Detail
Článek
Článek online
FT
Medvik - BMČ
  • Je něco špatně v tomto záznamu ?

Development of a drug early warning scoring model for cardiac arrest using deep learning methods

Hsiao-Ko Chang, Hui-Chih Wang, Chih-Fen Huang, Feipei Lai and Kuo-Chin Huang

. 2021 ; 17 (8) : 1-12.

Status minimální Jazyk angličtina Země Česko

Perzistentní odkaz   https://www.medvik.cz/link/bmc21023541

Background: In most of Taiwan's medical institutions, congestion is a serious problem for emergency departments. Due to a lack of hospital beds, patients spend more time in emergency retention zones, which make it difficult to detect cardiac arrest. Objective: We seek to develop a Drug Early Warning Scoring Model (DEWSM), including drug injections and vital signs as these research important features. We use it to predict cardiac arrest in emergency departments via drug classification and medical experts' suggestion. Methods: We propose this new model for detecting cardiac arrest via drug classification and by using a sliding window, and apply learning-based algorithms to time-series data for a DEWSM. To evaluate the proposed model, we use the area under the receiver operating characteristic curve (AUROC). Results: We identify the two important drug predictors: bits (intravenous therapy), and replenishers and regulators of water and electrolytes (fluid and electrolyte supplement). Weverify feature selection, in which accounting for drugs to improve the accuracy and demonstrate that thus accounting for the drugs significantly affects prediction. Also, we show that CPR events can be predicted four hours before the event. Conclusion: Our study used a sliding window to account for dynamic time-series data consisting of the patient's vital signs and drug injections. The experimental results of adding the drug injections were better than only vital signs. In addition, we using LSTM method as the main processing time series data, it was the bases for comparison of this research.

Citace poskytuje Crossref.org

Bibliografie atd.

Literatura

000      
00000naa a2200000 a 4500
001      
bmc21023541
003      
CZ-PrNML
005      
20211101115648.0
007      
cr|cn|
008      
210928s2021 xr ad fs 000 0|eng||
009      
eAR
024    7_
$a 10.24105/ejbi.2021.17.8.01-12 $2 doi
040    __
$a ABA008 $d ABA008 $e AACR2 $b cze
041    0_
$a eng
044    __
$a xr
100    1_
$a Chang, Hsiao-Ko $u Department of Computer Science & Information Engineering, National Taiwan University, Taipei, Taiwan
245    10
$a Development of a drug early warning scoring model for cardiac arrest using deep learning methods / $c Hsiao-Ko Chang, Hui-Chih Wang, Chih-Fen Huang, Feipei Lai and Kuo-Chin Huang
504    __
$a Literatura
520    9_
$a Background: In most of Taiwan's medical institutions, congestion is a serious problem for emergency departments. Due to a lack of hospital beds, patients spend more time in emergency retention zones, which make it difficult to detect cardiac arrest. Objective: We seek to develop a Drug Early Warning Scoring Model (DEWSM), including drug injections and vital signs as these research important features. We use it to predict cardiac arrest in emergency departments via drug classification and medical experts' suggestion. Methods: We propose this new model for detecting cardiac arrest via drug classification and by using a sliding window, and apply learning-based algorithms to time-series data for a DEWSM. To evaluate the proposed model, we use the area under the receiver operating characteristic curve (AUROC). Results: We identify the two important drug predictors: bits (intravenous therapy), and replenishers and regulators of water and electrolytes (fluid and electrolyte supplement). Weverify feature selection, in which accounting for drugs to improve the accuracy and demonstrate that thus accounting for the drugs significantly affects prediction. Also, we show that CPR events can be predicted four hours before the event. Conclusion: Our study used a sliding window to account for dynamic time-series data consisting of the patient's vital signs and drug injections. The experimental results of adding the drug injections were better than only vital signs. In addition, we using LSTM method as the main processing time series data, it was the bases for comparison of this research.
700    1_
$a Wang, Hui-Chih $u Department of Emergency Medicine, National Taiwan University Hospital, Taipei, Taiwan
700    1_
$a Huang, Chih-Fen $u Department of Pharmacy, National Taiwan University Hospital, Taipei, Taiwan; School of Pharmacy, College of Medicine, National Taiwan University, Taipei, Taiwan
700    1_
$a Lai, Feipei $u Department of Computer Science & Information Engineering, National Taiwan University, Taipei, Taiwan; Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan; Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan
700    1_
$a Huang, Kuo-Chin $u Department of Family Medicine, College of Medicine, National Taiwan University, Taipei, Taiwan; Department of Family Medicine, National Taiwan University Hospital, Taipei, Taiwan
773    0_
$t European journal for biomedical informatics $x 1801-5603 $g Roč. 17, č. 8 (2021), s. 1-12 $w MED00173462
856    41
$u http://www.ejbi.org/ $y domovská stránka časopisu - plný text volně přístupný
910    __
$a ABA008 $b online $y 0 $z 0
990    __
$a 20210927121633 $b ABA008
991    __
$a 20211101120513 $b ABA008
999    __
$a min $b bmc $g 1702514 $s 1144034
BAS    __
$a 3 $a 4
BMC    __
$a 2021 $b 17 $c 8 $d 1-12 $i 1801-5603 $m European Journal for Biomedical Informatics $n Eur. J. Biomed. Inform. (Praha) $x MED00173462
LZP    __
$a NLK 2021-40/dk

Najít záznam

Citační ukazatele

Možnosti archivace