XGBoost machine learning algorithm for differential diagnosis of pediatric syncope

The search for new methods of differential diagnosis of syncope types will allow to improve the diagnosis of vasovagal syncope (VVS), syncope due to orthostatic hypotension (OH) and cardiac syncope (CS) in childhood in order to make timely adequate diagnostic and therapeutic decisions. The aim of th...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Journal of V.N. Karazin Kharkiv National University. Series "Medicine" (Online) H. 47; S. 33 - 46
Hauptverfasser: Kovalchuk, Tetiana, Boyarchuk, Oksana, Bogai, Sviatoslav
Format: Journal Article
Sprache:Englisch
Veröffentlicht: 28.11.2023
ISSN:2313-6693, 2313-2396
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The search for new methods of differential diagnosis of syncope types will allow to improve the diagnosis of vasovagal syncope (VVS), syncope due to orthostatic hypotension (OH) and cardiac syncope (CS) in childhood in order to make timely adequate diagnostic and therapeutic decisions. The aim of the study was to develop an effective machine learning model for the differential diagnosis of VVS, syncope due to OH and CS in children. Materials and Methods. 140 patients with syncope, aged 8-17 years, were examined: 92 children with a diagnosis of VVS, 28 children with syncope due to OH and 20 children with CS. A machine learning model was built using XGBoost algorithm for multiclass classification based on input clinical, laboratory and instrumental patient data. Results. The developed machine learning model based on the XGBoost algorithm is effective in the differential diagnosis of VVS, syncope due to OH and CS, which is confirmed by the metrics of accuracy (0.93), precision (0.93 for VVS; 1.00 for syncope due to OH; 0.80 for CS), recall (0.96 for VVS; 1.00 for syncope due to OH; 0.67 for CS), f1 (0.95 for VVS; 1.00 for syncope due to OH; 0.73 for CS), ROC AUC (0.95 for VVS; 1.00 for syncope due to OH; 0.89 for CS), PR AUC (0.96 for VVS; 1.00 for syncope due to OH; 0.79 for CS),Cohen’s Kappa (0.85), and Matthews correlation coefficient (0.85). The most informative parameters of the syncope types differential diagnosis model are OH, paroxysmal supraventricular tachycardia, Hildebrandt coefficient, Calgary Syncope Seizure Score, vitamin B6, average duration of the P-Q interval during 24 hours, duration of tachycardia during 24 hours, stroke index, homocysteine, heart volume, and systolic blood volume. Conclusions. The proposed machine learning model has sufficient efficiency and can be used by pediatricians and pediatric cardiologists for the differential diagnosis of VS, syncope due to OH, and CS in childhood.
AbstractList The search for new methods of differential diagnosis of syncope types will allow to improve the diagnosis of vasovagal syncope (VVS), syncope due to orthostatic hypotension (OH) and cardiac syncope (CS) in childhood in order to make timely adequate diagnostic and therapeutic decisions. The aim of the study was to develop an effective machine learning model for the differential diagnosis of VVS, syncope due to OH and CS in children. Materials and Methods. 140 patients with syncope, aged 8-17 years, were examined: 92 children with a diagnosis of VVS, 28 children with syncope due to OH and 20 children with CS. A machine learning model was built using XGBoost algorithm for multiclass classification based on input clinical, laboratory and instrumental patient data. Results. The developed machine learning model based on the XGBoost algorithm is effective in the differential diagnosis of VVS, syncope due to OH and CS, which is confirmed by the metrics of accuracy (0.93), precision (0.93 for VVS; 1.00 for syncope due to OH; 0.80 for CS), recall (0.96 for VVS; 1.00 for syncope due to OH; 0.67 for CS), f1 (0.95 for VVS; 1.00 for syncope due to OH; 0.73 for CS), ROC AUC (0.95 for VVS; 1.00 for syncope due to OH; 0.89 for CS), PR AUC (0.96 for VVS; 1.00 for syncope due to OH; 0.79 for CS),Cohen’s Kappa (0.85), and Matthews correlation coefficient (0.85). The most informative parameters of the syncope types differential diagnosis model are OH, paroxysmal supraventricular tachycardia, Hildebrandt coefficient, Calgary Syncope Seizure Score, vitamin B6, average duration of the P-Q interval during 24 hours, duration of tachycardia during 24 hours, stroke index, homocysteine, heart volume, and systolic blood volume. Conclusions. The proposed machine learning model has sufficient efficiency and can be used by pediatricians and pediatric cardiologists for the differential diagnosis of VS, syncope due to OH, and CS in childhood.
Author Bogai, Sviatoslav
Boyarchuk, Oksana
Kovalchuk, Tetiana
Author_xml – sequence: 1
  givenname: Tetiana
  orcidid: 0000-0003-2455-3278
  surname: Kovalchuk
  fullname: Kovalchuk, Tetiana
  organization: I. Horbachevsky Ternopil National Medical University, Ternopil, Ukraine
– sequence: 2
  givenname: Oksana
  orcidid: 0000-0002-1234-0040
  surname: Boyarchuk
  fullname: Boyarchuk, Oksana
  organization: I. Horbachevsky Ternopil National Medical University, Ternopil, Ukraine
– sequence: 3
  givenname: Sviatoslav
  surname: Bogai
  fullname: Bogai, Sviatoslav
  organization: it-specialist, Ternopil, Ukraine
BookMark eNotkM1KQzEUhINUsNY-gpAXiCYnfzdLLVqFgiBduAtpmrSR26Qkd9O3t7d2dWaG4cA392iSSw4IPTL6BEoq-QyccaKU4QQocCI0oeIGTS8xcKMmVz1W7tC8tV9KKYBQoqNT9P2zfC2lDfjg_D7lgPvgak55h12_KzUN-wOOpeJtijHUkIfk-rNxu1xaarhEfAxnO9TkcTtlX47hAd1G17cwv94ZWr-_rRcfZPW1_Fy8rIg3XBBtjNNRe6mBsTOIN04qYM6Al1FwwULoIucdF1uqXAcQqdSbjXLUsy7Cls-Q_H_ra2mthmiPNR1cPVlG7WUaO3LbkduO01ihLRX8D-ATWLw
Cites_doi 10.1155/2022/1858300
10.1161/cir.0000000000000499
10.1093/europace/euaa370
10.1007/s10072-016-2740-5
10.1016/j.pcl.2020.05.004
10.1111/joim.12852
10.3389/fcvm.2022.839183
10.1097/pec.0000000000002149
10.3389/fpubh.2022.926069
10.1684/epd.2020.1234
10.1001/jama.2019.8001
10.23736/s0026-4806.21.07808-3
10.3345/cep.2022.00451
10.1186/s13052-022-01388-2
10.1038/s41598-023-36207-z
10.3389/fmolb.2022.843150
10.1016/j.amjmed.2022.06.020
10.1186/s12967-022-03369-9
10.1093/eurheartj/ehy210
10.15574/sp.2022.123.16
10.1111/j.1442-200x.2008.02783.x
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.26565/2313-6693-2023-47-04
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2313-2396
EndPage 46
ExternalDocumentID 10_26565_2313_6693_2023_47_04
GroupedDBID AAYXX
ADBBV
ALMA_UNASSIGNED_HOLDINGS
BCNDV
CITATION
GROUPED_DOAJ
ID FETCH-LOGICAL-c934-799a7f7c57211656c9a5621a92c5f4341ee8f33834d06a822f057bb6a0c18f2d3
ISSN 2313-6693
IngestDate Sat Nov 29 06:11:55 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 47
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c934-799a7f7c57211656c9a5621a92c5f4341ee8f33834d06a822f057bb6a0c18f2d3
ORCID 0000-0002-1234-0040
0000-0003-2455-3278
OpenAccessLink https://periodicals.karazin.ua/medicine/article/download/22710/20884
PageCount 14
ParticipantIDs crossref_primary_10_26565_2313_6693_2023_47_04
PublicationCentury 2000
PublicationDate 2023-11-28
PublicationDateYYYYMMDD 2023-11-28
PublicationDate_xml – month: 11
  year: 2023
  text: 2023-11-28
  day: 28
PublicationDecade 2020
PublicationTitle The Journal of V.N. Karazin Kharkiv National University. Series "Medicine" (Online)
PublicationYear 2023
References ref13
ref12
ref15
ref14
ref20
ref11
ref10
ref0
ref2
ref1
ref17
ref16
ref19
ref18
ref8
ref7
ref9
ref4
ref3
ref6
ref5
References_xml – ident: ref14
  doi: 10.1155/2022/1858300
– ident: ref16
  doi: 10.1161/cir.0000000000000499
– ident: ref4
  doi: 10.1093/europace/euaa370
– ident: ref11
  doi: 10.1007/s10072-016-2740-5
– ident: ref5
  doi: 10.1016/j.pcl.2020.05.004
– ident: ref9
  doi: 10.1111/joim.12852
– ident: ref20
  doi: 10.3389/fcvm.2022.839183
– ident: ref6
  doi: 10.1097/pec.0000000000002149
– ident: ref17
  doi: 10.3389/fpubh.2022.926069
– ident: ref0
  doi: 10.1684/epd.2020.1234
– ident: ref3
  doi: 10.1001/jama.2019.8001
– ident: ref8
  doi: 10.23736/s0026-4806.21.07808-3
– ident: ref7
  doi: 10.3345/cep.2022.00451
– ident: ref1
  doi: 10.1186/s13052-022-01388-2
– ident: ref19
  doi: 10.1038/s41598-023-36207-z
– ident: ref15
  doi: 10.3389/fmolb.2022.843150
– ident: ref2
  doi: 10.1016/j.amjmed.2022.06.020
– ident: ref18
  doi: 10.1186/s12967-022-03369-9
– ident: ref10
  doi: 10.1093/eurheartj/ehy210
– ident: ref13
  doi: 10.15574/sp.2022.123.16
– ident: ref12
  doi: 10.1111/j.1442-200x.2008.02783.x
SSID ssj0002246480
Score 2.2389302
Snippet The search for new methods of differential diagnosis of syncope types will allow to improve the diagnosis of vasovagal syncope (VVS), syncope due to...
SourceID crossref
SourceType Index Database
StartPage 33
Title XGBoost machine learning algorithm for differential diagnosis of pediatric syncope
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journal Collection
  customDbUrl:
  eissn: 2313-2396
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002246480
  issn: 2313-6693
  databaseCode: DOA
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lj9MwELaqXYS4oOUlnisfuFUOjfNwfAQEiwQUBBXqLXIcp80-kqrNRss_5GcxfuSxFULsgUsUOeokzXyyx5OZ70PopS9VnmVJRAopJYGIWBAeZJLIRAoflqOY5ka15BObz5Plkn-dTH51vTDtOauq5OqKb_6rq2EMnK1bZ2_g7t4oDMA5OB2O4HY4_pPjlydv6nrXTC9MmaTqdCFWU3G-qrdls74wpYWdMkpTms80puDOcpNsOvUOTWegm1bGAezQSmaC2B_e3NMNZZqkevpxLbZnZTuddwnGoerD05NSaVK89LP7nA-n-2SnrgsHXodcX9oabqWnoCFrUP_U7rLXvpztrl1aWWnt7y08fg1Qb8cpDRro3j46moUh5gxIHFvpRE8NYzSw8rcOlJar0029QTBaxG1ac395oBC8aiqN3j4xdw8ZsRLI1-m495bJvngRtk3GUKrNpNpMqs2kIUs1Me0hZRH3R5v7U0MyFMahkfHr723byYylV396oFGgNIp4FkforvMyfm0hdg9NVHUf3e689wB9c0jDDmm4QxrukYYBaXiMNNwjDdcF7pGGHdIeosX7d4u3H4iT6CCSByFhnAtWMBnpPAL8E8kFxNO-4FRGRQgBklJJoZMgYT6LBcSiBWwPsiwWM-knBc2DR-igqiv1GGHYqMNeo4hknGkNgCLz2UxpcsecBTKh_AnyuteRbiwRS_pXTzy96Q-eoTsDGJ-jg2Z7qV6gW7Jtyt322PjzN_x9ffU
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=XGBoost+machine+learning+algorithm+for+differential+diagnosis+of+pediatric+syncope&rft.jtitle=The+Journal+of+V.N.+Karazin+Kharkiv+National+University.+Series+%22Medicine%22+%28Online%29&rft.au=Kovalchuk%2C+Tetiana&rft.au=Boyarchuk%2C+Oksana&rft.au=Bogai%2C+Sviatoslav&rft.date=2023-11-28&rft.issn=2313-6693&rft.eissn=2313-2396&rft.issue=47&rft.spage=33&rft.epage=46&rft_id=info:doi/10.26565%2F2313-6693-2023-47-04&rft.externalDBID=n%2Fa&rft.externalDocID=10_26565_2313_6693_2023_47_04
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2313-6693&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2313-6693&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2313-6693&client=summon