• Something wrong with this record ?

Control of Blood Glucose for Type-1 Diabetes by Using Reinforcement Learning with Feedforward Algorithm

PD. Ngo, S. Wei, A. Holubová, J. Muzik, F. Godtliebsen,

. 2018 ; 2018 (-) : 4091497. [pub] 20181230

Language English Country United States

Document type Evaluation Study, Journal Article

Background: Type-1 diabetes is a condition caused by the lack of insulin hormone, which leads to an excessive increase in blood glucose level. The glucose kinetics process is difficult to control due to its complex and nonlinear nature and with state variables that are difficult to measure. Methods: This paper proposes a method for automatically calculating the basal and bolus insulin doses for patients with type-1 diabetes using reinforcement learning with feedforward controller. The algorithm is designed to keep the blood glucose stable and directly compensate for the external events such as food intake. Its performance was assessed using simulation on a blood glucose model. The usage of the Kalman filter with the controller was demonstrated to estimate unmeasurable state variables. Results: Comparison simulations between the proposed controller with the optimal reinforcement learning and the proportional-integral-derivative controller show that the proposed methodology has the best performance in regulating the fluctuation of the blood glucose. The proposed controller also improved the blood glucose responses and prevented hypoglycemia condition. Simulation of the control system in different uncertain conditions provided insights on how the inaccuracies of carbohydrate counting and meal-time reporting affect the performance of the control system. Conclusion: The proposed controller is an effective tool for reducing postmeal blood glucose rise and for countering the effects of external known events such as meal intake and maintaining blood glucose at a healthy level under uncertainties.

References provided by Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc19011946
003      
CZ-PrNML
005      
20190411101001.0
007      
ta
008      
190405s2018 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1155/2018/4091497 $2 doi
035    __
$a (PubMed)30693047
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Ngo, Phuong D $u UiT The Arctic University of Norway, Tromsø, Norway.
245    10
$a Control of Blood Glucose for Type-1 Diabetes by Using Reinforcement Learning with Feedforward Algorithm / $c PD. Ngo, S. Wei, A. Holubová, J. Muzik, F. Godtliebsen,
520    9_
$a Background: Type-1 diabetes is a condition caused by the lack of insulin hormone, which leads to an excessive increase in blood glucose level. The glucose kinetics process is difficult to control due to its complex and nonlinear nature and with state variables that are difficult to measure. Methods: This paper proposes a method for automatically calculating the basal and bolus insulin doses for patients with type-1 diabetes using reinforcement learning with feedforward controller. The algorithm is designed to keep the blood glucose stable and directly compensate for the external events such as food intake. Its performance was assessed using simulation on a blood glucose model. The usage of the Kalman filter with the controller was demonstrated to estimate unmeasurable state variables. Results: Comparison simulations between the proposed controller with the optimal reinforcement learning and the proportional-integral-derivative controller show that the proposed methodology has the best performance in regulating the fluctuation of the blood glucose. The proposed controller also improved the blood glucose responses and prevented hypoglycemia condition. Simulation of the control system in different uncertain conditions provided insights on how the inaccuracies of carbohydrate counting and meal-time reporting affect the performance of the control system. Conclusion: The proposed controller is an effective tool for reducing postmeal blood glucose rise and for countering the effects of external known events such as meal intake and maintaining blood glucose at a healthy level under uncertainties.
650    12
$a algoritmy $7 D000465
650    _2
$a krevní glukóza $x metabolismus $7 D001786
650    _2
$a počítačová simulace $7 D003198
650    _2
$a diabetes mellitus 1. typu $x krev $x farmakoterapie $7 D003922
650    _2
$a lidé $7 D006801
650    _2
$a inzulin $x aplikace a dávkování $7 D007328
650    _2
$a kinetika $7 D007700
650    _2
$a biologické modely $7 D008954
650    _2
$a posilování (psychologie) $7 D012054
650    _2
$a počítačem asistovaná terapie $x statistika a číselné údaje $7 D013813
655    _2
$a hodnotící studie $7 D023362
655    _2
$a časopisecké články $7 D016428
700    1_
$a Wei, Susan $u The University of Melbourne, Australia.
700    1_
$a Holubová, Anna $u Czech Technical University, Prague, Czech Republic.
700    1_
$a Muzik, Jan $u Czech Technical University, Prague, Czech Republic.
700    1_
$a Godtliebsen, Fred $u UiT The Arctic University of Norway, Tromsø, Norway.
773    0_
$w MED00173439 $t Computational and mathematical methods in medicine $x 1748-6718 $g Roč. 2018, č. - (2018), s. 4091497
856    41
$u https://pubmed.ncbi.nlm.nih.gov/30693047 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y a $z 0
990    __
$a 20190405 $b ABA008
991    __
$a 20190411101018 $b ABA008
999    __
$a ok $b bmc $g 1391256 $s 1050251
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2018 $b 2018 $c - $d 4091497 $e 20181230 $i 1748-6718 $m Computational and mathematical methods in medicine $n Comput Math Methods Med $x MED00173439
LZP    __
$a Pubmed-20190405

Find record

Citation metrics

Loading data ...

Archiving options

Loading data ...