There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.startPage | 107694 | - |
dc.citation.title | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE | - |
dc.citation.volume | 240 | - |
dc.contributor.author | Lim, Min Hyuk | - |
dc.contributor.author | Kim, Sungwan | - |
dc.date.accessioned | 2023-12-21T11:43:07Z | - |
dc.date.available | 2023-12-21T11:43:07Z | - |
dc.date.created | 2023-09-15 | - |
dc.date.issued | 2023-10 | - |
dc.description.abstract | Background and objectives: Complete identification of the glucose dynamics for a patient generally re-quires prior clinical procedures and several measurements for the patient. However, these steps may not be always feasible. To address this limitation, we propose a practical approach integrating learning-based model predictive control (MPC), adaptive basal and bolus injections, and suspension with minimal re-quirements of prior knowledge of the patient. Methods: The glucose dynamic system matrices were periodically updated using only input values, with-out any pretrained models. The optimal insulin dose was calculated based on a learning-based MPC al-gorithm. Meal detection and estimation modules were also introduced. The basal and bolus insulin in-jections were fine-tuned using the performance of glucose control from the previous day. To validate the proposed method, evaluations with 20 virtual patients from a type 1 diabetes metabolic simulator were employed. Results: Time-in-range (TIR) and time-below-range (TBR) were 90.8% (84.1% - 95.6%) and 0.3% (0% - 0.8%), as represented by the median, first (Q1), and third quartiles (Q3), respectively, when meal intakes were fully announced. When one out of three meal intake announcements was missing, TIR and TBR were 85.2% (75.0% - 88.9%) and 0.9% (0.4% - 1.1%), respectively. Conclusions: The proposed approach obviates the need for prior tests from patients and shows effective regulation of blood glucose levels. From the perspective of practical implementation in clinical environ-ments, to deal with minimal prior information of the patient, our study demonstrates how essential clin-ical knowledge and learning-based modules can be integrated into a control framework for an artificial pancreas. & COPY; 2023 Elsevier B.V. All rights reserved. | - |
dc.identifier.bibliographicCitation | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, v.240, pp.107694 | - |
dc.identifier.doi | 10.1016/j.cmpb.2023.107694 | - |
dc.identifier.issn | 0169-2607 | - |
dc.identifier.scopusid | 2-s2.0-85163489864 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/66014 | - |
dc.identifier.wosid | 001031812300001 | - |
dc.language | 영어 | - |
dc.publisher | ELSEVIER IRELAND LTD | - |
dc.title | A practical approach based on learning-based model predictive control with minimal prior knowledge of patients for artificial pancreas | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Interdisciplinary Applications; Computer Science, Theory & Methods; Engineering, Biomedical; Medical Informatics | - |
dc.relation.journalResearchArea | Computer Science; Engineering; Medical Informatics | - |
dc.type.docType | Article | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | Model predictive control | - |
dc.subject.keywordAuthor | Type 1 diabetes mellitus | - |
dc.subject.keywordAuthor | Closed-loop system | - |
dc.subject.keywordAuthor | Blood glucose control | - |
dc.subject.keywordAuthor | Minimal prior tests | - |
dc.subject.keywordPlus | ALGORITHMS | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.