Cargando…

A Clinically Applicable Approach to the Classification of B-Cell Non-Hodgkin Lymphomas with Flow Cytometry and Machine Learning

The immunophenotype is a key element to classify B-cell Non-Hodgkin Lymphomas (B-NHL); while it is routinely obtained through immunohistochemistry, the use of flow cytometry (FC) could bear several advantages. However, few FC laboratories can rely on a long-standing practical experience, and the lit...

Descripción completa

Detalles Bibliográficos
Autores principales: Gaidano, Valentina, Tenace, Valerio, Santoro, Nathalie, Varvello, Silvia, Cignetti, Alessandro, Prato, Giuseppina, Saglio, Giuseppe, De Rosa, Giovanni, Geuna, Massimo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7352227/
https://www.ncbi.nlm.nih.gov/pubmed/32599959
http://dx.doi.org/10.3390/cancers12061684
_version_ 1783557588513718272
author Gaidano, Valentina
Tenace, Valerio
Santoro, Nathalie
Varvello, Silvia
Cignetti, Alessandro
Prato, Giuseppina
Saglio, Giuseppe
De Rosa, Giovanni
Geuna, Massimo
author_facet Gaidano, Valentina
Tenace, Valerio
Santoro, Nathalie
Varvello, Silvia
Cignetti, Alessandro
Prato, Giuseppina
Saglio, Giuseppe
De Rosa, Giovanni
Geuna, Massimo
author_sort Gaidano, Valentina
collection PubMed
description The immunophenotype is a key element to classify B-cell Non-Hodgkin Lymphomas (B-NHL); while it is routinely obtained through immunohistochemistry, the use of flow cytometry (FC) could bear several advantages. However, few FC laboratories can rely on a long-standing practical experience, and the literature in support is still limited; as a result, the use of FC is generally restricted to the analysis of lymphomas with bone marrow or peripheral blood involvement. In this work, we applied machine learning to our database of 1465 B-NHL samples from different sources, building four artificial predictive systems which could classify B-NHL in up to nine of the most common clinico-pathological entities. Our best model shows an overall accuracy of 92.68%, a mean sensitivity of 88.54% and a mean specificity of 98.77%. Beyond the clinical applicability, our models demonstrate (i) the strong discriminatory power of MIB1 and Bcl2, whose integration in the predictive model significantly increased the performance of the algorithm; (ii) the potential usefulness of some non-canonical markers in categorizing B-NHL; and (iii) that FC markers should not be described as strictly positive or negative according to fixed thresholds, but they rather correlate with different B-NHL depending on their level of expression.
format Online
Article
Text
id pubmed-7352227
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-73522272020-07-21 A Clinically Applicable Approach to the Classification of B-Cell Non-Hodgkin Lymphomas with Flow Cytometry and Machine Learning Gaidano, Valentina Tenace, Valerio Santoro, Nathalie Varvello, Silvia Cignetti, Alessandro Prato, Giuseppina Saglio, Giuseppe De Rosa, Giovanni Geuna, Massimo Cancers (Basel) Article The immunophenotype is a key element to classify B-cell Non-Hodgkin Lymphomas (B-NHL); while it is routinely obtained through immunohistochemistry, the use of flow cytometry (FC) could bear several advantages. However, few FC laboratories can rely on a long-standing practical experience, and the literature in support is still limited; as a result, the use of FC is generally restricted to the analysis of lymphomas with bone marrow or peripheral blood involvement. In this work, we applied machine learning to our database of 1465 B-NHL samples from different sources, building four artificial predictive systems which could classify B-NHL in up to nine of the most common clinico-pathological entities. Our best model shows an overall accuracy of 92.68%, a mean sensitivity of 88.54% and a mean specificity of 98.77%. Beyond the clinical applicability, our models demonstrate (i) the strong discriminatory power of MIB1 and Bcl2, whose integration in the predictive model significantly increased the performance of the algorithm; (ii) the potential usefulness of some non-canonical markers in categorizing B-NHL; and (iii) that FC markers should not be described as strictly positive or negative according to fixed thresholds, but they rather correlate with different B-NHL depending on their level of expression. MDPI 2020-06-24 /pmc/articles/PMC7352227/ /pubmed/32599959 http://dx.doi.org/10.3390/cancers12061684 Text en © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Gaidano, Valentina
Tenace, Valerio
Santoro, Nathalie
Varvello, Silvia
Cignetti, Alessandro
Prato, Giuseppina
Saglio, Giuseppe
De Rosa, Giovanni
Geuna, Massimo
A Clinically Applicable Approach to the Classification of B-Cell Non-Hodgkin Lymphomas with Flow Cytometry and Machine Learning
title A Clinically Applicable Approach to the Classification of B-Cell Non-Hodgkin Lymphomas with Flow Cytometry and Machine Learning
title_full A Clinically Applicable Approach to the Classification of B-Cell Non-Hodgkin Lymphomas with Flow Cytometry and Machine Learning
title_fullStr A Clinically Applicable Approach to the Classification of B-Cell Non-Hodgkin Lymphomas with Flow Cytometry and Machine Learning
title_full_unstemmed A Clinically Applicable Approach to the Classification of B-Cell Non-Hodgkin Lymphomas with Flow Cytometry and Machine Learning
title_short A Clinically Applicable Approach to the Classification of B-Cell Non-Hodgkin Lymphomas with Flow Cytometry and Machine Learning
title_sort clinically applicable approach to the classification of b-cell non-hodgkin lymphomas with flow cytometry and machine learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7352227/
https://www.ncbi.nlm.nih.gov/pubmed/32599959
http://dx.doi.org/10.3390/cancers12061684
work_keys_str_mv AT gaidanovalentina aclinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT tenacevalerio aclinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT santoronathalie aclinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT varvellosilvia aclinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT cignettialessandro aclinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT pratogiuseppina aclinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT sagliogiuseppe aclinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT derosagiovanni aclinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT geunamassimo aclinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT gaidanovalentina clinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT tenacevalerio clinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT santoronathalie clinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT varvellosilvia clinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT cignettialessandro clinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT pratogiuseppina clinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT sagliogiuseppe clinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT derosagiovanni clinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning
AT geunamassimo clinicallyapplicableapproachtotheclassificationofbcellnonhodgkinlymphomaswithflowcytometryandmachinelearning