머신러닝 기법을 활용한 유산소 운동 중 혈당 변화 예측 모형
Prediction Models of Blood Glucose Change During Aerobic Exercise Using Machine Learning Techniques
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
PURPOSE: This study aimed to explore the relationship between blood glucose level changes and body characteristics during exercise and to present six models for predicting changes in blood glucose levels during exercise. METHODS: 148 healthy men and women (age: 31.9±9.7 year, fasting blood glucose: 102.1±14.1 mg/dL, p=.032) participated in the study, and 30 of them participated in the study. Eight variables were selected to build two prediction models: 24-hour ingested carbohydrates, age, blood glucose, heart rate changes, sex, skeletal muscle mass, heart rate recovery after exercise, and resting heart rate. Logistic regression and random forest classifier models were used to predict the changes in blood glucose levels during exercise. RESULTS: A total of six models were created for all participants, male and female. Random forest classification (training set: AUC=0.837, Youden index=0.66; validation set: AUC=0.730, Youden index=0.53) and logistic regression classification models (training set: AUC=0.807, Youden index=0.55; validation set: AUC=0.735, Youden index=0.57) were built. CONCLUSION: The random forest model showed good performance in classifying internal data, whereas the logistic regression classification model demonstrated relatively good performance in classifying validation data.
Abstract
PURPOSE: This study aimed to explore the relationship between blood glucose level changes and body characteristics during exercise and to present six models for predicting changes in blood glucose levels during exercise. METHODS: 148 healthy men and women (age: 31.9±9.7 year, fasting blood glucose: 102.1±14.1 mg/dL, p=.032) participated in the study, and 30 of them participated in the study. Eight variables were selected to build two prediction models: 24-hour ingested carbohydrates, age, blood glucose, heart rate changes, sex, skeletal muscle mass, heart rate recovery after exercise, and resting heart rate. Logistic regression and random forest classifier models were used to predict the changes in blood glucose levels during exercise. RESULTS: A total of six models were created for all participants, male and female. Random forest classification (training set: AUC=0.837, Youden index=0.66; validation set: AUC=0.730, Youden index=0.53) and logistic regression classification models (training set: AUC=0.807, Youden index=0.55; validation set: AUC=0.735, Youden index=0.57) were built. CONCLUSION: The random forest model showed good performance in classifying internal data, whereas the logistic regression classification model demonstrated relatively good performance in classifying validation data.
참고문헌 (30)
- Kim HH, "Non-invasive wearable continuous glucose monitoring sensors", Polym Sci and Technol, 31(4), pp.286~290 (2020)
- Park YH, "Introduction of non-invasive blood glucose measurement technology and method using vibration signal", J KSNVE, 29(1), pp.10~14 (2019)
- Gao J, "Simultaneous detection of glucose, uric acid and cholesterol using flexible microneedle electrode array-based biosensor and multi-channel portable electrochemical analyzer", Sensor Actuat B-Chem, (287), pp.102~110 (2019)
- Kopitar L, "Early detection of type 2 diabetes mellitus using machine learning-based prediction models", Sci Rep, 10(1), pp.11981~ (2020)
- Lai H, "Predictive models for diabetes mellitus using machine learning techniques", BMC Endocr Disord, 19(1), pp.1~9 (2019)
- Kourou K, "Machine learning applications in cancer prognosis and prediction", Comp Struct Biotechnol J, 13(1), pp.8~17 (2015)
- Oviedo S, "A review of personalized blood glucose prediction strategies for T1DM patients", Int J Numer Meth Bio, 33(6), pp.e2833~ (2017)
- Colberg SR, "Physical activity", exercise and diabetes : a position statement of the American Diabetes Association, 2016, pp.39(11), 2065~2079
- Faruqui SHA, "Development of a deep learning model for dynamic forecasting of blood glucose level for type 2 diabetes mellitus : secondary analysis of a randomized controlled trial", JMIR Mhealth Uhealth, 7(11), pp.e14452~ (2019)
- Thomas D, "Exercise for type 2 diabetes mellitus", Cochrane Db Syst Rev, (3) (2006)
- Kang SH, "Association between motivation types and anxiety in the patients with diabetes mellitus", Korean Soc Sport Psychol, (3) (2006)
- 서상훈, "Regulation of Blood Glucose Homeostasis during Prolonged Exercise", Molecules and Cells, 23(3), pp.272~279 (2007), 한국분자세포생물학회
- Fluss R, "Estimation of the Youden Index and its associated cutoff point", Biom J : J Math Methods Biosci, 47(4), pp.458~472 (2005)
- Munoz-Organero M, "Deep physiological model for blood glucose prediction in T1DM patients", Sens, 20(14), pp.3896~ (2020)
- Alfian G, "Blood glucose prediction model for type 1 diabetes based on artificial neural network with time-domain features", Biocybern Biomed Eng, 40(4), pp.1586~1599 (2020)
- Kim KK, "The change of bloodsugar level before and after exercise according to percent body fat", Korean Soc Sports Sci, 9(2), pp.705~713 (2000)
- Horton TJ, "Glucose kinetics differ between women and men, during and after exercise", J Appl Physiol, 100(6), pp.1883~1894 (2006)
- Roepstorff C, "Gender differences in substrate utilization during submaximal exercise in endurance-trained subjects", Am J Physiol-Endoc M, 282(2), pp.E435~E447 (2002)
- Wasserman DH, "Interactions between glucagon and other counterregulatory hormones during normoglycemic and hypoglycemic exercise in dogs", J Clin Investig, 74(4), pp.1404~1413 (1984)
- Yashin AI, "Maintaining physiological state for exceptional survival : What is the normal level of blood glucose and does it change with age?", Mech Ageing Dev, 130(9), pp.611~618 (2009)
- Febbraio MA, "Effects of carbohydrate ingestion before and during exercise on glucose kinetics and performance", J Appl Physiol, 89(6), pp.2220~2226 (2000)
- Adams OP, "The impact of brief high-intensity exercise on blood glucose levels", Diabetes Metab Syndr Obes: Targets Ther, 113(22) (2013)
- 조원희, "한국 성인의 안정시 심박수 및 근지구력과 제2형 당뇨 유병률의 관계", 운동과학, 26(4), pp.259~266 (2017), 한국운동생리학회[DOI]
- Lee DH, "Resting heart rate and risk of type 2 diabetes : a prospective cohort study and meta-analysis", Diabetes Metab Res Rev, 5(2), pp.e3095~ (2019)
- Ito C, "Correlation among fasting plasma glucose, two-hour plasma glucose levels in OGTT and HbA1c", Diabetes Res Clin Pract, 50(3), pp.225~230 (2000)
- Karnchanasorn R, "Comparison of the current diagnostic criterion of HbA1c with fasting and 2-hour plasma glucose concentration", J Diabetes Res, pp.6195494~ (2016)
- Hoeks LBEA, "Real-time continuous glucose monitoring system for treatment for diabetes : a systematic review", Diab Med, 28, pp.386~394 (2010)
- Akiba T, "Optuna: A next-generation hyperparameter optimization framework", Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp.2623~2631 (2019)
- Kopitar L, "Early detection of type 2 diabetes mellitus using machine learning-based prediction models", Scientific Reports, 10, pp.11981~ (2020)
- Krittanawong C, "Machine learning prediction in cardiovascular diseases: a meta-analysis", Scientific Reports, 10(1), pp.16057~ (2020)