Detail
Article
Online article
FT
Medvik - BMC
  • Something wrong with this record ?

Data processing pipeline for cardiogenic shock prediction using machine learning

N. Jajcay, B. Bezak, A. Segev, S. Matetzky, J. Jankova, M. Spartalis, M. El Tahlawi, F. Guerra, J. Friebel, T. Thevathasan, I. Berta, L. Pölzl, F. Nägele, E. Pogran, FA. Cader, M. Jarakovic, C. Gollmann-Tepeköylü, M. Kollarova, K. Petrikova, O....

. 2023 ; 10 (-) : 1132680. [pub] 20230323

Status not-indexed Language English Country Switzerland

Document type Journal Article

INTRODUCTION: 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. METHODS: 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. RESULTS: We achieved good classification performance thanks to data cleaning and imputation (cross-validated mean area under the curve 0.805) without hyperparameter optimization. CONCLUSION: We believe our pre-processing pipeline would prove helpful also for other classification and regression experiments.

3rd Department of Cardiology National and Kapodistrian University of Athens Athens Greece

3rd Medical Department Cardiology and Intensive Care Medicine Wilhelminen Hospital Vienna Austria

Affiliated to the Sackler Faculty of Medicine Tel Aviv University Tel Aviv Israel

Anesthesia and Intensive Care Fondazione Policlinico San Matteo Hospital IRCCS Pavia Italy

Berlin Institute of Health Charité Universitätsmedizin Berlin Berlin Germany

Cardiac Intensive Care Unit Institute for Cardiovascular Diseases of Vojvodina Sremska Kamenica Serbia

Cardiology and Arrhythmology Clinic Marche Polytechnic University University Hospital Umberto 1 Lancisi Salesi Ancona Italy

Cardiology Department Emergency County Clinical Hospital of Oradea Oradea Romania

Clinic of Cardiac Surgery National Institute of Cardiovascular Diseases Bratislava Slovakia

Department for Cardiac Surgery Cardiac Regeneration Research Medical University of Innsbruck Innsbruck Austria

Department of Acute Cardiology National Institute of Cardiovascular Diseases Bratislava Slovakia

Department of Cardiology Angiology and Intensive Care Medicine Deutsches Herzzentrum der Charité Campus Benjamin Franklin Charité Universitätsmedizin Berlin Berlin Germany

Department of Cardiology Faculty of Human Medicine Zagazig University Zagazig Egypt

Department of Cardiology Ibrahim Cardiac Hospital and Research Institute Dhaka Bangladesh

Department of Clinical Surgical Diagnostic and Paediatric Sciences University of Pavia Pavia Italy

Department of Complex Systems Institute of Computer Science Czech Academy of Sciences Prague Czech Republic

Department of Internal Medicine 2 Division of Cardiology Medical University of Vienna Vienna Austria

Deutsches Zentrum für Herz Kreislauf Forschung e 5 Berlin Germany

Duke Clinical Research Institute Durham NC United States

Faculty of Medicine Comenius University in Bratislava Bratislava Slovakia

Faculty of Medicine University of Novi Sad Novi Sad Serbia

Global Clinical Scholars Research Training Program Harvard Medical School Boston MA United States

Institute of Cardiovascular Sciences University of Birmingham Medical School Birmingham United Kingdom

Institute of Medical Informatics Charité Universitätsmedizin Berlin Berlin Germany

Premedix Academy Bratislava Slovakia

The Leviev Cardiothoracic and Vascular Center Chaim Sheba Medical Center Ramat Gan Israel

References provided by Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc23010125
003      
CZ-PrNML
005      
20230721095322.0
007      
ta
008      
230707s2023 sz f 000 0|eng||
009      
AR
024    7_
$a 10.3389/fcvm.2023.1132680 $2 doi
035    __
$a (PubMed)37034352
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a sz
100    1_
$a Jajcay, Nikola $u Premedix Academy, Bratislava, Slovakia $u Department of Complex Systems, Institute of Computer Science, Czech Academy of Sciences, Prague, Czech Republic
245    10
$a Data processing pipeline for cardiogenic shock prediction using machine learning / $c N. Jajcay, B. Bezak, A. Segev, S. Matetzky, J. Jankova, M. Spartalis, M. El Tahlawi, F. Guerra, J. Friebel, T. Thevathasan, I. Berta, L. Pölzl, F. Nägele, E. Pogran, FA. Cader, M. Jarakovic, C. Gollmann-Tepeköylü, M. Kollarova, K. Petrikova, O. Tica, KA. Krychtiuk, G. Tavazzi, C. Skurk, K. Huber, A. Böhm
520    9_
$a INTRODUCTION: 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. METHODS: 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. RESULTS: We achieved good classification performance thanks to data cleaning and imputation (cross-validated mean area under the curve 0.805) without hyperparameter optimization. CONCLUSION: We believe our pre-processing pipeline would prove helpful also for other classification and regression experiments.
590    __
$a NEINDEXOVÁNO
655    _2
$a časopisecké články $7 D016428
700    1_
$a Bezak, Branislav $u Premedix Academy, Bratislava, Slovakia $u Clinic of Cardiac Surgery, National Institute of Cardiovascular Diseases, Bratislava, Slovakia $u Faculty of Medicine, Comenius University in Bratislava, Bratislava, Slovakia
700    1_
$a Segev, Amitai $u The Leviev Cardiothoracic & Vascular Center, Chaim Sheba Medical Center, Ramat Gan, Israel $u Affiliated to the Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
700    1_
$a Matetzky, Shlomi $u The Leviev Cardiothoracic & Vascular Center, Chaim Sheba Medical Center, Ramat Gan, Israel $u Affiliated to the Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
700    1_
$a Jankova, Jana $u Premedix Academy, Bratislava, Slovakia
700    1_
$a Spartalis, Michael $u 3rd Department of Cardiology, National and Kapodistrian University of Athens, Athens, Greece $u Global Clinical Scholars Research Training (GCSRT) Program, Harvard Medical School, Boston, MA, United States
700    1_
$a El Tahlawi, Mohammad $u Department of Cardiology, Faculty of Human Medicine, Zagazig University, Zagazig, Egypt
700    1_
$a Guerra, Federico $u Cardiology and Arrhythmology Clinic, Marche Polytechnic University, University Hospital "Umberto I - Lancisi - Salesi", Ancona, Italy
700    1_
$a Friebel, Julian $u Department of Cardiology Angiology and Intensive Care Medicine, Deutsches Herzzentrum der Charité (DHZC), Campus Benjamin Franklin, Charité - Universitätsmedizin Berlin, Berlin, Germany
700    1_
$a Thevathasan, Tharusan $u Department of Cardiology Angiology and Intensive Care Medicine, Deutsches Herzzentrum der Charité (DHZC), Campus Benjamin Franklin, Charité - Universitätsmedizin Berlin, Berlin, Germany $u Berlin Institute of Health, Charité-Universitätsmedizin Berlin, Berlin, Germany $u Deutsches Zentrum für Herz-Kreislauf-Forschung e.V., Berlin, Germany $u Institute of Medical Informatics, Charité-Universitätsmedizin Berlin, Berlin, Germany
700    1_
$a Berta, Imrich $u Premedix Academy, Bratislava, Slovakia
700    1_
$a Pölzl, Leo $u Department for Cardiac Surgery, Cardiac Regeneration Research, Medical University of Innsbruck, Innsbruck, Austria
700    1_
$a Nägele, Felix $u Department for Cardiac Surgery, Cardiac Regeneration Research, Medical University of Innsbruck, Innsbruck, Austria
700    1_
$a Pogran, Edita $u 3rd Medical Department, Cardiology and Intensive Care Medicine, Wilhelminen Hospital, Vienna, Austria
700    1_
$a Cader, F Aaysha $u Department of Cardiology, Ibrahim Cardiac Hospital & Research Institute, Dhaka, Bangladesh
700    1_
$a Jarakovic, Milana $u Cardiac Intensive Care Unit, Institute for Cardiovascular Diseases of Vojvodina, Sremska Kamenica, Serbia $u Faculty of Medicine, University of Novi Sad, Novi Sad, Serbia
700    1_
$a Gollmann-Tepeköylü, Can $u Department for Cardiac Surgery, Cardiac Regeneration Research, Medical University of Innsbruck, Innsbruck, Austria
700    1_
$a Kollarova, Marta $u Premedix Academy, Bratislava, Slovakia
700    1_
$a Petrikova, Katarina $u Premedix Academy, Bratislava, Slovakia
700    1_
$a Tica, Otilia $u Cardiology Department, Emergency County Clinical Hospital of Oradea, Oradea, Romania $u Institute of Cardiovascular Sciences, University of Birmingham, Medical School, Birmingham, United Kingdom
700    1_
$a Krychtiuk, Konstantin A $u Department of Internal Medicine II, Division of Cardiology, Medical University of Vienna, Vienna, Austria $u Duke Clinical Research Institute Durham, NC, United States
700    1_
$a Tavazzi, Guido $u Department of Clinical-Surgical, Diagnostic and Paediatric Sciences, University of Pavia, Pavia, Italy $u Anesthesia and Intensive Care, Fondazione Policlinico San Matteo Hospital IRCCS, Pavia, Italy
700    1_
$a Skurk, Carsten $u Department of Cardiology Angiology and Intensive Care Medicine, Deutsches Herzzentrum der Charité (DHZC), Campus Benjamin Franklin, Charité - Universitätsmedizin Berlin, Berlin, Germany $u Deutsches Zentrum für Herz-Kreislauf-Forschung e.V., Berlin, Germany
700    1_
$a Huber, Kurt $u 3rd Medical Department, Cardiology and Intensive Care Medicine, Wilhelminen Hospital, Vienna, Austria
700    1_
$a Böhm, Allan $u Premedix Academy, Bratislava, Slovakia $u Faculty of Medicine, Comenius University in Bratislava, Bratislava, Slovakia $u Department of Acute Cardiology, National Institute of Cardiovascular Diseases, Bratislava, Slovakia
773    0_
$w MED00198704 $t Frontiers in cardiovascular medicine $x 2297-055X $g Roč. 10, č. - (2023), s. 1132680
856    41
$u https://pubmed.ncbi.nlm.nih.gov/37034352 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y p $z 0
990    __
$a 20230707 $b ABA008
991    __
$a 20230721095316 $b ABA008
999    __
$a ok $b bmc $g 1958640 $s 1196389
BAS    __
$a 3
BAS    __
$a PreBMC-PubMed-not-MEDLINE
BMC    __
$a 2023 $b 10 $c - $d 1132680 $e 20230323 $i 2297-055X $m Frontiers in cardiovascular medicine $n Front Cardiovasc Med $x MED00198704
LZP    __
$a Pubmed-20230707

Find record

Citation metrics

Loading data ...

Archiving options

Loading data ...