출력층으로 구성된다. 혈당 예측모델의 학습결과는 MAE=0.3781, MSE=0.8518, 및 RMSE=0.9229이며, 결정계수(R2)는 0.9994이다. PPG기반의 디지털기기를 이용한 비채혈적 생체신호를 이용하여 혈당관리의 가능성을 확인하였다. PPG기반의 표준화된 활력신호 획득 및 해석법, 다량의 데이터기반 심층학습(Deep Learning)의 데이터셋, 정확성를 실증하는 연구가 이어진다면 개의 혈당관리에 편이성과 대안적인 방법을 제공할 수 있을 것이다.

Keywords

References

  1. David Bruyette. (2022.10). Diabetes Mellitus in Dogs and Cats (Online). https://www.msdvetmanual.com/endocrine-system/the-pancreas/diabetes-mellitus-in-dogs-and-cats 
  2. J. Freitas et al. (2021). Causes of spontaneous death and euthanasia in dogs: A background study in Bahia, Brazil. Veterinarni Medicina, 66. 156-166. DOI : 10.17221/92/2020-VETMED. 
  3. ADRIENNE FARRICELL. (2023.1.24). The Most Common Causes of Death in Dogs (By Breed and Size) (Online). https://pethelpful.com/dogs/Study-Reveals-The-Most-Common-Causes-of-Death-in-Dogs 
  4. B. Shi, F. Chen, J. Chen & Y. Tsau. (2015). Zhongguo yi liao qi xie za zhi, Chinese journal of medical instrumentation, 39(2), 95-97. 
  5. J. Ma, C. Wang & Z. Li & H. Zhao (2011). Study of measuring heart rate and respiration rate based on PPG. Guangxue Jishu/Optical Technique, 37, 309-312. 
  6. A. B. Liu, P. C. Hsu, Z. L. , Chen & H. T. Wu, (2011). Measuring pulse wave velocity using ECG and photoplethysmography. Journal of medical systems, 35(5), 771-777. DOI : 10.1007/s10916-010-9469-0 
  7. B. C. Wilson & S. L. Jacques, (1990). Optical reflectance and transmittance of tissues: principles and applications. IEEE Journal of Quantum Electronics, 26, 2186-2199.  https://doi.org/10.1109/3.64355
  8. F. A. Duck, (2013) Physical properties of tissues: a comprehensive reference book. Academic press. 
  9. J. P. Varshney. (2020). Electrocardiography in Veterinary Medicine. Springer Nature Singapore Pte Ltd. 22(8), 4215. DOI : 10.3390/ijms22084215 
  10. J. Haggstrom, R, L. Hamlin, K. Hansson & C. Kvart (1996). Heart rate variability in relation to severity of mitral regurgitation in Cavalier King Charles spaniels. The Journal of small animal practice, 37(2), 69-75. DOI : 10.1111/j.1748-5827.1996.tb01941.x 
  11. S. Doxey & A. Boswood. (2004). Differences between breeds of dog in a measure of heart rate variability. The Veterinary record, 154(23), 713-717. DOI : 10.1136/vr.154.23.713 
  12. A. Struven, C. Holzapfel, C. Stremmel & S. Brunner. (2021). Obesity, Nutrition and Heart Rate Variability. International journal of molecular sciences, 22(8), 4215. DOI : 10.3390/ijms22084215 
  13. N. Azulay et al. (2022). Reduced heart rate variability is related to the number of metabolic syndrome components and manifest diabetes in the sixth Tromso study 2007-2008. Scientific reports, 12(1), 11998. DOI : 10.1038/s41598-022-15824-0 
  14. S. L. Jacques. (2013). Optical properties of biological tissues: a review. Physics in medicine and biology, 58(11), R37-R61. DOI : 10.1088/0031-9155/58/11/R37 
  15. N. Sieber-Ruckstuhl, M. Casella & C. E. Reusch. (2003). Home monitoring of blood glucose concentrations by owners of diabetic dogs and cats. 145. 537-543. 
  16. S. Corradini et al. (2016). Accuracy of a Flash Glucose Monitoring System in Diabetic Dogs. Journal of Veterinary Internal Medicine. 30. DOI : 10.1111/jvim.14355. 
  17. P. Rossetti, J. Bondia, J. Vehi & C. G. Fanelli. (2010). Estimating plasma glucose from interstitial glucose: the issue of calibration algorithms in commercial continuous glucose monitoring devices. Sensors (Basel, Switzerland), 10(12), 10936-10952. DOI : 10.3390/s101210936 
  18. C. Cobelli, M. Schiavon, C. Dalla Man, A. Basu & R. Basu. (2016). Interstitial Fluid Glucose Is Not Just a Shifted-in-Time but a Distorted Mirror of Blood Glucose: Insight from an In Silico Study. Diabetes technology & therapeutics, 18(8), 505-511. DOI : 10.1089/dia.2016.0112 
  19. A. Basu et al (2015). Time lag of glucose from intravascular to interstitial compartment in type 1 diabetes. Journal of diabetes science and technology, 9(1), 63-68. DOI : 10.1177/1932296814554797 
  20. K. Rebrin & G. M. Steil. (2000). Can interstitial glucose assessment replace blood glucose measurements?, Diabetes technology & therapeutics, 2(3), 461-472. DOI : 10.1089/15209150050194332 
  21. S. N. Thennadil, ,J. L. Rennert, B. J. Wenzel, K. H. Hazen, T. L. Ruchti, & M. B. Block. (2001). Comparison of glucose concentration in interstitial fluid, and capillary and venous blood during rapid changes in blood glucose levels. Diabetes technology & therapeutics, 3(3), 357-365. DOI : 10.1089/15209150152607132 
  22. T. P. Monsod et al, (2002). Do sensor glucose levels accurately predict plasma glucose concentrations during hypoglycemia and hyperinsulinemia?. Diabetes care, 25(5), 889-893. DOI : 10.2337/diacare.25.5.889 
  23. C.-G. Park & S.-K. Choi. (2022). The study of blood glucose level prediction using photoplethysmography and machine learning . Journal of Digital Policy, 1(2), 61-69. https://doi.org/10.23149/JDP.2022.1.2.061