Predicting Lymphoma Development by Exploiting Genetic Variants and Clinical Findings in a Machine Learning-Based Methodology With Ensemble Classifiers in a Cohort of Sjögren's Syndrome Patients

Lymphoma development constitutes one of the most serious clinico-pathological manifestations of patients with Sjögren's Syndrome (SS). Over the last decades the risk for lymphomagenesis in SS patients has been studied aiming to identify novel biomarkers and risk factors predict...

Full description

Saved in:
Bibliographic Details
Main Authors: Konstantina D. Kourou, Vasileios C. Pezoulas, Eleni I. Georga, Themis Exarchos, Costas Papaloukas, Michalis Voulgarelis, Andreas Goules, Andrianos Nezos, Athanasios G. Tzioufas, Earalampos M. Moutsopoulos, Clio Mavragani, Dimitrios I. Fotiadis
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Open Journal of Engineering in Medicine and Biology
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8954752/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849416320526843904
author Konstantina D. Kourou
Vasileios C. Pezoulas
Eleni I. Georga
Themis Exarchos
Costas Papaloukas
Michalis Voulgarelis
Andreas Goules
Andrianos Nezos
Athanasios G. Tzioufas
Earalampos M. Moutsopoulos
Clio Mavragani
Dimitrios I. Fotiadis
author_facet Konstantina D. Kourou
Vasileios C. Pezoulas
Eleni I. Georga
Themis Exarchos
Costas Papaloukas
Michalis Voulgarelis
Andreas Goules
Andrianos Nezos
Athanasios G. Tzioufas
Earalampos M. Moutsopoulos
Clio Mavragani
Dimitrios I. Fotiadis
author_sort Konstantina D. Kourou
collection DOAJ
description Lymphoma development constitutes one of the most serious clinico-pathological manifestations of patients with Sj&#x00F6;gren&#x0027;s Syndrome (SS). Over the last decades the risk for lymphomagenesis in SS patients has been studied aiming to identify novel biomarkers and risk factors predicting lymphoma development in this patient population. <italic>Objective:</italic> The current study aims to explore whether genetic susceptibility profiles of SS patients along with known clinical, serological and histological risk factors enhance the accuracy of predicting lymphoma development in this patient population. <italic>Methods:</italic> The potential predicting role of both genetic variants, clinical and laboratory risk factors were investigated through a Machine Learning-based (ML) framework which encapsulates ensemble classifiers. <italic>Results</italic>: Ensemble methods empower the classification accuracy with approaches which are sensitive to minor perturbations in the training phase. The evaluation of the proposed methodology based on a 10-fold stratified cross validation procedure yielded considerable results in terms of balanced accuracy (GB: 0.7780 &#x00B1; 0.1514, RF Gini: 0.7626 &#x00B1; 0.1787, RF Entropy: 0.7590 &#x00B1; 0.1837). <italic>Conclusions:</italic> The initial clinical, serological, histological and genetic findings at an early diagnosis have been exploited in an attempt to establish predictive tools in clinical practice and further enhance our understanding towards lymphoma development in SS.
format Article
id doaj-art-2d633b63df074461851f80840e7a0cf9
institution Kabale University
issn 2644-1276
language English
publishDate 2020-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of Engineering in Medicine and Biology
spelling doaj-art-2d633b63df074461851f80840e7a0cf92025-08-20T03:33:14ZengIEEEIEEE Open Journal of Engineering in Medicine and Biology2644-12762020-01-011495610.1109/OJEMB.2020.29651918954752Predicting Lymphoma Development by Exploiting Genetic Variants and Clinical Findings in a Machine Learning-Based Methodology With Ensemble Classifiers in a Cohort of Sj&#x00F6;gren&#x0027;s Syndrome PatientsKonstantina D. Kourou0https://orcid.org/0000-0003-4310-2739Vasileios C. Pezoulas1https://orcid.org/0000-0002-1872-693XEleni I. Georga2https://orcid.org/0000-0002-3607-0727Themis Exarchos3Costas Papaloukas4https://orcid.org/0000-0002-6736-5536Michalis Voulgarelis5Andreas Goules6Andrianos Nezos7Athanasios G. Tzioufas8Earalampos M. Moutsopoulos9Clio Mavragani10Dimitrios I. Fotiadis11https://orcid.org/0000-0002-5987-9350Unit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, The University of Ioannina, Ioannina, GreeceUnit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, The University of Ioannina, Ioannina, GreeceUnit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, The University of Ioannina, Ioannina, GreeceUnit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, The University of Ioannina, Ioannina, GreeceUnit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, The University of Ioannina, Ioannina, GreeceDepartment of Biomedical Research, Foundation for Research and Technology-Hellas, Institute of Molecular Biology and Biotechnology, Ioannina, GreeceDepartment of Biomedical Research, Foundation for Research and Technology-Hellas, Institute of Molecular Biology and Biotechnology, Ioannina, GreeceDepartment of Physiology, School of Medicine, National and Kapodistrian University of Athens, Athens, GreeceDepartment of Biomedical Research, Foundation for Research and Technology-Hellas, Institute of Molecular Biology and Biotechnology, Ioannina, GreeceAcademy of Athens, Athens, GreeceDepartment of Pathophysiology, School of Medicine, National and Kapodistrian University of Athens, Athens, GreeceUnit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, The University of Ioannina, Ioannina, GreeceLymphoma development constitutes one of the most serious clinico-pathological manifestations of patients with Sj&#x00F6;gren&#x0027;s Syndrome (SS). Over the last decades the risk for lymphomagenesis in SS patients has been studied aiming to identify novel biomarkers and risk factors predicting lymphoma development in this patient population. <italic>Objective:</italic> The current study aims to explore whether genetic susceptibility profiles of SS patients along with known clinical, serological and histological risk factors enhance the accuracy of predicting lymphoma development in this patient population. <italic>Methods:</italic> The potential predicting role of both genetic variants, clinical and laboratory risk factors were investigated through a Machine Learning-based (ML) framework which encapsulates ensemble classifiers. <italic>Results</italic>: Ensemble methods empower the classification accuracy with approaches which are sensitive to minor perturbations in the training phase. The evaluation of the proposed methodology based on a 10-fold stratified cross validation procedure yielded considerable results in terms of balanced accuracy (GB: 0.7780 &#x00B1; 0.1514, RF Gini: 0.7626 &#x00B1; 0.1787, RF Entropy: 0.7590 &#x00B1; 0.1837). <italic>Conclusions:</italic> The initial clinical, serological, histological and genetic findings at an early diagnosis have been exploited in an attempt to establish predictive tools in clinical practice and further enhance our understanding towards lymphoma development in SS.https://ieeexplore.ieee.org/document/8954752/Ensemble methodsgenetic variantslymphoma predictionmachine learningSjögren's Syndrome
spellingShingle Konstantina D. Kourou
Vasileios C. Pezoulas
Eleni I. Georga
Themis Exarchos
Costas Papaloukas
Michalis Voulgarelis
Andreas Goules
Andrianos Nezos
Athanasios G. Tzioufas
Earalampos M. Moutsopoulos
Clio Mavragani
Dimitrios I. Fotiadis
Predicting Lymphoma Development by Exploiting Genetic Variants and Clinical Findings in a Machine Learning-Based Methodology With Ensemble Classifiers in a Cohort of Sj&#x00F6;gren&#x0027;s Syndrome Patients
IEEE Open Journal of Engineering in Medicine and Biology
Ensemble methods
genetic variants
lymphoma prediction
machine learning
Sjögren's Syndrome
title Predicting Lymphoma Development by Exploiting Genetic Variants and Clinical Findings in a Machine Learning-Based Methodology With Ensemble Classifiers in a Cohort of Sj&#x00F6;gren&#x0027;s Syndrome Patients
title_full Predicting Lymphoma Development by Exploiting Genetic Variants and Clinical Findings in a Machine Learning-Based Methodology With Ensemble Classifiers in a Cohort of Sj&#x00F6;gren&#x0027;s Syndrome Patients
title_fullStr Predicting Lymphoma Development by Exploiting Genetic Variants and Clinical Findings in a Machine Learning-Based Methodology With Ensemble Classifiers in a Cohort of Sj&#x00F6;gren&#x0027;s Syndrome Patients
title_full_unstemmed Predicting Lymphoma Development by Exploiting Genetic Variants and Clinical Findings in a Machine Learning-Based Methodology With Ensemble Classifiers in a Cohort of Sj&#x00F6;gren&#x0027;s Syndrome Patients
title_short Predicting Lymphoma Development by Exploiting Genetic Variants and Clinical Findings in a Machine Learning-Based Methodology With Ensemble Classifiers in a Cohort of Sj&#x00F6;gren&#x0027;s Syndrome Patients
title_sort predicting lymphoma development by exploiting genetic variants and clinical findings in a machine learning based methodology with ensemble classifiers in a cohort of sj x00f6 gren x0027 s syndrome patients
topic Ensemble methods
genetic variants
lymphoma prediction
machine learning
Sjögren's Syndrome
url https://ieeexplore.ieee.org/document/8954752/
work_keys_str_mv AT konstantinadkourou predictinglymphomadevelopmentbyexploitinggeneticvariantsandclinicalfindingsinamachinelearningbasedmethodologywithensembleclassifiersinacohortofsjx00f6grenx0027ssyndromepatients
AT vasileioscpezoulas predictinglymphomadevelopmentbyexploitinggeneticvariantsandclinicalfindingsinamachinelearningbasedmethodologywithensembleclassifiersinacohortofsjx00f6grenx0027ssyndromepatients
AT eleniigeorga predictinglymphomadevelopmentbyexploitinggeneticvariantsandclinicalfindingsinamachinelearningbasedmethodologywithensembleclassifiersinacohortofsjx00f6grenx0027ssyndromepatients
AT themisexarchos predictinglymphomadevelopmentbyexploitinggeneticvariantsandclinicalfindingsinamachinelearningbasedmethodologywithensembleclassifiersinacohortofsjx00f6grenx0027ssyndromepatients
AT costaspapaloukas predictinglymphomadevelopmentbyexploitinggeneticvariantsandclinicalfindingsinamachinelearningbasedmethodologywithensembleclassifiersinacohortofsjx00f6grenx0027ssyndromepatients
AT michalisvoulgarelis predictinglymphomadevelopmentbyexploitinggeneticvariantsandclinicalfindingsinamachinelearningbasedmethodologywithensembleclassifiersinacohortofsjx00f6grenx0027ssyndromepatients
AT andreasgoules predictinglymphomadevelopmentbyexploitinggeneticvariantsandclinicalfindingsinamachinelearningbasedmethodologywithensembleclassifiersinacohortofsjx00f6grenx0027ssyndromepatients
AT andrianosnezos predictinglymphomadevelopmentbyexploitinggeneticvariantsandclinicalfindingsinamachinelearningbasedmethodologywithensembleclassifiersinacohortofsjx00f6grenx0027ssyndromepatients
AT athanasiosgtzioufas predictinglymphomadevelopmentbyexploitinggeneticvariantsandclinicalfindingsinamachinelearningbasedmethodologywithensembleclassifiersinacohortofsjx00f6grenx0027ssyndromepatients
AT earalamposmmoutsopoulos predictinglymphomadevelopmentbyexploitinggeneticvariantsandclinicalfindingsinamachinelearningbasedmethodologywithensembleclassifiersinacohortofsjx00f6grenx0027ssyndromepatients
AT cliomavragani predictinglymphomadevelopmentbyexploitinggeneticvariantsandclinicalfindingsinamachinelearningbasedmethodologywithensembleclassifiersinacohortofsjx00f6grenx0027ssyndromepatients
AT dimitriosifotiadis predictinglymphomadevelopmentbyexploitinggeneticvariantsandclinicalfindingsinamachinelearningbasedmethodologywithensembleclassifiersinacohortofsjx00f6grenx0027ssyndromepatients