Data processing pipeline for cardiogenic shock prediction using machine learning
Recent advances in machine learning provide new possibilities to process and analyse observational patient data to predict patient outcomes. In this paper, we introduce a data processing pipeline for cardiogenic shock (CS) prediction from the MIMIC III database of intensive cardiac care unit patient...
Saved in:
| Published in | Frontiers in cardiovascular medicine Vol. 10; p. 1132680 |
|---|---|
| Main Authors | , , , , , , , , , , , , , , , , , , , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Switzerland
Frontiers Media S.A
23.03.2023
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 2297-055X 2297-055X |
| DOI | 10.3389/fcvm.2023.1132680 |
Cover
| Abstract | Recent advances in machine learning provide new possibilities to process and analyse observational patient data to predict patient outcomes. In this paper, we introduce a data processing pipeline for cardiogenic shock (CS) prediction from the MIMIC III database of intensive cardiac care unit patients with acute coronary syndrome. The ability to identify high-risk patients could possibly allow taking pre-emptive measures and thus prevent the development of CS.
We mainly focus on techniques for the imputation of missing data by generating a pipeline for imputation and comparing the performance of various multivariate imputation algorithms, including k-nearest neighbours, two singular value decomposition (SVD)-based methods, and Multiple Imputation by Chained Equations. After imputation, we select the final subjects and variables from the imputed dataset and showcase the performance of the gradient-boosted framework that uses a tree-based classifier for cardiogenic shock prediction.
We achieved good classification performance thanks to data cleaning and imputation (cross-validated mean area under the curve 0.805) without hyperparameter optimization.
We believe our pre-processing pipeline would prove helpful also for other classification and regression experiments. |
|---|---|
| AbstractList | Recent advances in machine learning provide new possibilities to process and analyse observational patient data to predict patient outcomes. In this paper, we introduce a data processing pipeline for cardiogenic shock (CS) prediction from the MIMIC III database of intensive cardiac care unit patients with acute coronary syndrome. The ability to identify high-risk patients could possibly allow taking pre-emptive measures and thus prevent the development of CS.
We mainly focus on techniques for the imputation of missing data by generating a pipeline for imputation and comparing the performance of various multivariate imputation algorithms, including k-nearest neighbours, two singular value decomposition (SVD)-based methods, and Multiple Imputation by Chained Equations. After imputation, we select the final subjects and variables from the imputed dataset and showcase the performance of the gradient-boosted framework that uses a tree-based classifier for cardiogenic shock prediction.
We achieved good classification performance thanks to data cleaning and imputation (cross-validated mean area under the curve 0.805) without hyperparameter optimization.
We believe our pre-processing pipeline would prove helpful also for other classification and regression experiments. IntroductionRecent advances in machine learning provide new possibilities to process and analyse observational patient data to predict patient outcomes. In this paper, we introduce a data processing pipeline for cardiogenic shock (CS) prediction from the MIMIC III database of intensive cardiac care unit patients with acute coronary syndrome. The ability to identify high-risk patients could possibly allow taking pre-emptive measures and thus prevent the development of CS.MethodsWe mainly focus on techniques for the imputation of missing data by generating a pipeline for imputation and comparing the performance of various multivariate imputation algorithms, including k-nearest neighbours, two singular value decomposition (SVD)—based methods, and Multiple Imputation by Chained Equations. After imputation, we select the final subjects and variables from the imputed dataset and showcase the performance of the gradient-boosted framework that uses a tree-based classifier for cardiogenic shock prediction.ResultsWe achieved good classification performance thanks to data cleaning and imputation (cross-validated mean area under the curve 0.805) without hyperparameter optimization.ConclusionWe believe our pre-processing pipeline would prove helpful also for other classification and regression experiments. Recent advances in machine learning provide new possibilities to process and analyse observational patient data to predict patient outcomes. In this paper, we introduce a data processing pipeline for cardiogenic shock (CS) prediction from the MIMIC III database of intensive cardiac care unit patients with acute coronary syndrome. The ability to identify high-risk patients could possibly allow taking pre-emptive measures and thus prevent the development of CS.IntroductionRecent advances in machine learning provide new possibilities to process and analyse observational patient data to predict patient outcomes. In this paper, we introduce a data processing pipeline for cardiogenic shock (CS) prediction from the MIMIC III database of intensive cardiac care unit patients with acute coronary syndrome. The ability to identify high-risk patients could possibly allow taking pre-emptive measures and thus prevent the development of CS.We mainly focus on techniques for the imputation of missing data by generating a pipeline for imputation and comparing the performance of various multivariate imputation algorithms, including k-nearest neighbours, two singular value decomposition (SVD)-based methods, and Multiple Imputation by Chained Equations. After imputation, we select the final subjects and variables from the imputed dataset and showcase the performance of the gradient-boosted framework that uses a tree-based classifier for cardiogenic shock prediction.MethodsWe mainly focus on techniques for the imputation of missing data by generating a pipeline for imputation and comparing the performance of various multivariate imputation algorithms, including k-nearest neighbours, two singular value decomposition (SVD)-based methods, and Multiple Imputation by Chained Equations. After imputation, we select the final subjects and variables from the imputed dataset and showcase the performance of the gradient-boosted framework that uses a tree-based classifier for cardiogenic shock prediction.We achieved good classification performance thanks to data cleaning and imputation (cross-validated mean area under the curve 0.805) without hyperparameter optimization.ResultsWe achieved good classification performance thanks to data cleaning and imputation (cross-validated mean area under the curve 0.805) without hyperparameter optimization.We believe our pre-processing pipeline would prove helpful also for other classification and regression experiments.ConclusionWe believe our pre-processing pipeline would prove helpful also for other classification and regression experiments. |
| Author | Thevathasan, Tharusan Skurk, Carsten Segev, Amitai Böhm, Allan Jajcay, Nikola Cader, F. Aaysha Jankova, Jana Nägele, Felix Tavazzi, Guido Gollmann-Tepeköylü, Can Berta, Imrich Bezak, Branislav Petrikova, Katarina Krychtiuk, Konstantin A. Matetzky, Shlomi Pogran, Edita Spartalis, Michael Friebel, Julian Huber, Kurt El Tahlawi, Mohammad Tica, Otilia Guerra, Federico Kollarova, Marta Jarakovic, Milana Pölzl, Leo |
| AuthorAffiliation | 4 Faculty of Medicine , Comenius University in Bratislava , Bratislava , Slovakia 11 Department of Cardiology Angiology and Intensive Care Medicine, Deutsches Herzzentrum der Charité (DHZC), Campus Benjamin Franklin , Charité - Universitätsmedizin Berlin , Berlin , Germany 21 Institute of Cardiovascular Sciences , University of Birmingham, Medical School , Birmingham , United Kingdom 3 Clinic of Cardiac Surgery , National Institute of Cardiovascular Diseases , Bratislava , Slovakia 19 Faculty of Medicine , University of Novi Sad , Novi Sad , Serbia 22 Department of Internal Medicine II, Division of Cardiology , Medical University of Vienna , Vienna , Austria 24 Department of Clinical-Surgical, Diagnostic and Paediatric Sciences , University of Pavia , Pavia , Italy 8 Global Clinical Scholars Research Training (GCSRT) Program , Harvard Medical School , Boston, MA , United States 16 3rd Medical Department, Cardiology and Intensive Care Medicine , Wilhelminen Hospital , Vienna , Austria 2 Departme |
| AuthorAffiliation_xml | – name: 20 Cardiology Department , Emergency County Clinical Hospital of Oradea , Oradea , Romania – name: 13 Deutsches Zentrum für Herz-Kreislauf-Forschung e.V. , Berlin , Germany – name: 26 Department of Acute Cardiology , National Institute of Cardiovascular Diseases , Bratislava , Slovakia – name: 16 3rd Medical Department, Cardiology and Intensive Care Medicine , Wilhelminen Hospital , Vienna , Austria – name: 17 Department of Cardiology , Ibrahim Cardiac Hospital & Research Institute , Dhaka , Bangladesh – name: 14 Institute of Medical Informatics , Charité—Universitätsmedizin Berlin , Berlin , Germany – name: 2 Department of Complex Systems , Institute of Computer Science, Czech Academy of Sciences , Prague , Czech Republic – name: 21 Institute of Cardiovascular Sciences , University of Birmingham, Medical School , Birmingham , United Kingdom – name: 4 Faculty of Medicine , Comenius University in Bratislava , Bratislava , Slovakia – name: 10 Cardiology and Arrhythmology Clinic , Marche Polytechnic University, University Hospital “Umberto I - Lancisi - Salesi” , Ancona , Italy – name: 23 Duke Clinical Research Institute Durham , NC , United States – name: 25 Anesthesia and Intensive Care , Fondazione Policlinico San Matteo Hospital IRCCS , Pavia , Italy – name: 6 Affiliated to the Sackler Faculty of Medicine , Tel Aviv University , Tel Aviv , Israel – name: 11 Department of Cardiology Angiology and Intensive Care Medicine, Deutsches Herzzentrum der Charité (DHZC), Campus Benjamin Franklin , Charité - Universitätsmedizin Berlin , Berlin , Germany – name: 1 Premedix Academy , Bratislava , Slovakia – name: 5 The Leviev Cardiothoracic & Vascular Center , Chaim Sheba Medical Center , Ramat Gan , Israel – name: 8 Global Clinical Scholars Research Training (GCSRT) Program , Harvard Medical School , Boston, MA , United States – name: 19 Faculty of Medicine , University of Novi Sad , Novi Sad , Serbia – name: 18 Cardiac Intensive Care Unit , Institute for Cardiovascular Diseases of Vojvodina , Sremska Kamenica , Serbia – name: 22 Department of Internal Medicine II, Division of Cardiology , Medical University of Vienna , Vienna , Austria – name: 3 Clinic of Cardiac Surgery , National Institute of Cardiovascular Diseases , Bratislava , Slovakia – name: 9 Department of Cardiology, Faculty of Human Medicine , Zagazig University , Zagazig , Egypt – name: 7 3rd Department of Cardiology , National and Kapodistrian University of Athens , Athens , Greece – name: 12 Berlin Institute of Health , Charité—Universitätsmedizin Berlin , Berlin , Germany – name: 24 Department of Clinical-Surgical, Diagnostic and Paediatric Sciences , University of Pavia , Pavia , Italy – name: 15 Department for Cardiac Surgery, Cardiac Regeneration Research , Medical University of Innsbruck , Innsbruck , Austria |
| Author_xml | – sequence: 1 givenname: Nikola surname: Jajcay fullname: Jajcay, Nikola – sequence: 2 givenname: Branislav surname: Bezak fullname: Bezak, Branislav – sequence: 3 givenname: Amitai surname: Segev fullname: Segev, Amitai – sequence: 4 givenname: Shlomi surname: Matetzky fullname: Matetzky, Shlomi – sequence: 5 givenname: Jana surname: Jankova fullname: Jankova, Jana – sequence: 6 givenname: Michael surname: Spartalis fullname: Spartalis, Michael – sequence: 7 givenname: Mohammad surname: El Tahlawi fullname: El Tahlawi, Mohammad – sequence: 8 givenname: Federico surname: Guerra fullname: Guerra, Federico – sequence: 9 givenname: Julian surname: Friebel fullname: Friebel, Julian – sequence: 10 givenname: Tharusan surname: Thevathasan fullname: Thevathasan, Tharusan – sequence: 11 givenname: Imrich surname: Berta fullname: Berta, Imrich – sequence: 12 givenname: Leo surname: Pölzl fullname: Pölzl, Leo – sequence: 13 givenname: Felix surname: Nägele fullname: Nägele, Felix – sequence: 14 givenname: Edita surname: Pogran fullname: Pogran, Edita – sequence: 15 givenname: F. Aaysha surname: Cader fullname: Cader, F. Aaysha – sequence: 16 givenname: Milana surname: Jarakovic fullname: Jarakovic, Milana – sequence: 17 givenname: Can surname: Gollmann-Tepeköylü fullname: Gollmann-Tepeköylü, Can – sequence: 18 givenname: Marta surname: Kollarova fullname: Kollarova, Marta – sequence: 19 givenname: Katarina surname: Petrikova fullname: Petrikova, Katarina – sequence: 20 givenname: Otilia surname: Tica fullname: Tica, Otilia – sequence: 21 givenname: Konstantin A. surname: Krychtiuk fullname: Krychtiuk, Konstantin A. – sequence: 22 givenname: Guido surname: Tavazzi fullname: Tavazzi, Guido – sequence: 23 givenname: Carsten surname: Skurk fullname: Skurk, Carsten – sequence: 24 givenname: Kurt surname: Huber fullname: Huber, Kurt – sequence: 25 givenname: Allan surname: Böhm fullname: Böhm, Allan |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37034352$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kUtv1DAUhS1URMvQH8AGZclmBr8fK4QKLZUqwQIkdpZzczPjksTBzlTi35N0hqplwcrW9XfOufJ5SU6GNCAhrxndCGHduxbu-g2nXGwYE1xb-oycce7Mmir14-TR_ZScl3JLKWVKWqXtC3IqDBVSKH5Gvn4MU6jGnABLicO2GuOIXRywalOuIOQmpi0OEaqyS_BzJrGJMMU0VPt7vg-wW_AOQx7mwSvyvA1dwfPjuSLfLz99u_i8vvlydX3x4WYNUutpLVzLa-AmCKckC9bUtkXWgm4QHFiFumbSKWgb4ay2xgIVNW-ClmBQKCVW5Prg26Rw68cc-5B_-xSivx-kvPUhTxE69EJzN6cqZ4OSwUqHBgIXlAaLRs5fsSLvD17jvu6xARymHLonpk9fhrjz23TnGaXGMGlmh7dHh5x-7bFMvo8FsOvCgGlfPDfOMaOZszP65nHYQ8rfTmaAHQDIqZSM7QPCqF-q90v1fqneH6ufNeYfDcQpLDXN-8buP8o_5NO0oA |
| CitedBy_id | crossref_primary_10_1093_ehjacc_zuae037 crossref_primary_10_1093_ehjdh_ztaf002 crossref_primary_10_3390_diagnostics14111103 crossref_primary_10_3390_jcdd11040125 crossref_primary_10_1016_j_jscai_2024_102047 crossref_primary_10_7759_cureus_50395 crossref_primary_10_4103_AGINGADV_AGINGADV_D_24_00025 |
| Cites_doi | 10.48550/arxiv.1407.2330 10.1161/circoutcomes.109.875658 10.1097/01.mlr.0000182534.19832.83 10.21037/atm.2019.10.79 10.1093/ehjacc/zuac041.077 10.1186/s12874-018-0615-6 10.1186/s13613-018-0448-9 10.1080/01621459.1988.10478722 10.1007/s10916-019-1279-4 10.9790/0661-0651215 10.1111/j.1467-9876.2007.00613.x 10.1161/circinterventions.116.004337 10.1002/mpr.329 10.1016/j.cpnec.2021.100052 10.1001/jama.2019.17831 10.1007/978-3-030-19810-7_19 10.1136/bmjopen-2020-044779 10.1016/j.chemolab.2012.11.010 10.1038/sdata.2016.35 10.1002/sim.8915 10.1532/hsf.3571 10.1371/journal.pone.0232176 10.1093/aje/kwt312 10.1136/bmj.b2393 10.1016/j.spinee.2018.11.009 10.1177/0962280206074466 10.1002/ejhf.339 10.1136/bmjopen-2013-002847 10.1186/1471-2288-14-75 10.3389/fcvm.2021.765693 10.1371/journal.pone.0176124 10.1016/j.neucom.2019.06.100 10.4149/BLL_2022_003 10.5815/ijitcs.2019.02.03 10.1002/sim.2099 10.1109/tkde.2018.2867533 10.1191/1740774504cn032oa |
| ContentType | Journal Article |
| Copyright | 2023 Jajcay, Bezak, Segev, Matetzky, Jankova, Spartalis, El Tahlawi, Guerra, Friebel, Thevathasan, Berta, Pölzl, Nägele, Pogran, Cader, Jarakovic, Gollmann-Tepeköylü, Kollarova, Petrikova, Tica, Krychtiuk, Tavazzi, Skurk, Huber and Böhm. 2023 Jajcay, Bezak, Segev, Matetzky, Jankova, Spartalis, El Tahlawi, Guerra, Friebel, Thevathasan, Berta, Pölzl, Nägele, Pogran, Cader, Jarakovic, Gollmann-Tepeköylü, Kollarova, Petrikova, Tica, Krychtiuk, Tavazzi, Skurk, Huber and Böhm. 2023 Jajcay, Bezak, Segev, Matetzky, Jankova, Spartalis, El Tahlawi, Guerra, Friebel, Thevathasan, Berta, Pölzl, Nägele, Pogran, Cader, Jarakovic, Gollmann-Tepeköylü, Kollarova, Petrikova, Tica, Krychtiuk, Tavazzi, Skurk, Huber and Böhm |
| Copyright_xml | – notice: 2023 Jajcay, Bezak, Segev, Matetzky, Jankova, Spartalis, El Tahlawi, Guerra, Friebel, Thevathasan, Berta, Pölzl, Nägele, Pogran, Cader, Jarakovic, Gollmann-Tepeköylü, Kollarova, Petrikova, Tica, Krychtiuk, Tavazzi, Skurk, Huber and Böhm. – notice: 2023 Jajcay, Bezak, Segev, Matetzky, Jankova, Spartalis, El Tahlawi, Guerra, Friebel, Thevathasan, Berta, Pölzl, Nägele, Pogran, Cader, Jarakovic, Gollmann-Tepeköylü, Kollarova, Petrikova, Tica, Krychtiuk, Tavazzi, Skurk, Huber and Böhm. 2023 Jajcay, Bezak, Segev, Matetzky, Jankova, Spartalis, El Tahlawi, Guerra, Friebel, Thevathasan, Berta, Pölzl, Nägele, Pogran, Cader, Jarakovic, Gollmann-Tepeköylü, Kollarova, Petrikova, Tica, Krychtiuk, Tavazzi, Skurk, Huber and Böhm |
| DBID | AAYXX CITATION NPM 7X8 5PM DOA |
| DOI | 10.3389/fcvm.2023.1132680 |
| DatabaseName | CrossRef PubMed MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 2297-055X |
| ExternalDocumentID | oai_doaj_org_article_3629c46598a54a849e7ca2300a8e7470 PMC10077147 37034352 10_3389_fcvm_2023_1132680 |
| Genre | Journal Article |
| GrantInformation_xml | – fundername: ; grantid: VEGA 1/0563/21 |
| GroupedDBID | 53G 5VS 9T4 AAFWJ AAYXX ACGFS ACXDI ADBBV ADRAZ AFPKN ALMA_UNASSIGNED_HOLDINGS AOIJS BCNDV CITATION GROUPED_DOAJ HYE KQ8 M48 M~E OK1 PGMZT RPM IAO IEA IHR IHW IPNFZ NPM RIG 7X8 5PM |
| ID | FETCH-LOGICAL-c466t-39f2bc27a39541a87b8fe1fc6dec9c85e6b1495cfd3986878c03b2da64c7e3553 |
| IEDL.DBID | M48 |
| ISSN | 2297-055X |
| IngestDate | Wed Aug 27 01:32:27 EDT 2025 Thu Aug 21 18:38:10 EDT 2025 Fri Sep 05 04:45:20 EDT 2025 Thu Jan 02 22:53:53 EST 2025 Tue Jul 01 01:10:42 EDT 2025 Thu Apr 24 23:09:10 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | processing pipeline cardiogenic shock prediction model classification machine learning missing data imputation |
| Language | English |
| License | 2023 Jajcay, Bezak, Segev, Matetzky, Jankova, Spartalis, El Tahlawi, Guerra, Friebel, Thevathasan, Berta, Pölzl, Nägele, Pogran, Cader, Jarakovic, Gollmann-Tepeköylü, Kollarova, Petrikova, Tica, Krychtiuk, Tavazzi, Skurk, Huber and Böhm. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c466t-39f2bc27a39541a87b8fe1fc6dec9c85e6b1495cfd3986878c03b2da64c7e3553 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 Edited by: Benedikt Schrage, University Medical Center Hamburg-Eppendorf, Germany Specialty Section: This article was submitted to Heart Failure and Transplantation, a section of the journal Frontiers in Cardiovascular Medicine Reviewed by: Stefania Sacchi, San Raffaele Scientific Institute (IRCCS), Italy Meraj Neyazi, University Medical Center Hamburg-Eppendorf, Germany Kishore Surendra, University Medical Center Hamburg-Eppendorf, Germany |
| OpenAccessLink | http://journals.scholarsportal.info/openUrl.xqy?doi=10.3389/fcvm.2023.1132680 |
| PMID | 37034352 |
| PQID | 2799176198 |
| PQPubID | 23479 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_3629c46598a54a849e7ca2300a8e7470 pubmedcentral_primary_oai_pubmedcentral_nih_gov_10077147 proquest_miscellaneous_2799176198 pubmed_primary_37034352 crossref_primary_10_3389_fcvm_2023_1132680 crossref_citationtrail_10_3389_fcvm_2023_1132680 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2023-03-23 |
| PublicationDateYYYYMMDD | 2023-03-23 |
| PublicationDate_xml | – month: 03 year: 2023 text: 2023-03-23 day: 23 |
| PublicationDecade | 2020 |
| PublicationPlace | Switzerland |
| PublicationPlace_xml | – name: Switzerland |
| PublicationTitle | Frontiers in cardiovascular medicine |
| PublicationTitleAlternate | Front Cardiovasc Med |
| PublicationYear | 2023 |
| Publisher | Frontiers Media S.A |
| Publisher_xml | – name: Frontiers Media S.A |
| References | Liu (B30) 2013; 120 Waljee (B20) 2013; 3 Herbers (B19) 2021; 7 Ambler (B25) 2007; 16 Morris (B27) 2014; 14 Mandawat (B13) 2017; 10 Huque (B18) 2018; 18 He (B21) 2010; 3 Song (B8) 2021; 24 Rafsunjani (B37) 2019; 11 Johnson (B6) 2016; 3 Shah (B24) 2014; 179 Wood (B39) 2004; 1 Sterne (B38) 2009; 338 Nemethova (B3) 2019; 985 Alonso (B42) 2019; 43 Peterkova (B10) Li (B9) 2021; 11 Azur (B23) 2011; 20 Vincent (B15) 2018; 8 Tang (B22) 2006; 24 Alejo (B35) 2010 Peterson (B5) 2019; 322 Stevens (B33) 2017; 12 Salfrán (B31) 2016 Dai (B7) 2020; 15 Lan (B16) 2019; 7 De Luca (B12) 2015; 17 Yao (B29) 2018; 31 Abayomi (B32) 2008; 57 Little (B17) 1988; 83 Kovács (B36) 2019; 366 Staartjes (B41) 2019; 19 Ghassemi (B1) 2018 Ke (B26) 2017 Bohm (B2) 2022; 123 Bohm (B11) 2022; 11 Quan (B14) 2005; 43 Noghrehchi (B40) 2021; 40 Pears (B34) 2014 Malarvizhi (B28) 2012; 5 Sanchez-Martinez (B4) 2022; 8 |
| References_xml | – year: 2014 ident: B34 article-title: Synthetic minority over-sampling technique (smote) for predicting software build outcomes publication-title: arXiv doi: 10.48550/arxiv.1407.2330 – year: 2018 ident: B1 article-title: Opportunities in machine learning for healthcare publication-title: arXiv – volume: 3 start-page: 98 year: 2010 ident: B21 article-title: Missing data analysis using multiple imputation: getting to the heart of the matter publication-title: Circ Cardiovasc Qual Outcomes doi: 10.1161/circoutcomes.109.875658 – volume: 43 start-page: 1130 year: 2005 ident: B14 article-title: Coding algorithms for defining comorbidities in Icd-9-Cm and Icd-10 administrative data publication-title: Med Care doi: 10.1097/01.mlr.0000182534.19832.83 – volume: 7 start-page: 662 year: 2019 ident: B16 article-title: Utilization of echocardiography during septic shock was associated with a decreased 28-day mortality: a propensity score-matched analysis of the mimic-iii database publication-title: Ann Transl Med doi: 10.21037/atm.2019.10.79 – volume: 11 start-page: i107 year: 2022 ident: B11 article-title: Artificial intelligence model for prediction of cardiogenic shock in patients with acute coronary syndrome publication-title: Eur Heart J Acute Cardiovascular Care doi: 10.1093/ehjacc/zuac041.077 – volume: 18 start-page: 168 year: 2018 ident: B18 article-title: A comparison of multiple imputation methods for missing data in longitudinal studies publication-title: BMC Med Res Methodol doi: 10.1186/s12874-018-0615-6 – volume: 8 start-page: 107 year: 2018 ident: B15 article-title: Mean arterial pressure and mortality in patients with distributive shock: a retrospective analysis of the mimic-iii database publication-title: Ann Intensive Care doi: 10.1186/s13613-018-0448-9 – ident: B10 – volume: 83 start-page: 1198 year: 1988 ident: B17 article-title: A test of missing completely at random for multivariate data with missing values publication-title: J Am Stat Assoc doi: 10.1080/01621459.1988.10478722 – volume-title: Lightgbm: A highly efficient gradient boosting decision tree year: 2017 ident: B26 – volume: 43 start-page: 140 year: 2019 ident: B42 article-title: Predictive, personalized, preventive and participatory (4p) medicine applied to telemedicine and ehealth in the literature publication-title: J Med Syst doi: 10.1007/s10916-019-1279-4 – volume: 5 start-page: 5 year: 2012 ident: B28 article-title: K-Nearest neighbor in missing data imputation publication-title: IJERD doi: 10.9790/0661-0651215 – volume: 57 start-page: 273 year: 2008 ident: B32 article-title: Diagnostics for multivariate imputations publication-title: J R Stat Soc, C: Appl Stat doi: 10.1111/j.1467-9876.2007.00613.x – volume: 10 start-page: e004337 year: 2017 ident: B13 article-title: Percutaneous mechanical circulatory support devices in cardiogenic shock publication-title: Circ: Cardiovasc Interventions doi: 10.1161/circinterventions.116.004337 – volume: 20 start-page: 40 year: 2011 ident: B23 article-title: Multiple imputation by chained equations: what is it and how does it work? publication-title: Int J Methods Psychiatr Res doi: 10.1002/mpr.329 – volume: 7 start-page: 100052 year: 2021 ident: B19 article-title: How to deal with non-detectable and outlying values in biomarker research: best practices and recommendations for univariate imputation approaches publication-title: Compr Psychoneuroendocrinology doi: 10.1016/j.cpnec.2021.100052 – volume: 322 start-page: 2283 year: 2019 ident: B5 article-title: Machine learning, predictive analytics, and clinical practice: can the past inform the present? publication-title: JAMA doi: 10.1001/jama.2019.17831 – volume: 985 start-page: 191 year: 2019 ident: B3 article-title: Identification of kdd problems from medical data publication-title: Adv Intell Syst Comput doi: 10.1007/978-3-030-19810-7_19 – volume: 11 start-page: e044779 year: 2021 ident: B9 article-title: Prediction model of in-hospital mortality in intensive care unit patients with heart failure: machine learning-based, retrospective analysis of the mimic-iii database publication-title: BMJ Open doi: 10.1136/bmjopen-2020-044779 – volume: 120 start-page: 106 year: 2013 ident: B30 article-title: Comparison of five iterative imputation methods for multivariate classification publication-title: Chemometr Intell Lab Syst doi: 10.1016/j.chemolab.2012.11.010 – volume: 3 start-page: 160035 year: 2016 ident: B6 article-title: Mimic-Iii, a freely accessible critical care database publication-title: Sci Data doi: 10.1038/sdata.2016.35 – volume: 40 start-page: 2467 year: 2021 ident: B40 article-title: Selecting the model for multiple imputation of missing data: just use an ic! publication-title: Stat Med doi: 10.1002/sim.8915 – volume: 24 start-page: E351 year: 2021 ident: B8 article-title: Clinical characteristics of aortic aneurysm in mimic-iii publication-title: Heart Surg Forum doi: 10.1532/hsf.3571 – start-page: 303 volume-title: Advances in neural networks year: 2010 ident: B35 article-title: Edited nearest neighbor rule for improving neural networks classifications – volume: 15 start-page: e0232176 year: 2020 ident: B7 article-title: Analysis of adult disease characteristics and mortality on mimic-iii publication-title: PLoS One doi: 10.1371/journal.pone.0232176 – volume: 179 start-page: 764 year: 2014 ident: B24 article-title: Comparison of random forest and parametric imputation models for imputing missing data using mice: a caliber study publication-title: Am J Epidemiol doi: 10.1093/aje/kwt312 – volume: 338 start-page: b2393 year: 2009 ident: B38 article-title: Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls publication-title: Br Med J doi: 10.1136/bmj.b2393 – volume: 19 start-page: 853 year: 2019 ident: B41 article-title: Deep learning-based preoperative predictive analytics for patient-reported outcomes following lumbar discectomy: feasibility of center-specific modeling publication-title: Spine J doi: 10.1016/j.spinee.2018.11.009 – volume: 16 start-page: 277 year: 2007 ident: B25 article-title: A comparison of imputation techniques for handling missing predictor values in a risk model with a binary outcome publication-title: Stat Methods Med Res doi: 10.1177/0962280206074466 – volume: 17 start-page: 1124 year: 2015 ident: B12 article-title: Temporal trends in the epidemiology, management, and outcome of patients with cardiogenic shock complicating acute coronary syndromes publication-title: Eur J Heart Fail doi: 10.1002/ejhf.339 – volume-title: Missing data: on criteria to evaluate imputation methods year: 2016 ident: B31 – volume: 3 start-page: e002847 year: 2013 ident: B20 article-title: Comparison of imputation methods for missing laboratory data in medicine publication-title: BMJ Open doi: 10.1136/bmjopen-2013-002847 – volume: 14 start-page: 75 year: 2014 ident: B27 article-title: Tuning multiple imputation by predictive mean matching and local residual draws publication-title: BMC Med Res Methodol doi: 10.1186/1471-2288-14-75 – volume: 8 start-page: 765693 year: 2022 ident: B4 article-title: Machine learning for clinical decision-making: challenges and opportunities in cardiovascular imaging publication-title: Front Cardiovasc Med doi: 10.3389/fcvm.2021.765693 – volume: 12 start-page: e0176124 year: 2017 ident: B33 article-title: A comparison of multiple testing adjustment methods with block-correlation positively-dependent tests publication-title: PLoS One doi: 10.1371/journal.pone.0176124 – volume: 366 start-page: 352 year: 2019 ident: B36 article-title: Smote-Variants: a python implementation of 85 minority oversampling techniques publication-title: Neurocomputing doi: 10.1016/j.neucom.2019.06.100 – volume: 123 start-page: 16 year: 2022 ident: B2 article-title: Technical and practical aspects of artificial intelligence in cardiology publication-title: Bratisl Lek Listy doi: 10.4149/BLL_2022_003 – volume: 11 start-page: 21 year: 2019 ident: B37 article-title: An empirical comparison of missing value imputation techniques on aps failure prediction publication-title: IJ Inf Technol Comput Sci doi: 10.5815/ijitcs.2019.02.03 – volume: 24 start-page: 2111 year: 2006 ident: B22 article-title: A comparison of imputation methods in a longitudinal randomized clinical trial publication-title: Stat Med doi: 10.1002/sim.2099 – volume: 31 start-page: 1 year: 2018 ident: B29 article-title: Accelerated and inexact soft-impute for large-scale matrix and tensor completion publication-title: IEEE Trans Knowl Data Eng doi: 10.1109/tkde.2018.2867533 – volume: 1 start-page: 368 year: 2004 ident: B39 article-title: Are missing outcome data adequately handled? A review of published randomized controlled trials in Major medical journals publication-title: Clin Trials doi: 10.1191/1740774504cn032oa |
| SSID | ssj0001548568 |
| Score | 2.2778418 |
| Snippet | Recent advances in machine learning provide new possibilities to process and analyse observational patient data to predict patient outcomes. In this paper, we... IntroductionRecent advances in machine learning provide new possibilities to process and analyse observational patient data to predict patient outcomes. In... |
| SourceID | doaj pubmedcentral proquest pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | 1132680 |
| SubjectTerms | cardiogenic shock Cardiovascular Medicine classification machine learning missing data imputation prediction model processing pipeline |
| SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA7iQbyIb-uLCJ6EYrZ5H30iguJBwVtI00QXtLvorr_fmbYuuyJ68dqmNHwzTb5pZr4h5FB4rytwnrw0rMpFCFVuU5S5iZVNEkWhDBY439yqqwdx_Sgfp1p9YU5YKw_cAncMC6wNQklrvBTeCBt18MCbmTcRqHATrTPLpoKptj5YGKlMe4wJUZg9TuEDC88Ljl1MCoUykFMbUaPX_xPJ_J4rObX5XC6TpY410pN2titkLtarZOGmOxdfI3fnfuTpsE36h82IDvtDLDSPFDgpDU3OKXhKP9D3Z1gAYSQ-ijah42b8a5NTGWnXROJpnTxcXtyfXeVdr4QcwFGjnNtUlKHQnlspet7o0qTYS0FVMdhgZFQlxkIhVdwaZbQJjJdF5ZUIOgLn4Btkvh7UcYtQr3zZS1jSykohufRK6RC1Up4lzkTKCPsCzoVOSBz7Wbw4CCgQa4dYO8TadVhn5GjyyLBV0fht8ClaYzIQBbCbC-AWrnML95dbZOTgy5YOPhg8BfF1HIzfXaGBEuPPG5ORzda2k1dxWP-APxYZMTNWn5nL7J26_9yIcmO2ie4Jvf0fs98hi4gI5roVfJfMj97GcQ_Iz6jcb_z8E4eGAUM priority: 102 providerName: Directory of Open Access Journals |
| Title | Data processing pipeline for cardiogenic shock prediction using machine learning |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/37034352 https://www.proquest.com/docview/2799176198 https://pubmed.ncbi.nlm.nih.gov/PMC10077147 https://doaj.org/article/3629c46598a54a849e7ca2300a8e7470 |
| Volume | 10 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlR1daxQxMJQK4ov4UfXUlgg-FVb38p0HEWstRaj44MG9hWw2aQ_q3nkfov--M9nc0ZND6OPuTrKbmcnOTOaLkLfCe90C81SNqdtKhNBWNkVZmdjaJLEolMEE54tv6nwkvo7leI-s21sVBC52mnbYT2o0v37359ffj7DhP6DFCfL2fQq_MaeccWxQwpQBC_5edhdhJF_R9vukYWH65DjGsAaplOPez7l7li1JlQv679JC_w2mvCWdzh6Rh0WtpJ96PnhM9mL3hNy_KI7zp-T7qV96OuuzAkBa0dlkhpnokYLSSkMOSgVWmgS6uII_JEDiUCQaXWX4nznoMtLSZeLygIzOvvz4fF6VZgpVEEotK24TawLTnlspht7oxqQ4TEG1MdhgZFQNGkshtdwaZbQJNW9Y65UIOoJSwp-R_W7axReEeuWbYcKc17oRkkuvlA5RK-XrxGuRBqReI86FUmkcG15cO7A4ENcOce0Q167gekCON0NmfZmN_wGfIDU2gFghO9-Yzi9d2XAOBLOFlUtrvBTeCBt18GBv1d5EMKFgkjdrWjrYUegm8V2crhaOadCZ8XTHDMjznrabV3H4QYKCyQbEbFF961u2n3STq1y1G8NR9FDol3dZ6ivyAC8x6I3x12R_OV_FQ9CCls1RPj04yhx-A7B7BLE |
| linkProvider | Scholars Portal |
| 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=Data+processing+pipeline+for+cardiogenic+shock+prediction+using+machine+learning&rft.jtitle=Frontiers+in+cardiovascular+medicine&rft.au=Jajcay%2C+Nikola&rft.au=Bezak%2C+Branislav&rft.au=Segev%2C+Amitai&rft.au=Matetzky%2C+Shlomi&rft.date=2023-03-23&rft.issn=2297-055X&rft.eissn=2297-055X&rft.volume=10&rft_id=info:doi/10.3389%2Ffcvm.2023.1132680&rft.externalDBID=n%2Fa&rft.externalDocID=10_3389_fcvm_2023_1132680 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2297-055X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2297-055X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2297-055X&client=summon |