15 23

Cited 0 times in

Early Detection of Bacteraemia Using Ten Clinical Variables with an Artificial Neural Network Approach

DC FieldValueLanguage
dc.contributor.author송영구-
dc.contributor.author정수진-
dc.contributor.author이경화-
dc.contributor.author동재준-
dc.date.accessioned2019-10-28T02:07:39Z-
dc.date.available2019-10-28T02:07:39Z-
dc.date.issued2019-
dc.identifier.urihttps://ir.ymlib.yonsei.ac.kr/handle/22282913/171500-
dc.description.abstractAn adequate model for predicting bacteraemia has not yet been developed. This study aimed to evaluate the performance of an artificial neural network (ANN)-based prediction model in comparison with previous statistical models. The performance of multi-layer perceptron (MLP), a representative ANN model, was verified via comparison with a non-neural network model. A total of 1260 bacteraemia episodes were identified in 13,402 patients. In MLP with 128 hidden layer nodes, the area under the receiver operating characteristic curve (AUC) of the prediction performance was 0.729 (95% confidence interval [CI]; 0.712-0.728), while in MLP with 256 hidden layer nodes, it was 0.727 (95% CI; 0.713-0.727). In a conventional Bayesian statistical method, the AUC was 0.7. The aforementioned two MLP models exhibited the highest sensitivity (0.810). The ranking of clinical variables was used to describe the influential power of the prediction. Serum alkaline phosphatase was one of the most influential clinical variables, and one-out search was the best ranking method for measuring the influence of the clinical variables. Furthermore, adding variables beyond the 10 top-ranking ones did not significantly affect the prediction of bacteraemia. The ANN model is not inferior to conventional statistical approaches. Bacteraemia can be predicted using only the top 10 clinical variables determined by a ranking method, and the model can be used in clinical practice by applying real-time monitoring.-
dc.description.statementOfResponsibilityopen-
dc.languageEnglish-
dc.publisherMDPI AG-
dc.relation.isPartOfJournal of Clinical Medicine-
dc.rightsCC BY-NC-ND 2.0 KR-
dc.titleEarly Detection of Bacteraemia Using Ten Clinical Variables with an Artificial Neural Network Approach-
dc.typeArticle-
dc.contributor.collegeCollege of Medicine (의과대학)-
dc.contributor.departmentDept. of Internal Medicine (내과학교실)-
dc.contributor.googleauthorKyoung Hwa Lee-
dc.contributor.googleauthorJae June Dong-
dc.contributor.googleauthorSu Jin Jeong-
dc.contributor.googleauthorMyeong-Hun Chae-
dc.contributor.googleauthorByeong Soo Lee-
dc.contributor.googleauthorHong Jae Kim-
dc.contributor.googleauthorSung Hun Ko-
dc.contributor.googleauthorYoung Goo Song-
dc.identifier.doi10.3390/jcm8101592-
dc.contributor.localIdA02037-
dc.contributor.localIdA03638-
dc.contributor.localIdA03638-
dc.contributor.localIdA04620-
dc.contributor.localIdA04620-
dc.contributor.localIdA04927-
dc.contributor.localIdA04927-
dc.relation.journalcodeJ03556-
dc.identifier.eissn2077-0383-
dc.identifier.pmid31581716-
dc.subject.keywordartificial intelligence-
dc.subject.keywordartificial neural network-
dc.subject.keywordbacteraemia-
dc.subject.keywordmachine learning-
dc.subject.keywordprediction-
dc.contributor.alternativeNameSong, Young Goo-
dc.contributor.affiliatedAuthor송영구-
dc.contributor.affiliatedAuthor정수진-
dc.contributor.affiliatedAuthor정수진-
dc.contributor.affiliatedAuthor이경화-
dc.contributor.affiliatedAuthor이경화-
dc.contributor.affiliatedAuthor동재준-
dc.contributor.affiliatedAuthor동재준-
dc.citation.volume8-
dc.citation.number10-
dc.citation.startPageE1592-
dc.identifier.bibliographicCitationJournal of Clinical Medicine, Vol.8(10) : E1592, 2019-
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Internal Medicine (내과학교실) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Family Medicine (가정의학교실) > 1. Journal Papers

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.