Retrospective Cohort Study
Copyright ©The Author(s) 2024. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Hepatol. Feb 27, 2024; 16(2): 193-210
Published online Feb 27, 2024. doi: 10.4254/wjh.v16.i2.193
Predicting major adverse cardiovascular events after orthotopic liver transplantation using a supervised machine learning model: A cohort study
Jonathan Soldera, Leandro Luis Corso, Matheus Machado Rech, Vinícius Remus Ballotin, Lucas Goldmann Bigarella, Fernanda Tomé, Nathalia Moraes, Rafael Sartori Balbinot, Santiago Rodriguez, Ajacio Bandeira de Mello Brandão, Bruno Hochhegger
Jonathan Soldera, Post Graduate Program at Acute Medicine and Gastroenterology, University of South Wales, Cardiff CF37 1DL, United Kingdom
Jonathan Soldera, Bruno Hochhegger, Postgraduate Program in Pathology, Federal University of Health Sciences of Porto Alegre (UFCSPA), Porto Alegre 90050-170, Brazil
Leandro Luis Corso, Fernanda Tomé, Nathalia Moraes, Department of Engineering, Universidade de Caxias do Sul, Caxias do Sul 95070-560, Brazil
Matheus Machado Rech, Vinícius Remus Ballotin, Lucas Goldmann Bigarella, Rafael Sartori Balbinot, School of Medicine, Universidade de Caxias do Sul, Caxias do Sul 95070-560, Brazil
Santiago Rodriguez, Ajacio Bandeira de Mello Brandão, Postgraduate Program in Hepatology, Federal University of Health Sciences of Porto Alegre (UFCSPA), Porto Alegre 90050-170, Brazil
Co-first authors: Jonathan Soldera and Leandro Luis Corso.
Author contributions: Soldera J, Corso LL, Rech MM, Tomé F, and Moraes N substantially contributed to the conception and design of the work, data collection, and drafting of the manuscript; Corso LL; Rech MM are credited with the development of the algorithm upon which the machine learning model relies; Ballotin VR, Bigarella LG, Balbinot RS, and Rodriguez S substantially contributed to data collection and critical revision of the manuscript; Brandão ABM and Hochhegger B were responsible for supervision, manuscript revision, and additional writing; and all authors have reviewed and approved the final version and agreed to be accountable for the work’s integrity.
Institutional review board statement: The study was reviewed and approved for publication by our Institutional Reviewer under protocol no. 07793412.2.3001.5345.
Informed consent statement: The Ethics Committee waived the need for informed consent for this study since it solely utilized data from medical charts without direct patient contact.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
Data sharing statement: The original anonymous dataset is available on request from the corresponding author at jonathansoldera@gmail.com. The code for implementation of the reported pipeline on the present dataset, including data preprocessing, feature engineering, model development, hypermeter optimization, and model assessment, is provided in the GitHub repository, publicly and freely available through the following link: https://github.com/matheus-rech/ML.
STROBE statement: The authors have read the STROBE Statement-checklist of items, and the manuscript was prepared and revised according to the STROBE Statement-checklist of items.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Jonathan Soldera, MD, PhD, Instructor, Post Graduate Program at Acute Medicine and Gastroenterology, University of South Wales, Llantwit Rd, Pontypridd, Cardiff CF37 1DL, United Kingdom. jonathansoldera@gmail.com
Received: November 2, 2023
Peer-review started: November 2, 2023
First decision: December 1, 2023
Revised: December 27, 2023
Accepted: February 4, 2024
Article in press: February 4, 2024
Published online: February 27, 2024
Processing time: 116 Days and 14.9 Hours
Abstract
BACKGROUND

Liver transplant (LT) patients have become older and sicker. The rate of post-LT major adverse cardiovascular events (MACE) has increased, and this in turn raises 30-d post-LT mortality. Noninvasive cardiac stress testing loses accuracy when applied to pre-LT cirrhotic patients.

AIM

To assess the feasibility and accuracy of a machine learning model used to predict post-LT MACE in a regional cohort.

METHODS

This retrospective cohort study involved 575 LT patients from a Southern Brazilian academic center. We developed a predictive model for post-LT MACE (defined as a composite outcome of stroke, new-onset heart failure, severe arrhythmia, and myocardial infarction) using the extreme gradient boosting (XGBoost) machine learning model. We addressed missing data (below 20%) for relevant variables using the k-nearest neighbor imputation method, calculating the mean from the ten nearest neighbors for each case. The modeling dataset included 83 features, encompassing patient and laboratory data, cirrhosis complications, and pre-LT cardiac assessments. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC). We also employed Shapley additive explanations (SHAP) to interpret feature impacts. The dataset was split into training (75%) and testing (25%) sets. Calibration was evaluated using the Brier score. We followed Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis guidelines for reporting. Scikit-learn and SHAP in Python 3 were used for all analyses. The supplementary material includes code for model development and a user-friendly online MACE prediction calculator.

RESULTS

Of the 537 included patients, 23 (4.46%) developed in-hospital MACE, with a mean age at transplantation of 52.9 years. The majority, 66.1%, were male. The XGBoost model achieved an impressive AUROC of 0.89 during the training stage. This model exhibited accuracy, precision, recall, and F1-score values of 0.84, 0.85, 0.80, and 0.79, respectively. Calibration, as assessed by the Brier score, indicated excellent model calibration with a score of 0.07. Furthermore, SHAP values highlighted the significance of certain variables in predicting postoperative MACE, with negative noninvasive cardiac stress testing, use of nonselective beta-blockers, direct bilirubin levels, blood type O, and dynamic alterations on myocardial perfusion scintigraphy being the most influential factors at the cohort-wide level. These results highlight the predictive capability of our XGBoost model in assessing the risk of post-LT MACE, making it a valuable tool for clinical practice.

CONCLUSION

Our study successfully assessed the feasibility and accuracy of the XGBoost machine learning model in predicting post-LT MACE, using both cardiovascular and hepatic variables. The model demonstrated impressive performance, aligning with literature findings, and exhibited excellent calibration. Notably, our cautious approach to prevent overfitting and data leakage suggests the stability of results when applied to prospective data, reinforcing the model’s value as a reliable tool for predicting post-LT MACE in clinical practice.

Keywords: Liver transplantation; Major adverse cardiac events; Machine learning; Myocardial perfusion imaging; Stress test

Core Tip: This study presents a robust machine learning model, utilizing the XGBoost algorithm, to predict major adverse cardiovascular events (MACE) following liver transplantation. The model demonstrated high accuracy and calibration, with key factors such as noninvasive cardiac stress test outcomes, use of nonselective beta-blockers, direct bilirubin levels, blood type O, and dynamic alterations on myocardial perfusion scintigraphy identified as significant predictors. This tool offers valuable insights into the risk assessment of post-liver transplant MACE, particularly in an aging and comorbid patient population.