[논문]심탄도와 인공지능을 이용한 혈당수치 예측모델 연구

최상기; 박철구

doi:10.14400/jdc.2021.19.9.257

심탄도와 인공지능을 이용한 혈당수치 예측모델 연구
The study of blood glucose level prediction model using ballistocardiogram and artificial intelligence 원문보기

디지털융복합연구 = Journal of digital convergence, v.19 no.9, 2021년, pp.257 - 269

최상기 (소프트웨어융합연구소) , 박철구 (소프트웨어융합연구소)

초록
AI-Helper

논문은 심탄도(BCG, Ballistocardiogram) 센서를 이용하여 생체신호 데이터를 비침습, 무구속적인 방식으로 수집하고, ICT 기술과 고성능 컴퓨팅 환경에서 인공지능 기계학습 알고리즘을 활용하여 데이터 기반 혈당 예측 알고리즘 모델 개발 및 검증하는 방법을 제시하고 연구하는 것이다. 혈당수치 예측모델은 MLP 아키텍처에 입력노드는 심박수, 호흡수, 심박출량, 심박변이도, SDNN, RMSSD, PNN50, 나이, 성별이며, 은닉층 7개를 사용하였다. 실험 결과는 5회 실험한 학습데이터의 평균 MSE, MAE 및 RMSE 값은 각각 0.5226, 0.6328 및 0.7692이며 검증데이터 평균 값은 각각 0.5408, 0.6776, 0.7968이었으며, 결정계수(R2) 수치는 0.9997의 결과를 보였다. 데이터를 기반으로 한 혈당수치를 예측하는 모델을 표준화하고 데이터셋 수집과 예측 정확성을 검증하는 연구가 계속적으로 진행된다면 비침습 방식의 혈당 수준 관리에 활용될 수 있을 것으로 사료된다.

Abstract ▼ AI-Helper

The purpose of this study is to collect biosignal data in a non-invasive and non-restrictive manner using a BCG (Ballistocardiogram) sensor, and utilize artificial intelligence machine learning algorithms in ICT and high-performance computing environments. And it is to present and study a method for developing and validating a data-based blood glucose prediction model. In the blood glucose level prediction model, the input nodes in the MLP architecture are data of heart rate, respiration rate, stroke volume, heart rate variability, SDNN, RMSSD, PNN50, age, and gender, and the hidden layer 7 were used. As a result of the experiment, the average MSE, MAE, and RMSE values of the learning data tested 5 times were 0.5226, 0.6328, and 0.7692, respectively, and the average values of the validation data were 0.5408, 0.6776, and 0.7968, respectively, and the coefficient of determination (R2) was 0.9997. If research to standardize a model for predicting blood sugar levels based on data and to verify data set collection and prediction accuracy continues, it is expected that it can be used for non-invasive blood sugar level management.

주제어

표/그림 (20)

그림 Fig. 1. Unit waveforms in ECG and BCG (head-to-foot direction)[16].
표 Table 1. BCG Sensor Specifications[25]
표 Table 2. Blood glucose meter specifications (Roche, Accu-chek® Instant)[27]
그림 Fig. 3. Data collection diagram
표 Table 3. Computing system specifications
표 Table 4. BCG 신호처리 계산식[28].
그림 Fig. 4. Correlation between BCG heart rate and PSG heart rate during sleep[29].
그림 Fig. 5. Scatter of Heart Rate in ECG and BCG
그림 Fig. 6. Clarke error gird.
그림 Fig. 7. Blood glucose prediction model and validation process
표 Table 5. BCG data age distribution
표 Table 6. Statistical analysis result
표 Table 7. Correlation matrix for BCG data variables (N=9,786)
그림 Fig. 8. MLP architecture
표 Table 8. Hyperparameters
표 Table 9. Prediction and performance Results in MLP
그림 Fig. 9. Clarke Error Grid Analysis Result of Predictive Model (at H7 Model)
표 Table 10. Input node group for verifying variables that affect the predictive model
표 Table 11. Blood Glucose level predictive performance results by input node
그림 Fig. 10. Clarke Error Grid Analysis Results by Input Node

참고문헌 (35)

KyungHee University Medical Center (2021.07.25). Medical Commons:Diabetes. https://www.khuh.or.kr/04/01.php? hospitalpathmd&tablemdlecture&page1&commandview_article&key262&s_key&keycode&keycode2
Ruth S Weinstock. (2021.05.20). Patient education: Blood glucose monitoring in diabetes (Beyond the Basics). https://www.uptodate.com/contents/blood-glucose-monitoring-in-diabetes-beyond-the-basics
Wolfsdorf, Joseph & Glaser, Nicole & Agus, Michael & Fritsch, Maria & Hanas, Ragnar & Rewers, Arleta & Sperling, Mark & Codner, Ethel. (2018). Diabetic Ketoacidosis and Hyperglycemic Hyperosmolar State: A Consensus Statement from the International Society for Pediatric and Adolescent Diabetes. Pediatric Diabetes. 19 Suppl 27. DOI : 10.1111/pedi.12701.

상세보기
Yanggyo Kang. (2019). Glucose Management Using Continuous Glucose Monitors. J Korean Diabetes 2019;20:42-46. DOI : 10.4093/jkd.2019.20.1.42

상세보기
Korean Diabetes Association. (2016.03.23). 2015 Treatment Guidelines for Diabetes. Gold Planning. Seoul. https://www.diabetes.or.kr
Ganz, T., Wainstein, J., Gilad, S., Limor, R., Boaz, M., & Stern, N. (2017). Serum asymmetric dimethylarginine and arginine levels predict microvascular and macrovascular complications in type 2 diabetes mellitus. Diabetes/metabolism research and reviews, 33(2), DOI : 10.1002/dmrr.2836

상세보기
American Diabetes Association. (2009). Diagnosis and Classification of Diabetes Mellitus. Diabetes Care. Vol. 32 (Supplement 1) S62-S67; DOI: 10.2337/dc09-S062

상세보기
Hovorka R. (2015). Artificial Pancreas Project at Cambridge 2013. Diabetic medicine : a journal of the British Diabetic Association, 32(8), 987-992. DOI : 10.1111/dme.12766

상세보기
Sudharsan, B., Peeples, M., & Shomali, M. (2015). Hypoglycemia prediction using machine learning models for patients with type 2 diabetes. Journal of diabetes science and technology, 9(1), 86-90. DOI : 10.1177/1932296814554260

상세보기
Zhang, L., Wang, Y., Niu, M., Wang, C., & Wang, Z. (2020). Machine learning for characterizing risk of type 2 diabetes mellitus in a rural Chinese population: the Henan Rural Cohort Study. Scientific reports, 10(1), 4406. DOI : 10.1038/s41598-020-61123-x

상세보기
Plis, K., Bunescu, R.C., Marling, C., Shubrook, J., & Schwartz, F. (2014). A Machine Learning Approach to Predicting Blood Glucose Levels for Diabetes Management. AAAI Workshop: Modern Artificial Intelligence for Health Analytics.
Pustozerov, E., Popova, P., Tkachuk, A., Bolotko, Y., Yuldashev, Z., & Grineva, E. (2018). Development and Evaluation of a Mobile Personalized Blood Glucose Prediction System for Patients With Gestational Diabetes Mellitus. JMIR mHealth and uHealth, 6(1), e6. DOI : 10.2196/mhealth.9236

상세보기
Konstam M. A. (2012). Home monitoring should be the central element in an effective program of heart failure disease management. Circulation, 125(6), 820-827. DOI : 10.1161/CIRCULATIONAHA.111.031161

상세보기
Fye W. B. (1994). A history of the origin, evolution, and impact of electrocardiography. The American journal of cardiology. 73(13). 937-949. DOI : 10.1016/0002-9149(94)90135-x

상세보기
Gordon J. W. (1877). Certain Molar Movements of the Human Body produced by the Circulation of the Blood. Journal of anatomy and physiology, 11(Pt 3), 533-536.
Alvarado-Serrano, C., Luna-Lozano, P.S., & Pallas-Areny, R. (2016). An algorithm for beat-to-beat heart rate detection from the BCG based on the continuous spline wavelet transform. Biomed. Signal Process. Control., 27, 96-102. DOI : 10.1016/j.bspc.2016.02.002.

상세보기
Murata, (2020.09.10). Contactless Bed Sensor, Inertial force Sensor. Murata Manufacturing Co., Ltd. http://www.murata.com/products/sensor/accel/sca10h_11h.
Amos, A. F., McCarty, D. J., & Zimmet, P. (1997). The rising global burden of diabetes and its complications: estimates and projections to the year 2010. Diabetic medicine : a journal of the British Diabetic Association, 14 Suppl 5, S1-S85.
Korean Diabetes Association. (2021.04.05) 2021 Diabetes Treatment Guidelines Guidelines. https://www.diabetes.or.kr/pro/publish/guide.php?modelist
Heinemann, L., & Boecker, D. (2011). Lancing: quo vadis?. Journal of diabetes science and technology, 5(4), 966-981. DOI : 10.1177/193229681100500420

상세보기
Lyandres, O., Yuen, J. M., Shah, N. C., VanDuyne, R. P., Walsh, J. T., & Glucksberg, M. R. (2008). Progress toward an in vivo surface-enhanced Raman spectroscopy glucose sensor. Diabetes technology & therapeutics, 10(4), 257-265. DOI : 10.1089/dia.2007.0288

상세보기
Wahr, J. A., Tremper, K. K., Samra, S., & Delpy, D. T. (1996). Near-infrared spectroscopy: theory and applications. Journal of cardiothoracic and vascular anesthesia, 10(3), 406-418. DOI : 10.1016/s1053-0770(96)80107-8

상세보기
Siesler, Heinz & Ozaki, Yukihiro & Kawata, S. & Heise, Herbert. (2002). Near-Infrared Spectroscopy: Principles, Instruments, Applications. 16. 636-638.
Sbrignadello, Stefano & Tura, Andrea & Ravazzani, Paolo. (2013). Electroimpedance Spectroscopy for the Measurement of the Dielectric Properties of Sodium Chloride Solutions at Different Glucose Concentrations. Journal of Spectroscopy. 2013. DOI : 10.1155/2013/571372.

상세보기
Murata Electronics. (2021.4.15). Acceleration Sensor Modules SCA11H-A01-036 Data Sheet. https://www.murata.com/en-global/products/sensor/accel/overview/lineup/sca10h_11h.
Ministry of Food and Drug Safety. (2019.09.23). Blood glucose monitoring systems, self-testing. https://udiportal.mfds.go.kr/brd/view/P03_01?ntceSn14
Accu-chek Instant. (2019. 3. 21). User's Manual; Blood Glucose Meter. https://www.accu-chekcac.com/en/download/file/fid/13361
Murata Electronics. (2015.11.12). Ballistocaiographic sensors provide contact-less approach to measuring patient vital signs. https://www.murata.com/en-eu/products/info/sensor/accel/2015/1112
Sami Nurmi, (2016). Nocturnal sleep quality and quantity analysis with ballistocardiography. School of Electrical Engineering, Espoo, Finland, 2016.
Sang-Ki, Choi., Geo-Lyong, Lee., (2020). Heart rate monitoring and predictability of diabetes using ballistocardiogram(pilot study). Journal of Digital Convergence. Vol.18. No.8. 231-242. 10.14400/JDC.2020.18.8.231

원문보기 상세보기
Clarke, W. L., Cox, D., Gonder-Frederick, L. A., Carter, W., & Pohl, S. L. (1987). Evaluating clinical accuracy of systems for self-monitoring of blood glucose. Diabetes care, 10(5), 622-628. DOI : 10.2337/diacare.10.5.622

상세보기
Benichou, T., Pereira, B., Mermillod, M., Tauveron, I., Pfabigan, D., Maqdasy, S., & Dutheil, F. (2018). Heart rate variability in type 2 diabetes mellitus: A systematic review and meta-analysis. PloS one, 13(4), e0195166. DOI : 10.1371/journal.pone.0195166

상세보기
Minato, S., Takenouchi, A., Uchida, J., Tsuboi, A., Kurata, M., Fukuo, K., & Kazumi, T. (2017). Association of Whole Blood Viscosity With Metabolic Syndrome in Type 2 Diabetic Patients: Independent Association With Post-Breakfast Triglyceridemia. Journal of clinical medicine research, 9(4), 332-338. DOI : 10.14740/jocmr2885w

상세보기
Ahn, C. W.. (2014). Clinical study for diagnostic efficacy of diabetic angiopathy using hemorheological measurement system (RheoScan). MOHW. Health Technology R&D Project. Yonsei University Industry-Academic Innovation Team
Clarke W. L. (2005). The original Clarke Error Grid Analysis (EGA). Diabetes technology & therapeutics, 7(5), 776-779. DOI : 10.1089/dia.2005.7.776

상세보기

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증