Machine Learning Algorithms to Detect Sex in Myocardial Perfusion Imaging.

Autor:	de Souza Filho EM; Post-graduation in Cardiovascular Sciences, Universidade Federal Fluminense, Niterói, Brazil.; Department of Languages and Technologies, Universidade Federal Rural Do Rio de Janeiro, Rio de Janeiro, Brazil., Fernandes FA; Post-graduation in Cardiovascular Sciences, Universidade Federal Fluminense, Niterói, Brazil.; Department of Nuclear Medicine, Hospital Universitário Antônio Pedro, Universidade Federal Fluminense, Niterói, Brazil., Portela MGR; Department of Psychology, Hospital Pró-Cardíaco, Rio de Janeiro, Brazil., Newlands PH; Department of Education, Instituto Nacional de Cardiologia, Rio de Janeiro, Brazil., de Carvalho LND; Department of Languages and Technologies, Universidade Federal Rural Do Rio de Janeiro, Rio de Janeiro, Brazil., Dos Santos TF; Department of Nuclear Medicine, Hospital Universitário Antônio Pedro, Universidade Federal Fluminense, Niterói, Brazil., Dos Santos AASMD; Post-graduation in Cardiovascular Sciences, Universidade Federal Fluminense, Niterói, Brazil., Mesquita ET; Post-graduation in Cardiovascular Sciences, Universidade Federal Fluminense, Niterói, Brazil., Seixas FL; Institute of Computing, Universidade Federal Fluminense, Niterói, Brazil., Mesquita CT; Post-graduation in Cardiovascular Sciences, Universidade Federal Fluminense, Niterói, Brazil., Gismondi RA; Post-graduation in Cardiovascular Sciences, Universidade Federal Fluminense, Niterói, Brazil.
Jazyk:	angličtina
Zdroj:	Frontiers in cardiovascular medicine [Front Cardiovasc Med] 2021 Oct 29; Vol. 8, pp. 741679. Date of Electronic Publication: 2021 Oct 29 (Print Publication: 2021).
DOI:	10.3389/fcvm.2021.741679
Abstrakt:	Myocardial perfusion imaging (MPI) is an essential tool used to diagnose and manage patients with suspected or known coronary artery disease. Additionally, the General Data Protection Regulation (GDPR) represents a milestone about individuals' data security concerns. On the other hand, Machine Learning (ML) has had several applications in the most diverse knowledge areas. It is conceived as a technology with huge potential to revolutionize health care. In this context, we developed ML models to evaluate their ability to distinguish an individual's sex from MPI assessment. We used 260 polar maps (140 men/120 women) to train ML algorithms from a database of patients referred to a university hospital for clinically indicated MPI from January 2016 to December 2018. We tested 07 different ML models, namely, Classification and Regression Tree (CART), Naive Bayes (NB), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Adaptive Boosting (AB), Random Forests (RF) and, Gradient Boosting (GB). We used a cross-validation strategy. Our work demonstrated that ML algorithms could perform well in assessing the sex of patients undergoing myocardial scintigraphy exams. All the models had accuracy greater than 82%. However, only SVM achieved 90%. KNN, RF, AB, GB had, respectively, 88, 86, 85, 83%. Accuracy standard deviation was lower in KNN, AB, and RF (0.06). SVM and RF had had the best area under the receiver operating characteristic curve (0.93), followed by GB (0.92), KNN (0.91), AB, and NB (0.9). SVM and AB achieved the best precision. Our results bring some challenges regarding the autonomy of patients who wish to keep sex information confidential and certainly add greater complexity to the debate about what data should be considered sensitive to the light of the GDPR. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2021 Souza Filho, Fernandes, Portela, Newlands, Carvalho, Santos, Santos, Mesquita, Seixas, Mesquita and Gismondi.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu