Predicting the Need for Cardiovascular Surgery: A   Comparative   Study   of   Machine   Learning Models

Arman Ghavidel; Pilar Pazos; Rolando  Del Aguila Suarez; Alireza Atashi

doi:10.35882/jeeemi.v6i2.359

Arman Ghavidel Department of Engineering Management and Systems Engineering, Old Dominion University, Norfolk, USA https://orcid.org/0009-0003-9798-8958
Pilar Pazos Department of Engineering Management and Systems Engineering, Old Dominion University, Norfolk, USA https://orcid.org/0000-0003-4348-7798
Rolando Del Aguila Suarez School of Nursing, Hampton University, Hampton, VA, USA
Alireza Atashi Department of Digital Health, Tehran University of Medical Sciences, Tehran, Iran https://orcid.org/0000-0002-9923-9665

DOI: https://doi.org/10.35882/jeeemi.v6i2.359

Keywords: clinical decision-making, deep neural networks, health feature selection, resampling methods, imbalanced data, machine learning

Abstract

This research examines the efficacy of ensemble Machine Learning (ML) models, mainly focusing on Deep Neural Networks (DNNs), in predicting the need for cardiovascular surgery, a critical aspect of clinical decision-making. It addresses key challenges such as class imbalance, which is pivotal in healthcare settings. The research involved a comprehensive comparison and evaluation of the performance of previously published ML methods against a new Deep Learning (DL) model. This comparison utilized a dataset encompassing 50,000 patient records from a large hospital between 2015-2022. The study proposes enhancing the efficacy of these models through feature selection and hyperparameter optimization, employing techniques like grid search. A novel aspect of this research was the comparison of a newly developed DNN model with existing ensemble models based on similar cardiovascular datasets. The results indicated the DNN model's superior predictive accuracy, demonstrating an Area Under the Curve (AUC) of 74%, alongside notable precision (68%) and recall (72%) for the minority class, which indicates patients requiring surgery. The model further achieved a 70% F1-Score and a balanced accuracy rate of 72%, significantly outperforming the existing ensemble models in every key performance metric. The study underscores the transformative potential of DNNs in predictive modeling for cardiovascular care and highlights the importance of integrating advanced ML techniques into clinical workflows. Future research should delve into the practical application and integration of these models.

Downloads

Download data is not yet available.

Author Biographies

Arman Ghavidel, Department of Engineering Management and Systems Engineering, Old Dominion University, Norfolk, USA

Arman Ghavidel is currently pursuing his Ph.D. in Engineering Management and Systems Engineering at Old Dominion University, located in Norfolk, VA, USA. He specializes in the intersection of healthcare and technology, and his research is focused on leveraging Machine Learning, Deep Learning, and Data Mining techniques to address critical challenges in healthcare. Arman is dedicated to advancing the field through innovative research and is actively involved in the academic community, contributing to the development of cutting-edge solutions that promise to transform healthcare delivery and patient outcomes

Pilar Pazos, Department of Engineering Management and Systems Engineering, Old Dominion University, Norfolk, USA

Pilar Pazos is a Professor in the Department of Engineering Management and Systems Engineering at Old Dominion University. She received a B.S. and M.S. Industrial Engineering from the University of Vigo, Spain, a M.S. in Systems Engineering. and PhD in Industrial Engineering from Texas Tech University. She has published studies in process improvement, modeling and simulation, and data analytics in health care

Rolando Del Aguila Suarez, School of Nursing, Hampton University, Hampton, VA, USA

Dr. Rolando Del Aguila Suarez is a distinguished professional with a Ph.D. in Healthcare Administration and a Master of Nursing, among other qualifications. He has worked as a biomedical researcher, healthcare administrator, and nurse, and has extensive experience managing medical and educational facilities. Currently, he serves as an Assistant Professor at Hampton University School of Nursing, where he integrates his vast experience into his teaching, with a focus on promoting mental health awareness in the community

Alireza Atashi, Department of Digital Health, Tehran University of Medical Sciences, Tehran, Iran

ALIREZA ATASHI is the Head of the Cancer Informatics Department at Motamed Cancer Institute, Tehran, Iran, and an Assistant Professor in medical informatics at the e-Health Department at Tehran University of Medical Sciences. His research interests include medical data mining, clinical informatics, patient registries, and telemedicine, especially in cancer and intensive care fields, where he has done several studies

References

Park, J. and P.N. Bonde, Machine Learning in Cardiac Surgery: Predicting Mortality and Readmission. Asaio j, 2022. 68(12): p. 1490-1500.

Song, Z., et al., Machine learning in predicting cardiac surgery-associated acute kidney injury: A systemic review and meta-analysis. Frontiers in Cardiovascular Medicine, 2022. 9.

Musikant, D., et al., Host Epac1 is required for cAMP-mediated invasion by Trypanosoma cruzi. Molecular and Biochemical Parasitology, 2017. 211: p. 67-70.

Fu, M., et al. An Ensemble Machine Learning Model For the Early Detection of Sepsis From Clinical Data. in 2019 Computing in Cardiology (CinC). 2019.

Anderson, J.G., et al., Modeling the costs and outcomes of cardiovascular surgery. Health Care Management Science, 2002. 5: p. 103-111.

Park, D.J., et al., Development of machine learning model for diagnostic disease prediction based on laboratory tests. Scientific reports, 2021. 11(1): p. 7567.

Vervoort, D., et al., Cardiac surgery in low-and middle-income countries: a state-of-the-art review. The Annals of Thoracic Surgery, 2021. 111(4): p. 1394-1400.

Vervoort, D., et al., Global cardiac surgery: access to cardiac surgical care around the world. The Journal of thoracic and cardiovascular surgery, 2020. 159(3): p. 987-996. e6.

Huang, Y., et al., Application of machine learning in predicting survival outcomes involving real-world data: a scoping review. BMC Medical Research Methodology, 2023. 23(1): p. 268.

Zhou, P.-Y. and A.K.C. Wong, Explanation and prediction of clinical data with imbalanced class distribution based on pattern discovery and disentanglement. BMC Medical Informatics and Decision Making, 2021. 21(1): p. 16.

Ghavidel, A., R. Ghousi, and A. Atashi, An ensemble data mining approach to discover medical patterns and provide a system to predict the mortality in the ICU of cardiac surgery based on stacking machine learning method. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2023. 11(4): p. 1316-1326.

Ghavidel, A., P. Pazos-Lago, and R. Ghousi, Proceedings of the IISE Annual Conference & Expo 2023, in Institute of Industrial and Systems Engineers (IISE), B.E. K. Babski-Reeves, D. Hampton, eds., Editor. 2023, IISE: New Orleans, Louisiana.

Sayılar, B.C. and O. Ceylan. Grid Search Based Hyperparameter Optimization for Machine Learning Based Non-Intrusive Load Monitoring. in 2023 58th International Universities Power Engineering Conference (UPEC). 2023. IEEE.

Triwiyanto, T., et al., How Deep Learning and Neural Networks can Improve Prosthetics and Exoskeletons: A Review of State-of-the-Art Methods and Challenges. Journal of Electronics, Electromedical Engineering, and Medical Informatics, 2023. 5(4): p. 277-289.

Lapp, L., et al. Evaluation of random forest and ensemble methods at predicting complications following cardiac surgery. in Conference on Artificial Intelligence in Medicine in Europe. 2019. Springer.

Ghorbani, R., et al., A New Hybrid Predictive Model to Predict the Early Mortality Risk in Intensive Care Units on a Highly Imbalanced Dataset. IEEE Access, 2020. 8: p. 141066-141079.

Zheng, H., S.W.A. Sherazi, and J.Y. Lee, A Stacking Ensemble Prediction Model for the Occurrences of Major Adverse Cardiovascular Events in Patients With Acute Coronary Syndrome on Imbalanced Data. IEEE Access, 2021. 9: p. 113692-113704.

Razzaghi, T., et al., Predictive models for bariatric surgery risks with imbalanced medical datasets. Annals of Operations Research, 2019. 280(1): p. 1-18.

Shamshirband, S., et al., A review on deep learning approaches in healthcare systems: Taxonomies, challenges, and open issues. Journal of Biomedical Informatics, 2021. 113: p. 103627.

Kotsiantis, S.B., D. Kanellopoulos, and P.E. Pintelas, Data preprocessing for supervised leaning. International journal of computer science, 2006. 1(2): p. 111-117.

Géron, A., Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. 2022: " O'Reilly Media, Inc.".

Javadnejad, F., et al., Analyzing incentives and barriers to electric vehicle adoption in the United States. Environment Systems and Decisions, 2023.

Iklima, Z., T.M. Kadarina, and R. Priambodo, Reduction of feature extraction for COVID-19 CXR using depthwise separable convolution network. Journal of Electronics, Electromedical Engineering, and Medical Informatics, 2022. 4(4): p. 204-209.

Zheng, A. and A. Casari, Feature engineering for machine learning: principles and techniques for data scientists. 2018: " O'Reilly Media, Inc.".

Basiri, M., F. Javadnejad, and A. Saeidi. Forecasting crude oil price with an artificial neural network model based on a regular pattern for selecting training and testing sets using dynamic command-line functions. in 24th International Mining Congress & Exhibition of Turkey (IMCET). 2015.

Ghavidel, A. and P. Pazos, Machine learning (ML) techniques to predict breast cancer in imbalanced datasets: a systematic review. Journal of Cancer Survivorship, 2023.

Ansyari, M.R., et al., Implementation of Random Forest and Extreme Gradient Boosting in the Classification of Heart Disease Using Particle Swarm Optimization Feature Selection. Journal of Electronics, Electromedical Engineering, and Medical Informatics, 2023. 5(4): p. 250-260.

Ghavidel, A., R. Ghousi, and A. Atashi, An ensemble data mining approach to discover medical patterns and provide a system to predict the mortality in the ICU of cardiac surgery based on stacking machine learning method. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2022: p. 1-11.

Veerman, J.L., et al., Television viewing time and reduced life expectancy: a life table analysis. British journal of sports medicine, 2012. 46(13): p. 927-930.

Powell-Wiley, T.M., et al., Obesity and cardiovascular disease: a scientific statement from the American Heart Association. Circulation, 2021. 143(21): p. e984-e1010.

Nugraha, A.T., Design and build a distance and heart rate monitoring system on a dynamic bike integrated with power generating system. Journal of Electronics, Electromedical Engineering, and Medical Informatics, 2022. 4(4): p. 210–215-210–215.

Lakatta, E.G., Age-associated cardiovascular changes in health: impact on cardiovascular disease in older persons. Heart failure reviews, 2002. 7: p. 29-49.

Lee, A.L. and R.S. Goldstein, Gastroesophageal reflux disease in COPD: links and risks. International journal of chronic obstructive pulmonary disease, 2015: p. 1935-1949.

Herrera, D., et al., Association between periodontal diseases and cardiovascular diseases, diabetes and respiratory diseases: Consensus report of the Joint Workshop by the European Federation of Periodontology (EFP) and the European arm of the World Organization of Family Doctors (WONCA Europe). Journal of Clinical Periodontology, 2023. 50(6): p. 819-841.

Rosengren, A., et al., Socioeconomic status and risk of cardiovascular disease in 20 low-income, middle-income, and high-income countries: the Prospective Urban Rural Epidemiologic (PURE) study. The Lancet Global Health, 2019. 7(6): p. e748-e760.

Fuchs, F.D. and P.K. Whelton, High blood pressure and cardiovascular disease. Hypertension, 2020. 75(2): p. 285-292.

Akasaki, Y. and M. Ohishi, Cerebrovascular and cardiovascular diseases caused by drugs of abuse. Hypertension Research, 2020. 43(5): p. 363-371.

Masoudkabir, F., et al., Does opium consumption have shared impact on atherosclerotic cardiovascular disease and cancer? Archives of Iranian Medicine, 2022. 25(1): p. 50-63.

Jortveit, J., et al., Incidence, risk factors and outcome of young patients with myocardial infarction. Heart, 2020.

Erlianita, N., et al., Implementation of SMOTE and whale optimization algorithm on breast cancer classification using backpropagation. Journal of Electronics, Electromedical Engineering, and Medical Informatics, 2023. 5(4): p. 303–313-303–313.

Chawla, N.V., et al., SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, 2002. 16: p. 321-357.

He, H., et al. Adaptive synthetic sampling approach for imbalanced learning. IEEE international joint conference on neural networks. in IEEE World Congress On Computational Intelligence. 2008.

Mishra, S., Artificial intelligence: A review of progress and prospects in medicine and healthcare. Journal of Electronics, Electromedical Engineering, and Medical Informatics, 2022. 4(1): p. 1-23.

Davis, J. and M. Goadrich. The relationship between Precision-Recall and ROC curves. in Proceedings of the 23rd international conference on Machine learning. 2006.

Fawcett, T., An introduction to ROC analysis. Pattern recognition letters, 2006. 27(8): p. 861-874.

Carrington, A.M., et al., Deep ROC analysis and AUC as balanced average accuracy, for improved classifier selection, audit and explanation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022. 45(1): p. 329-341.