Xia Yu1, Ning Ma1, Tao Yang1, Yawen Zhang2, Qing Miao2, Junjun Tao2, Hongru Li1, Yiming Li2, Yehong Yang3. 1. College of Information Science and Engineering, Northeastern University, Shenyang, 110819, China. 2. Department of Endocrinology and Metabolism, Huashan Hospital, Fudan University, Shanghai, 200040, China. 3. Department of Endocrinology and Metabolism, Huashan Hospital, Fudan University, Shanghai, 200040, China. yehongyang@fudan.edu.cn.
Abstract
BACKGROUND: Early alarm of hypoglycemia, detection of asymptomatic hypoglycemia, and effective control of blood glucose fluctuation make a great contribution to diabetic treatment. In this study, we designed a multi-level hypoglycemia early alarm system to mine potential information in Continuous Glucose Monitoring (CGM) time series and improve the overall alarm performance for different clinical situations. METHODS: Through symbolizing the historical CGM records, the Prefix Span was adopted to obtain the early alarm/non-alarm frequent sequence libraries of hypoglycemia events. The longest common subsequence was used to remove the common frequent sequence for achieving the hypoglycemia early alarm in different clinical situations. Then, the frequent sequence pattern libraries with different risk thresholds were designed as the core module of the proposed multi-level hypoglycemia early alarm system. RESULTS: The model was able to predict hypoglycemia events in the clinical dataset of level-I (sensitivity 85.90%, false-positive 23.86%, miss alarm rate 14.10%, average early alarm time 20.61 min), level-II (sensitivity 80.36%, false-positive 17.37%, miss alarm rate 19.63%, average early alarm time 27.66 min), and level-III (sensitivity 78.07%, false-positive 13.59%, miss alarm rate 21.93%, average early alarm time 33.80 min), respectively. CONCLUSIONS: The proposed approach could effectively predict hypoglycemia events based on different risk thresholds to meet different prevention and treatment requirements. Moreover, the experimental results confirm the practicality and prospects of the proposed early alarm system, which reflects further significance in personalized medicine for hypoglycemia prevention.
BACKGROUND: Early alarm of hypoglycemia, detection of asymptomatic hypoglycemia, and effective control of blood glucose fluctuation make a great contribution to diabetic treatment. In this study, we designed a multi-level hypoglycemia early alarm system to mine potential information in Continuous Glucose Monitoring (CGM) time series and improve the overall alarm performance for different clinical situations. METHODS: Through symbolizing the historical CGM records, the Prefix Span was adopted to obtain the early alarm/non-alarm frequent sequence libraries of hypoglycemia events. The longest common subsequence was used to remove the common frequent sequence for achieving the hypoglycemia early alarm in different clinical situations. Then, the frequent sequence pattern libraries with different risk thresholds were designed as the core module of the proposed multi-level hypoglycemia early alarm system. RESULTS: The model was able to predict hypoglycemia events in the clinical dataset of level-I (sensitivity 85.90%, false-positive 23.86%, miss alarm rate 14.10%, average early alarm time 20.61 min), level-II (sensitivity 80.36%, false-positive 17.37%, miss alarm rate 19.63%, average early alarm time 27.66 min), and level-III (sensitivity 78.07%, false-positive 13.59%, miss alarm rate 21.93%, average early alarm time 33.80 min), respectively. CONCLUSIONS: The proposed approach could effectively predict hypoglycemia events based on different risk thresholds to meet different prevention and treatment requirements. Moreover, the experimental results confirm the practicality and prospects of the proposed early alarm system, which reflects further significance in personalized medicine for hypoglycemia prevention.
Authors: Amelia J Cook; Stephanie N DuBose; Nicole Foster; Emma L Smith; Mengdi Wu; Georgina Margiotta; Michael R Rickels; Jane Speight; Nicole de Zoysa; Stephanie A Amiel Journal: Diabetes Care Date: 2019-08-07 Impact factor: 19.112
Authors: Eyal Dassau; Fraser Cameron; Hyunjin Lee; B Wayne Bequette; Howard Zisser; Lois Jovanovic; H Peter Chase; Darrell M Wilson; Bruce A Buckingham; Francis J Doyle Journal: Diabetes Care Date: 2010-06 Impact factor: 17.152
Authors: Bruce Buckingham; Erin Cobry; Paula Clinton; Victoria Gage; Kimberly Caswell; Elizabeth Kunselman; Fraser Cameron; H Peter Chase Journal: Diabetes Technol Ther Date: 2009-02 Impact factor: 6.118
Authors: Mary B Abraham; Jennifer A Nicholas; Grant J Smith; Janice M Fairchild; Bruce R King; Geoffrey R Ambler; Fergus J Cameron; Elizabeth A Davis; Timothy W Jones Journal: Diabetes Care Date: 2017-11-30 Impact factor: 19.112