A multi-level hypoglycemia early alarm system based on sequence pattern mining

• Published in: BMC medical informatics and decision making Vol. 21; no. 1; pp. 22 - 11
• Main Authors: Yu, Xia, Ma, Ning, Yang, Tao, Zhang, Yawen, Miao, Qing, Tao, Junjun, Li, Hongru, Li, Yiming, Yang, Yehong
• Format: Journal Article
• Language: English
• Published: London BioMed Central 21.01.2021; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Accuracy; Alarm systems; Algorithms; Analysis; Blood Glucose; Blood Glucose Self-Monitoring; Blood sugar monitoring; Care and treatment; Data mining; Dengue fever; Diabetes; Diabetes mellitus; Diabetes Mellitus, Type 1; Diagnosis; Evaluation; Explainable AI in Medical Informatics and Decision Support; Glucose; Glucose monitoring; Health Informatics; Humans; Hyperglycemia; Hypoglycemia; Hypoglycemia - diagnosis; Hypoglycemia early alarm; Information Systems and Communication Service; Machine learning; Management of Computing and Information Systems; Medicine; Medicine & Public Health; modeling; Monitoring, Ambulatory; Pattern analysis; Precision medicine; Prefix span; Prevention; Research Article; Sensitivity; Sequential pattern mining; technology; Thresholds; China; Prefix span; Hypoglycemia early alarm; Diabetes mellitus; Sequential pattern mining
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/s12911-021-01389-x

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.