Hematological Oncology journal women in lymphoma special issue: Latest updates in nodal peripheral T-cell lymphoma.

In the last decade, there has been increased understanding of the pathologic features and biology of peripheral T cell lymphomas (PTCLs) through development of multi omics and molecular profiling techniques. In addition, international collaborations through multi center trials as well as prospective registry studies have improved our knowledge of host and tumor genomic factors and treatment factors affecting disease outcomes. In our review today, we aim to highlight the current epidemiology, latest advances in classification, disease biology and the evolving treatment landscape for nodal PTCLs.

Distribution of lymphoma subtypes in Ukraine according to the WHO 2016 classification.

The Ukrainian Lymphoma Registry (ULR) was established in 2019 with the aim of monitoring the quality of diagnosis, staging, and treatment of lymphoma in Ukraine. Between September 2019 and October 2021, 546 patients with newly diagnosed lymphoma were prospectively registered. All cases were diagnosed according to the 2016 updated WHO lymphoma classification. The male-to-female ratio (M/F) for the whole population was 0.7, with a median age of 46 years (range 18-95). The adoption of the 2016 WHO classification resulted in the identification of 36 different lymphoma subtypes, with 132 cases (24.2%) classified differently compared to the 2008 WHO classification. Only 12 cases (2.8%) were true new entities, including seven cases of high-grade B-cell lymphoma NOS, three of anaplastic large B-cell lymphoma, ALK-negative, 1 case of HHV8+ DLBCL NOS, and 1 of high-grade B-cell lymphoma with C-MYC and BCL2/BCL6 rearrangement. Moreover, 55 (61.1%) entities, including 37 defined by WHO 2008 and 18 defined by WHO 2016, were not represented at all. The analysis of cases registered in the ULR provides a comprehensive breakdown of the subtypes, stage distribution, and treatment of malignant lymphomas (ML) in Ukraine, supporting the usefulness of prospective data collection and timely reporting. We believe that this study is the first step toward a better understanding of the real-life outcomes of patients with ML.

Addressing the clinical unmet needs in primary Sjögren's Syndrome through the sharing, harmonization and federated analysis of 21 European cohorts.

For many decades, the clinical unmet needs of primary Sjögren's Syndrome (pSS) have been left unresolved due to the rareness of the disease and the complexity of the underlying pathogenic mechanisms, including the pSS-associated lymphomagenesis process. Here, we present the HarmonicSS cloud-computing exemplar which offers beyond the state-of-the-art data analytics services to address the pSS clinical unmet needs, including the development of lymphoma classification models and the identification of biomarkers for lymphomagenesis. The users of the platform have been able to successfully interlink, curate, and harmonize 21 regional, national, and international European cohorts of 7,551 pSS patients with respect to the ethical and legal issues for data sharing. Federated AI algorithms were trained across the harmonized databases, with reduced execution time complexity, yielding robust lymphoma classification models with 85% accuracy, 81.25% sensitivity, 85.4% specificity along with 5 biomarkers for lymphoma development. To our knowledge, this is the first GDPR compliant platform that provides federated AI services to address the pSS clinical unmet needs.

A computational pipeline for data augmentation towards the improvement of disease classification and risk stratification models: A case study in two clinical domains.

Virtual population generation is an emerging field in data science with numerous applications in healthcare towards the augmentation of clinical research databases with significant lack of population size. However, the impact of data augmentation on the development of AI (artificial intelligence) models to address clinical unmet needs has not yet been investigated. In this work, we assess whether the aggregation of real with virtual patient data can improve the performance of the existing risk stratification and disease classification models in two rare clinical domains, namely the primary Sjögren's Syndrome (pSS) and the hypertrophic cardiomyopathy (HCM), for the first time in the literature. To do so, multivariate approaches, such as, the multivariate normal distribution (MVND), and straightforward ones, such as, the Bayesian networks, the artificial neural networks (ANNs), and the tree ensembles are compared against their performance towards the generation of high-quality virtual data. Both boosting and bagging algorithms, such as, the Gradient boosting trees (XGBoost), the AdaBoost and the Random Forests (RFs) were trained on the augmented data to evaluate the performance improvement for lymphoma classification and HCM risk stratification. Our results revealed the favorable performance of the tree ensemble generators, in both domains, yielding virtual data with goodness-of-fit 0.021 and KL-divergence 0.029 in pSS and 0.029, 0.027 in HCM, respectively. The application of the XGBoost on the augmented data revealed an increase by 10.9% in accuracy, 10.7% in sensitivity, 11.5% in specificity for lymphoma classification and 16.1% in accuracy, 16.9% in sensitivity, 13.7% in specificity in HCM risk stratification.

Ontogeny, Genetics, Molecular Biology, and Classification of B- and T-Cell Non-Hodgkin Lymphoma.

Mature B- and T-cell lymphomas are diverse in their biology, etiology, genetics, clinical behavior, and response to specific therapies. Here, we review the principles of diagnostic classification for non-Hodgkin lymphomas, summarize the characteristic features of major entities, and place recent biological and molecular findings in the context of principles that are applicable across the spectrum of mature lymphoid cancers.

Lymphoma classification update: B-cell non-Hodgkin lymphomas.

INTRODUCTION: Lymphomas are classified based on the normal counterpart, or cell of origin, from which they arise. Because lymphocytes have physiologic immune functions that vary both by lineage and by stage of differentiation, the classification of lymphomas arising from these normal lymphoid populations is complex. Recent genomic data have contributed additional complexity. Areas covered: Lymphoma classification follows the World Health Organization (WHO) system, which reflects international consensus and is based on pathological, genetic, and clinical factors. A 2016 revision to the WHO classification of lymphoid neoplasms recently was reported. The present review focuses on B-cell non-Hodgkin lymphomas, the most common group of lymphomas, and summarizes recent changes most relevant to hematologists and other clinicians who care for lymphoma patients. Expert commentary: Lymphoma classification is a continually evolving field that needs to be responsive to new clinical, pathological, and molecular understanding of lymphoid neoplasia. Among the entities covered in this review, the 2016 revision of the WHO classification particularly impact the subclassification and genetic stratification of diffuse large B-cell lymphoma and high-grade B-cell lymphomas, and reflect evolving criteria and nomenclature for indolent B-cell lymphomas and lymphoproliferative disorders.

Lymphoma classification update: T-cell lymphomas, Hodgkin lymphomas, and histiocytic/dendritic cell neoplasms.

INTRODUCTION: Lymphomas are classified based on the normal counterpart, or cell of origin, from which they arise. Because lymphocytes have physiologic immune functions that vary both by lineage and by stage of differentiation, the classification of lymphomas arising from these normal lymphoid populations is complex. Recent genomic data have contributed additional depth to this complexity. Areas covered: Lymphoma classification follows the World Health Organization (WHO) system, which reflects international consensus and is based on pathological, genetic, and clinical factors. The present review focuses on the classification of T-cell lymphomas, Hodgkin lymphomas, and histiocytic and dendritic cell neoplasms, summarizing changes reflected in the 2016 revision to the WHO classification. These changes are critical to hematologists and other clinicians who care for patients with these disorders. Expert commentary: Lymphoma classification is a continually evolving field that needs to be responsive to new clinical, pathological, and molecular understanding of lymphoid neoplasia. Among the entities covered in this review, the 2016 revisions in the WHO classification particularly impact T-cell lymphomas, including a new umbrella category of T-follicular helper cell-derived lymphomas and evolving recognition of indolent T-cell lymphomas and lymphoproliferative disorders.

Automatic lymphoma classification with sentence subgraph mining from pathology reports.

OBJECTIVE: Pathology reports are rich in narrative statements that encode a complex web of relations among medical concepts. These relations are routinely used by doctors to reason on diagnoses, but often require hand-crafted rules or supervised learning to extract into prespecified forms for computational disease modeling. We aim to automatically capture relations from narrative text without supervision. METHODS: We design a novel framework that translates sentences into graph representations, automatically mines sentence subgraphs, reduces redundancy in mined subgraphs, and automatically generates subgraph features for subsequent classification tasks. To ensure meaningful interpretations over the sentence graphs, we use the Unified Medical Language System Metathesaurus to map token subsequences to concepts, and in turn sentence graph nodes. We test our system with multiple lymphoma classification tasks that together mimic the differential diagnosis by a pathologist. To this end, we prevent our classifiers from looking at explicit mentions or synonyms of lymphomas in the text. RESULTS AND CONCLUSIONS: We compare our system with three baseline classifiers using standard n-grams, full MetaMap concepts, and filtered MetaMap concepts. Our system achieves high F-measures on multiple binary classifications of lymphoma (Burkitt lymphoma, 0.8; diffuse large B-cell lymphoma, 0.909; follicular lymphoma, 0.84; Hodgkin lymphoma, 0.912). Significance tests show that our system outperforms all three baselines. Moreover, feature analysis identifies subgraph features that contribute to improved performance; these features agree with the state-of-the-art knowledge about lymphoma classification. We also highlight how these unsupervised relation features may provide meaningful insights into lymphoma classification.

Models for mature T-cell lymphomas--a critical appraisal of experimental systems and their contribution to current T-cell tumorigenic concepts.

Mature T-cell lymphomas/leukemias (MTCL) have been understudied lymphoid neoplasms that currently receive growing attention. Our historically rudimentary molecular understanding and dissatisfactory interventional success in this complex and for the most part poor-prognostic group of tumors is only slightly improving. A major limiting aspect in further progress in these rare neoplasms is the lack of suitable model systems that would substantially facilitate pathogenic studies and pre-clinical drug evaluations. Such representations of MTCL have thus far not been systematically appraised. We therefore provide an overview on existing models and point out their particular advantages and limitations in the context of the specific scientific questions. After addressing issues of species-specific differences and classifications, we summarize data on MTCL cell lines of human as well as murine origin, on murine strain predispositions to MTCL, on available models of genetically engineered mice, and on transplant systems. From an in-silico meta-analysis of available primary data of gene expression profiles on human MTCL we cross-reference genes reported to transform T-cells in mice and reflect on their general vs entity-restricted relevance and on target-promoter influences. Overall, we identify the urgent need for new models of higher fidelity to human MTCL with respect to their increasingly recognized diversity and to predictions of drug response.