Data processing pipeline for cardiogenic shock prediction using machine learning

• Published in: Frontiers in cardiovascular medicine Vol. 10; p. 1132680
• Main Authors: Jajcay, Nikola, Bezak, Branislav, Segev, Amitai, Matetzky, Shlomi, Jankova, Jana, Spartalis, Michael, El Tahlawi, Mohammad, Guerra, Federico, Friebel, Julian, Thevathasan, Tharusan, Berta, Imrich, Pölzl, Leo, Nägele, Felix, Pogran, Edita, Cader, F. Aaysha, Jarakovic, Milana, Gollmann-Tepeköylü, Can, Kollarova, Marta, Petrikova, Katarina, Tica, Otilia, Krychtiuk, Konstantin A., Tavazzi, Guido, Skurk, Carsten, Huber, Kurt, Böhm, Allan
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 23.03.2023
• Subjects: cardiogenic shock; Cardiovascular Medicine; classification; machine learning; missing data imputation; prediction model; processing pipeline; processing pipeline; cardiogenic shock; prediction model; classification; machine learning; missing data imputation
• ISSN: 2297-055X; 2297-055X
• DOI: 10.3389/fcvm.2023.1132680

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.