Fault detection of continuous glucose measurements based on modified k-medoids clustering algorithm
- PDF / 902,960 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 89 Downloads / 202 Views
(0123456789().,-volV)(0123456789(). ,- volV)
S.I. : BIO-INSPIRED COMPUTING FOR DLA
Fault detection of continuous glucose measurements based on modified k-medoids clustering algorithm Xia Yu1 • Xiaoyu Sun1 • Yuhang Zhao1 • Jianchang Liu1 • Hongru Li1 Received: 10 August 2020 / Accepted: 7 October 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract As continuous glucose monitoring (CGM) systems provide critical feedback information of blood glucose concentration to the artificial pancreas for patients with type 1 diabetes (T1D), faults in CGM may seriously affect the computation of insulin infusion rates which can lead to fatal consequences accompany with hypoglycemia or hyperglycemia. In the present work, the k-medoids clustering algorithm is modified by calculating cluster number with a Bayesian Information Criterion (BIC)-based cost function and the SAC (SSE-ASW Criterion) evaluation coefficient which considers both SSE (Sum of Square due to Error) and ASW (Average Silhouette Width) criteria. Then, the modified k-medoids clustering algorithm is proposed to detect sensor failures online with CGM measurements. Different from the qualitative model-based methods and quantitative model-based methods, sufficient clean data are the only requirement of the proposed method. During online monitoring, the new glycemic variability is then tracked against predefined confidence limits during training period to indicate abnormality. The feasibility of the proposed method is successfully assessed using CGM data collected from the UVa/Padova metabolic simulator. Keywords Type 1 diabetes Continuous glucose monitoring k-medoids clustering Abnormality detection
1 Introduction Continuous glucose monitoring (CGM) sensors are critical components in the administration of amount of insulin injected to patients with type 1 diabetes (T1D), especially in the closed-loop artificial pancreas (AP) [1–7] control systems which are expected to regulate T1D patients’ blood glucose concentration (BGC) automatically. However, the CGM sensors may not be able to provide accurate information of the actual BGC as a result of losing of sensitivity, dislodging, interruption in signal transmission and pressure on sensor patch area [8]. Erroneous CGM readings may lead to wrong insulin dose, which frequently may cause hypoglycemia or hyperglycemia. Hence, detection of faults and abnormalities in CGM measurements is significant for AP systems.
& Xia Yu [email protected] 1
College of Information Science and Engineering, Northeastern University, Shenyang, China
Fault detection algorithms can be generally divided into three groups: qualitative model-based methods [9], quantitative model-based methods [10–13] and process historical data-based methods [14]. Qualitative methods depend on the expert systems which contain quantities of if–thenelse rules. The rules are designed to mimic the decision process of human experts, and as the expanding of knowledge, the number of if–then-else rules will rapidly increase, meanwhile, some r
Data Loading...
