Artificial-Intelligence, Data-Driven, Comprehensive Classification of Myeloid Neoplasms Based on Genomic, Morphological and Histological Features

Background. Recent advancements in genome characterization have transformed the study of myeloid neoplasms (MN). Accordingly, there is a shift from traditional classification schemes, based on morphological and clinical information, to next-generation systems (2022 WHO/ICC) which incorporate genomic features. However, current classifications do not clearly define the hierarchical importance of genomic vs morphological features in determining disease entities, leading to inconsistencies in clinical practice; moreover, they do not specifically address areas of overlap among different MN Methods. In the TITAN study, we retrospectively studied 20,054 patients with MN in which clinical and morphological data, together with cytogenetics, mutational screening and outcome were available. We included 7104 AML, 8410 MDS, 2986 MDS/MPN and 1554 MF. We used MOSAIC, an AI-based framework to define unsupervised clusters according to homogeneous morphological and genomic features. Shapley Additive exPlanations (SHAP) was applied to investigate features of importance and their effects on cluster assignment Results. We identified 34 distinct clusters and created a dashboard (https://titan-xkb3corsxq-ew.a.run.app/) where the most relevant features, clinical phenotypes, and outcomes are summarized. SHAP revealed that genomics often outweighs morphology in defining disease entities Six clusters had splicing mutations as dominant features, albeit with different hematological phenotypes (mainly including MDS and MDS/MPN pts). The presence of additional high-risk genomic features (RUNX1/ASXL1 mutations, del(7q)/-7, abn(3q26.2) and complex karyotype) identified patients with poor survival within each category. A separate cluster including MN with splicing mutations and increased blasts (mainly including MDS and AML patients) was characterized by poor response to treatments and dismal outcome MN with TP53 mutations constituted a distinct entity, regardless of clinical phenotype and blast count and had the poorest prognosis. Mutational and CNV analysis showed biallelic inactivation of TP53 in the majority of patients. Most monoallelic TP53 were assigned to a different cluster. Patients that evolved to AML often acquired biallelic inactivation, suggesting that TP53 allelic status may identify different disease phases within the same entity Among morphological features, marrow fibrosis held significant hierarchical importance in defining clusters, driving patient assignment into three distinct groups characterized by 1) JAK/STAT mutations alone, 2) JAK/STAT mutations with high-risk molecular features, 3) wildtype JAK/STAT. The latter group included both MDS and MF patients who exhibited a higher risk of clonal evolution and shorter survival Overall, 10 out of 34 clusters included patients from different MN subtypes as defined by ICC/WHO criteria, accounting for 38.1% of the entire population. This suggests that current classifications do not efficiently capture boundaries between different entities. Importantly, among 1482 patients with RNAseq data from BM progenitors available, the newly identified clusters exhibited distinct gene expression profiles, thus providing evidence for the biological consistency of the proposed classification The 34 clusters were characterized by different risks of clonal progression and survival. Based on this finding and the observation that, in most cases, heterogeneous phenotypes contributed to each cluster, we developed a pan-MN prognostic score. This score is based on clinical and molecular parameters and is designed to be applicable to all patients, regardless of clinical labels. The performance of the score (c-index 0.75) was comparable to that of currently available disease-specific tools Conclusion. The integrative analysis of genomic profiling and morphological features provides a proof of concept for a novel classification approach for MN, that may refine the overlapping areas among disease entities and more effectively identify patients with a homogeneous biological background. It could serve as a foundation for an innovative prognostic assessment of MN patients, independent of traditional clinical labels. The clinical implementation of pan-MN tools is expected to improve the effectiveness and quality of personalized diagnosis, treatment decisions and clinical trial eligibility

Authors

Institutions

Publication Details

Journal
Blood
Published
2024-11-05
DOI
https://doi.org/10.1182/blood-2024-204826
Citations
2
Primary Topic
Digital Imaging for Blood Diseases
Type
article
Field-Weighted Citation Impact
0.50

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Artificial-Intelligence, Data-Driven, Comprehensive Classification of Myeloid Neoplasms Based on Genomic, Morphological and Histological Features

Yu‐Hung Wang, Elena Riva, Hsin‐An Hou, Francesca Ficara et al.
2 citations
Blood
Digital Imaging for Blood Diseases
0.50
article

Artificial-Intelligence, Data-Driven, Comprehensive Classification of Myeloid Neoplasms Based on Genomic, Morphological and Histological Features

Yu‐Hung Wang, Elena Riva, Hsin‐An Hou, Francesca Ficara, Elisabetta Sauta, Ulrich Germing, Francesco Passamonti, Wen‐Chien Chou, Rami S. Komrokji, Marie Robin, Saverio D’Amico, Paola Guglielmelli, David Quintela, Lorenzo Dall’Olio, Ilaria Carola Casetti, Chien‐Chin Lin, Anthony Michael Hunter, Alessia Campagna, Éric Solary, Matteo Zampini, Gastone Castellani, David Andrew Sallman, Angela Consagra, Erica Travaglino, Massimo Bernardi, Anne Sophie Kubasch, Claudia Sala, Tariq Zuheir Kewan, Daniele Dall’Olio, Vladan Vučinić, Somedeb Ball, Manja Meggendorfer, Eric Padron, Patrizia Chiusolo, Torsten Haferlach, Cristina Astrid Tentori, Alessandro Maria Vannucchi, Wolfgang Kern, Lisa Pleyer, Sanam Loghavi, Marisa Calabuig, Nico Gagelmann, Carmelo Gurnari, Gabriele Todisco, María Díez‐Campelo, Maria Teresa Voso, Chi‐Yuan Yao, Blanca Xicoy, Alejandro Pita, Marina Díaz‐Beyá, Michaëla Fontenay, Marta Ubezio, Uwe Platzbecker, Françesc Solé, Hussein Awada, Jan Philipp Bewersdorf, Jaroslaw Pawel Maciejewski, Giulia Maggioni, Andrés Jerez, Luca Lanino, Verónica Roldán, Laura Palomo, Matteo Giovanni Della Porta, Valeria Santini, Gianluca Asti, Alessandro Buizza, Mattia Delleani, Armando Santoro, Antonio Russo, Paloma García Martín, Estefania Cerezo Velasco, Pierre Fenaux, Guillermo Garcia-Manero, Elena Cornejo, Amer M. Zeidan, Najla H. Al Ali, Lorenza Borin, Nicolaus Kröger, Hwei-Fang Tien, Dolly Viviana Fiallo Suarez
article en
2 citations

Abstract

Background. Recent advancements in genome characterization have transformed the study of myeloid neoplasms (MN). Accordingly, there is a shift from traditional classification schemes, based on morphological and clinical information, to next-generation systems (2022 WHO/ICC) which incorporate genomic features. However, current classifications do not clearly define the hierarchical importance of genomic vs morphological features in determining disease entities, leading to inconsistencies in clinical practice; moreover, they do not specifically address areas of overlap among different MN Methods. In the TITAN study, we retrospectively studied 20,054 patients with MN in which clinical and morphological data, together with cytogenetics, mutational screening and outcome were available. We included 7104 AML, 8410 MDS, 2986 MDS/MPN and 1554 MF. We used MOSAIC, an AI-based framework to define unsupervised clusters according to homogeneous morphological and genomic features. Shapley Additive exPlanations (SHAP) was applied to investigate features of importance and their effects on cluster assignment Results. We identified 34 distinct clusters and created a dashboard (https://titan-xkb3corsxq-ew.a.run.app/) where the most relevant features, clinical phenotypes, and outcomes are summarized. SHAP revealed that genomics often outweighs morphology in defining disease entities Six clusters had splicing mutations as dominant features, albeit with different hematological phenotypes (mainly including MDS and MDS/MPN pts). The presence of additional high-risk genomic features (RUNX1/ASXL1 mutations, del(7q)/-7, abn(3q26.2) and complex karyotype) identified patients with poor survival within each category. A separate cluster including MN with splicing mutations and increased blasts (mainly including MDS and AML patients) was characterized by poor response to treatments and dismal outcome MN with TP53 mutations constituted a distinct entity, regardless of clinical phenotype and blast count and had the poorest prognosis. Mutational and CNV analysis showed biallelic inactivation of TP53 in the majority of patients. Most monoallelic TP53 were assigned to a different cluster. Patients that evolved to AML often acquired biallelic inactivation, suggesting that TP53 allelic status may identify different disease phases within the same entity Among morphological features, marrow fibrosis held significant hierarchical importance in defining clusters, driving patient assignment into three distinct groups characterized by 1) JAK/STAT mutations alone, 2) JAK/STAT mutations with high-risk molecular features, 3) wildtype JAK/STAT. The latter group included both MDS and MF patients who exhibited a higher risk of clonal evolution and shorter survival Overall, 10 out of 34 clusters included patients from different MN subtypes as defined by ICC/WHO criteria, accounting for 38.1% of the entire population. This suggests that current classifications do not efficiently capture boundaries between different entities. Importantly, among 1482 patients with RNAseq data from BM progenitors available, the newly identified clusters exhibited distinct gene expression profiles, thus providing evidence for the biological consistency of the proposed classification The 34 clusters were characterized by different risks of clonal progression and survival. Based on this finding and the observation that, in most cases, heterogeneous phenotypes contributed to each cluster, we developed a pan-MN prognostic score. This score is based on clinical and molecular parameters and is designed to be applicable to all patients, regardless of clinical labels. The performance of the score (c-index 0.75) was comparable to that of currently available disease-specific tools Conclusion. The integrative analysis of genomic profiling and morphological features provides a proof of concept for a novel classification approach for MN, that may refine the overlapping areas among disease entities and more effectively identify patients with a homogeneous biological background. It could serve as a foundation for an innovative prognostic assessment of MN patients, independent of traditional clinical labels. The clinical implementation of pan-MN tools is expected to improve the effectiveness and quality of personalized diagnosis, treatment decisions and clinical trial eligibility

BloodVol. 144(Supplement 1)
University of Rome Tor Vergata (IT), Universitat Autònoma de Barcelona (ES), Cleveland Clinic (US), Memorial Sloan Kettering Cancer Center (US), Humanitas University (IT), The University of Texas MD Anderson Cancer Center (US), Emory University (US), Inserm (FR), Universität Hamburg (DE), University of Milan (IT), Université Paris Cité (FR), Agostino Gemelli University Polyclinic (IT), Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico (IT), Moffitt Cancer Center (US), Yale University (US), Kettering University (US), Düsseldorf University Hospital (DE), Josep Carreras Leukaemia Research Institute (ES), Hôpital Cochin (FR), Munich Leukemia Laboratory (Germany) (DE), Assistance Publique – Hôpitaux de Paris (FR), Hospital Universitario de Gran Canaria Doctor Negrín (ES), Consorci Sanitari de Terrassa (ES), Complejo Hospitalario de Salamanca (ES), Far Eastern Memorial Hospital (TW), Institut Català d'Oncologia (ES), University Medical Center Hamburg-Eppendorf (DE), Azienda Ospedaliera San Gerardo (IT), Instituto de Investigación Biosanitaria de Granada (ES), Institute of Neurological Sciences (IT), Istituto delle Scienze Neurologiche di Bologna (IT), Vall d'Hebron Hospital Universitari (ES), National Taiwan University Hospital (TW), Instituto de Investigación Biomédica de Salamanca (ES), Hospital de Cruces (ES), Groupe Francophone des Myélodysplasies (FR), Centro de Investigación del Cáncer (ES), Hôpital Saint-Louis (FR), Fundación Josep Carreras Contra la Leucemia (ES), Policlinico San Matteo Fondazione (IT), Istituti di Ricovero e Cura a Carattere Scientifico (IT), ASST Fatebenefratelli Sacco (IT), INCLIVA Health Research Institute (ES), IRCCS Humanitas Research Hospital (IT), Smilow Cancer Hospital (US), Heinrich Heine University Düsseldorf (DE), University of Florence (IT), Vanderbilt University Medical Center (US), Leipzig University (DE), University of Bologna (IT)
Amgen, Bristol-Myers Squibb, Gilead Sciences, Alexion Pharmaceuticals, Celgene, Therakos, Helsinn, Jazz Pharmaceuticals, National Comprehensive Cancer Network, Astex Pharmaceuticals, Agios Pharmaceuticals, CTI Biopharma, Incyte, Syndax Pharmaceuticals, Astellas Pharma, Servier, Swedish Orphan Biovitrum, Medac, Aptitude Health, Genentech, Daiichi Sankyo Europe
No poverty
Openalex Percentile: Top 33%
Digital Imaging for Blood Diseases
0.50
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.