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 the treatment for diabetic patients. In this study, we designed a multi-level hypoglycemia early alarm system to improve the overall performance of hypoglycemia early alarm. Methods: Through symbolizing the historical CGM data, the Prefix Span was adopted to obtain the early alarm and non-alarm frequent sequence libraries of hypoglycemia. The longest common subsequence was used to remove the common frequent sequence for achieving the hypoglycemia early alarm on the clinical dataset. Frequent sequence pattern libraries with different risk levels were designed by choosing different thresholds and a multi-level hypoglycemia early alarm system for different clinical situations were established. 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 20.61min), level-II (sensitivity 80.36%, false-positive 17.37%, miss alarm rate 19.63%, average early alarm time 27.66min), and level-III (sensitivity 78.07%, false-positive 13.59%, miss alarm rate 21.93%, average early alarm time 33.80min), respectively.Conclusions: The proposed approach could effectively predict hypoglycemia events on the basis of different thresholds to meet different prevention and treatment requirements in clinical situations. 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.

Download Full-text

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

BMC Medical Informatics and Decision Making ◽

10.1186/s12911-021-01389-x ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Xia Yu ◽

Ning Ma ◽

Tao Yang ◽

Yawen Zhang ◽

Qing Miao ◽

...

Keyword(s):

False Positive ◽

Pattern Mining ◽

Glucose Monitoring ◽

Longest Common Subsequence ◽

Effective Control ◽

Alarm System ◽

Sequence Pattern ◽

Frequent Sequence ◽

Multi Level ◽

Risk Thresholds

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.

Download Full-text

Frequent Sequence Pattern Mining with Differential Privacy

Intelligent Computing Theories and Application - Lecture Notes in Computer Science ◽

10.1007/978-3-319-95930-6_42 ◽

2018 ◽

pp. 454-466 ◽

Cited By ~ 1

Author(s):

Fengli Zhou ◽

Xiaoli Lin

Keyword(s):

Pattern Mining ◽

Differential Privacy ◽

Sequence Pattern ◽

Frequent Sequence

Download Full-text

Constructing A Novel Spark-based Distributed Maximum Frequent Sequence Pattern Mining for IoT Log

Proceedings of the 8th International Conference on Communication and Network Security - ICCNS 2018 ◽

10.1145/3290480.3290497 ◽

2018 ◽

Author(s):

Xiong Chen ◽

Ruliang Xiao ◽

Du Xin ◽

Xinhong Lin ◽

Li Lin

Keyword(s):

Pattern Mining ◽

Sequence Pattern ◽

Frequent Sequence

Download Full-text

Multi-level 3D Densenets for False-positive Reduction in Lung Nodule Detection Based on Chest Computed Tomography

Current Medical Imaging Formerly Current Medical Imaging Reviews ◽

10.2174/1573405615666191113122840 ◽

2020 ◽

Vol 16 (8) ◽

pp. 1004-1021

Author(s):

Xiaoqi Lu ◽

Yu Gu ◽

Lidong Yang ◽

Baohua Zhang ◽

Ying Zhao ◽

...

Keyword(s):

False Positive ◽

Contextual Information ◽

Lung Nodule ◽

Positive Sample ◽

Lung Nodules ◽

Lung Nodule Detection ◽

Nodule Detection ◽

Level Information ◽

Multi Level ◽

Cade System

Objective: False-positive nodule reduction is a crucial part of a computer-aided detection (CADe) system, which assists radiologists in accurate lung nodule detection. In this research, a novel scheme using multi-level 3D DenseNet framework is proposed to implement false-positive nodule reduction task. Methods: Multi-level 3D DenseNet models were extended to differentiate lung nodules from falsepositive nodules. First, different models were fed with 3D cubes with different sizes for encoding multi-level contextual information to meet the challenges of the large variations of lung nodules. In addition, image rotation and flipping were utilized to upsample positive samples which consisted of a positive sample set. Furthermore, the 3D DenseNets were designed to keep low-level information of nodules, as densely connected structures in DenseNet can reuse features of lung nodules and then boost feature propagation. Finally, the optimal weighted linear combination of all model scores obtained the best classification result in this research. Results: The proposed method was evaluated with LUNA16 dataset which contained 888 thin-slice CT scans. The performance was validated via 10-fold cross-validation. Both the Free-response Receiver Operating Characteristic (FROC) curve and the Competition Performance Metric (CPM) score show that the proposed scheme can achieve a satisfactory detection performance in the falsepositive reduction track of the LUNA16 challenge. Conclusion: The result shows that the proposed scheme can be significant for false-positive nodule reduction task.

Download Full-text

Piroxicam reduces acute and chronic pain response in type 1 diabetic rats

Journal of Basic and Clinical Physiology and Pharmacology ◽

10.1515/jbcpp-2019-0367 ◽

2021 ◽

Vol 0 (0) ◽

Author(s):

Abbas Alimoradian ◽

Fatemeh Samimi ◽

Hadise Aslfalah ◽

Seied Amirhossein Latifi ◽

Mehdi Salehi ◽

...

Keyword(s):

Chronic Pain ◽

Normal Saline ◽

Life Quality ◽

Chronic Phase ◽

Diabetic Rats ◽

Effective Control ◽

Diabetic Patients ◽

Formalin Injection ◽

Analgesic Effects

Abstract Objectives Pain associated with various underlying pathologies is a major cause of morbidity and diminished life quality in diabetic patients. Effective control of pain requires the use of analgesics with the best efficacy and with minimal side effects. Therefore, our aim in this study was to investigate the effects of non-steroidal anti-inflammatory drugs (NSAIDs) on pain in diabetic rats. Methods In this study, we investigated the analgesic effects of drugs belonging to three different classes of NSAIDs in a rat model of diabetes. Four diabetic groups received normal saline, diclofenac, piroxicam and ketorolac, respectively, and four non-diabetic groups received normal saline, diclofenac, piroxicam and ketorolac. Type 1 diabetes was induced in rats by a single injection of streptozotocin (60 mg/kg bw). Formalin (50 µL of 2.5%) nociception assay was used to examine the effect of treatment with diclofenac, piroxicam and ketorolac on acute and chronic pain in healthy and diabetic rats. Results Piroxicam showed significant analgesic effects both in the acute phase of pain (5–10 min after injection of formalin into the left hind paw), and in the chronic phase (20–60 min after formalin injection) in healthy as well as diabetic rats. Diclofenac and ketorolac also reduced pain scores in healthy rats. However, these two drugs failed to diminish pain in diabetic rats. Conclusion Our data point for better efficacy of piroxicam in controlling pain in diabetes.

Download Full-text

An Efficient Weighted Negative Sequence Pattern Mining Algorithm with Multiple Minimum Support

Advances in Intelligent Systems and Computing - International Conference on Applications and Techniques in Cyber Intelligence ATCI 2019 ◽

10.1007/978-3-030-25128-4_58 ◽

2019 ◽

pp. 460-469

Author(s):

Dongyuan Wang ◽

He Jiang ◽

Aixin Yang

Keyword(s):

Pattern Mining ◽

Sequence Pattern ◽

Negative Sequence ◽

Minimum Support ◽

Mining Algorithm

Download Full-text

Batch-Free Event Sequence Pattern Mining for Communication Stream Data with Instant and Persistent Events

Wireless Personal Communications ◽

10.1007/s11277-018-5985-x ◽

2018 ◽

Vol 105 (2) ◽

pp. 673-689 ◽

Cited By ~ 1

Author(s):

Keon Myung Lee ◽

Chan Sik Han ◽

Joong Nam Jun ◽

Jee Hyong Lee ◽

Sang Ho Lee

Keyword(s):

Pattern Mining ◽

Event Sequence ◽

Stream Data ◽

Sequence Pattern

Download Full-text

Examining and investigating the impact of demographic characteristics and chronic diseases on mortality of COVID-19: Retrospective study

PLoS ONE ◽

10.1371/journal.pone.0257131 ◽

2021 ◽

Vol 16 (9) ◽

pp. e0257131

Author(s):

Abbas Al Mutair ◽

Alya Al Mutairi ◽

Saad Alhumaid ◽

Syed Maaz Abdullah ◽

Abdul Rehman Zia Zaidi ◽

...

Keyword(s):

Diabetes Mellitus ◽

Saudi Arabia ◽

Binary Logistic Regression ◽

Demographic Characteristics ◽

Control Measures ◽

Effective Control ◽

Diabetic Patients ◽

History Of ◽

And Gender ◽

The Impact

Background Epidemiological features characterization of COVID-19 is highly important for developing and implementing effective control measures. In Saudi Arabia mortality rate varies between 0.6% to 1.26%. The purpose of the study was to investigate whether demographic characteristics (age and gender) and non-communicable diseases (Hypertension and Diabetes mellitus) have a significant association with mortality in COVID-19 patients. Methods Prior to data collection, an expedite approval was obtained from Institutional Review Board (IRB Log No: RC. RC20.09.10) in Al Habib Research Center at Dr. Sulaiman Al-Habib Medical Group, Riyadh, Saudi Arabia. This is a retrospective design where we used descriptive and inferential analysis to analyse the data. Binary logistic regression was done to study the association between comorbidities and mortality of COVID-19. Results 43 (86%) of the male patients were non-survivors while 7 (14%) of the female patients were survivors. The odds of non-survivors among hypertensive patients are 3.56 times higher than those who are not having a history of Hypertension (HTN). The odds of non-survivors among diabetic patients are 5.17 times higher than those who are not having a history of Diabetes mellitus (DM). The odds of non-survivors are 2.77 times higher among those who have a history of HTN and DM as compared to those who did not have a history of HTN and DM. Conclusions Those patients that had a history of Hypertension and Diabetes had a higher probability of non-survival in contrast to those who did not have a history of Diabetes and hypertension. Further studies are required to study the association of comorbidities with COVID-19 and mortality.

Download Full-text