A multi-level hypoglycemia early alarm system based on sequence pattern mining
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 Conti...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-01-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-021-01389-x |
| _version_ | 1818665070865940480 |
|---|---|
| author | Xia Yu Ning Ma Tao Yang Yawen Zhang Qing Miao Junjun Tao Hongru Li Yiming Li Yehong Yang |
| author_facet | Xia Yu Ning Ma Tao Yang Yawen Zhang Qing Miao Junjun Tao Hongru Li Yiming Li Yehong Yang |
| author_sort | Xia Yu |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-17T05:42:48Z |
| format | Article |
| id | doaj.art-797406a4417a4874ab70eda36e9cd083 |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-12-17T05:42:48Z |
| publishDate | 2021-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-797406a4417a4874ab70eda36e9cd0832022-12-21T22:01:23ZengBMCBMC Medical Informatics and Decision Making1472-69472021-01-0121111110.1186/s12911-021-01389-xA multi-level hypoglycemia early alarm system based on sequence pattern miningXia Yu0Ning Ma1Tao Yang2Yawen Zhang3Qing Miao4Junjun Tao5Hongru Li6Yiming Li7Yehong Yang8College of Information Science and Engineering, Northeastern UniversityCollege of Information Science and Engineering, Northeastern UniversityCollege of Information Science and Engineering, Northeastern UniversityDepartment of Endocrinology and Metabolism, Huashan Hospital, Fudan UniversityDepartment of Endocrinology and Metabolism, Huashan Hospital, Fudan UniversityDepartment of Endocrinology and Metabolism, Huashan Hospital, Fudan UniversityCollege of Information Science and Engineering, Northeastern UniversityDepartment of Endocrinology and Metabolism, Huashan Hospital, Fudan UniversityDepartment of Endocrinology and Metabolism, Huashan Hospital, Fudan UniversityAbstract 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.https://doi.org/10.1186/s12911-021-01389-xHypoglycemia early alarmSequential pattern miningPrefix spanDiabetes mellitus |
| spellingShingle | Xia Yu Ning Ma Tao Yang Yawen Zhang Qing Miao Junjun Tao Hongru Li Yiming Li Yehong Yang A multi-level hypoglycemia early alarm system based on sequence pattern mining BMC Medical Informatics and Decision Making Hypoglycemia early alarm Sequential pattern mining Prefix span Diabetes mellitus |
| title | A multi-level hypoglycemia early alarm system based on sequence pattern mining |
| title_full | A multi-level hypoglycemia early alarm system based on sequence pattern mining |
| title_fullStr | A multi-level hypoglycemia early alarm system based on sequence pattern mining |
| title_full_unstemmed | A multi-level hypoglycemia early alarm system based on sequence pattern mining |
| title_short | A multi-level hypoglycemia early alarm system based on sequence pattern mining |
| title_sort | multi level hypoglycemia early alarm system based on sequence pattern mining |
| topic | Hypoglycemia early alarm Sequential pattern mining Prefix span Diabetes mellitus |
| url | https://doi.org/10.1186/s12911-021-01389-x |
| work_keys_str_mv | AT xiayu amultilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT ningma amultilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT taoyang amultilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT yawenzhang amultilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT qingmiao amultilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT junjuntao amultilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT hongruli amultilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT yimingli amultilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT yehongyang amultilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT xiayu multilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT ningma multilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT taoyang multilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT yawenzhang multilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT qingmiao multilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT junjuntao multilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT hongruli multilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT yimingli multilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining AT yehongyang multilevelhypoglycemiaearlyalarmsystembasedonsequencepatternmining |