Accurate classification of plasma cell dyscrasias is achieved by combining artificial intelligence and flow cytometry

Article Article scientifique Article Accurate classification of plasma cell dyscrasias is achieved by combining artificial intelligence and flow cytometry eng 2021-11-03 2022-03 author Clichet Valentin author Harrivel Véronique author Delette Caroline author Guiheneuf Eric author Gautier Murielle author Morel Pierre 0000-0002-0782-3144 author Assouan Déborah author Merlusca Lavinia author Beaumont Marie author Lebon Delphine author Caulier Alexis author Marolleau Jean-Pierre author Matthes Thomas 0000-0002-4875-2477 27368 author Vergez François 0000-0002-0063-4404 author Garcon Loic 648628 author Boyer Thomas Paul Jean 0000-0001-8133-5491 805149 1175-1183 10.1111/bjh.17933 34730236 0007-1048 Monoclonal gammopathy of unknown significance (MGUS), smouldering multiple myeloma (SMM), and multiple myeloma (MM) are very common neoplasms. However, it is often difficult to distinguish between these entities. In the present study, we aimed to classify the most powerful markers that could improve diagnosis by multiparametric flow cytometry (MFC). The present study included 348 patients based on two independent cohorts. We first assessed how representative the data were in the discovery cohort (123 MM, 97 MGUS) and then analysed their respective plasma cell (PC) phenotype in order to obtain a set of correlations with a hypersphere visualisation. Cluster of differentiation (CD)27 and CD38 were differentially expressed in MGUS and MM (P < 0·001). We found by a gradient boosting machine method that the percentage of abnormal PCs and the ratio PC/CD117 positive precursors were the most influential parameters at diagnosis to distinguish MGUS and MM. Finally, we designed a decisional algorithm allowing a predictive classification ≥95% when PC dyscrasias were suspected, without any misclassification between MGUS and SMM. We validated this algorithm in an independent cohort of PC dyscrasias (n = 87 MM, n = 41 MGUS). This artificial intelligence model is freely available online as a diagnostic tool application website for all MFC centers worldwide (https://aihematology.shinyapps.io/PCdyscrasiasToolDg/). Artificial intelligence Monoclonal gammopathy of undetermined significance Multiparametric flow cytometry Multiple myeloma Aged Artificial Intelligence Diagnosis, Computer-Assisted Female Flow Cytometry Humans Male Monoclonal Gammopathy of Undetermined Significance / classification Monoclonal Gammopathy of Undetermined Significance / diagnosis Multiple Myeloma / classification Multiple Myeloma / diagnosis Paraproteinemias / classification Paraproteinemias / diagnosis Retrospective Studies Dewey 616 56 Département de médecine 221 false 586 Analyses cellulaires et moléculaires des hémopathies malignes 929 British journal of haematology 196 5 6861090f-1340-493c-8dc8-1a8852fdef39 Article (Published version) Restricted Br J Haematol - 2021 - Clichet - Ac.pdf 1311106 application/pdf restrictedAccess Faculté de médecine / Section de médecine clinique / Département de médecine

Title	Published in	Access level	OA Policy	Year	Views	Downloads

Accurate classification of plasma cell dyscrasias is achieved by combining artificial intelligence and flow cytometry	British journal of haematology			2022	288	2

Archive ouverte UNIGE

Boyer, Thomas Paul Jean