FCM marker importance for MRD assessment in T-cell acute lymphoblastic leukemia: An AIEOP-BFM-ALL-FLOW study group report.

T-lineage acute lymphoblastic leukemia (T-ALL) accounts for about 15% of pediatric and about 25% of adult ALL cases. Minimal/measurable residual disease (MRD) assessed by flow cytometry (FCM) is an important prognostic indicator for risk stratification. In order to assess the MRD a limited number of antibodies directed against the most discriminative antigens must be selected. We propose a pipeline for evaluating the influence of different markers for cell population classification in FCM data. We use linear support vector machine, fitted to each sample individually to avoid issues with patient and laboratory variations. The best separating hyperplane direction as well as the influence of omitting specific markers is considered. Ninety-one bone marrow samples of 43 pediatric T-ALL patients from five reference laboratories were analyzed by FCM regarding marker importance for blast cell identification using combinations of eight different markers. For all laboratories, CD48 and CD99 were among the top three markers with strongest contribution to the optimal hyperplane, measured by median separating hyperplane coefficient size for all samples per center and time point (diagnosis, Day 15, Day 33). Based on the available limited set tested (CD3, CD4, CD5, CD7, CD8, CD45, CD48, CD99), our findings prove that CD48 and CD99 are useful markers for MRD monitoring in T-ALL. The proposed pipeline can be applied for evaluation of other marker combinations in the future.

Incarceration history is associated with HIV infection among community-recruited people who inject drugs in Europe: A propensity-score matched analysis of cross-sectional studies.

AIMS: We measured the association between a history of incarceration and HIV positivity among people who inject drugs (PWID) across Europe. DESIGN, SETTING AND PARTICIPANTS: This was a cross-sectional, multi-site, multi-year propensity-score matched analysis conducted in Europe. Participants comprised community-recruited PWID who reported a recent injection (within the last 12 months). MEASUREMENTS: Data on incarceration history, demographics, substance use, sexual behavior and harm reduction service use originated from cross-sectional studies among PWID in Europe. Our primary outcome was HIV status. Generalized linear mixed models and propensity-score matching were used to compare HIV status between ever- and never-incarcerated PWID. FINDINGS: Among 43 807 PWID from 82 studies surveyed (in 22 sites and 13 countries), 58.7% reported having ever been in prison and 7.16% (n = 3099) tested HIV-positive. Incarceration was associated with 30% higher odds of HIV infection [adjusted odds ratio (aOR) = 1.32, 95% confidence interval (CI) = 1.09-1.59]; the association between a history of incarceration and HIV infection was strongest among PWID, with the lowest estimated propensity-score for having a history of incarceration (aOR = 1.78, 95% CI = 1.47-2.16). Additionally, mainly injecting cocaine and/or opioids (aOR = 2.16, 95% CI = 1.33-3.53), increased duration of injecting drugs (per 8 years aOR = 1.31, 95% CI = 1.16-1.48), ever sharing needles/syringes (aOR = 1.91, 95% CI = 1.59-2.28) and increased income inequality among the general population (measured by the Gini index, aOR = 1.34, 95% CI = 1.18-1.51) were associated with a higher odds of HIV infection. Older age (per 8 years aOR = 0.84, 95% CI = 0.76-0.94), male sex (aOR = 0.77, 95% CI = 0.65-0.91) and reporting pharmacies as the main source of clean syringes (aOR = 0.72, 95% CI = 0.59-0.88) were associated with lower odds of HIV positivity. CONCLUSIONS: A history of incarceration appears to be independently associated with HIV infection among people who inject drugs (PWID) in Europe, with a stronger effect among PWID with lower probability of incarceration.

Automated identification of cell populations in flow cytometry data with transformers.

Acute Lymphoblastic Leukemia (ALL) is the most frequent hematologic malignancy in children and adolescents. A strong prognostic factor in ALL is given by the Minimal Residual Disease (MRD), which is a measure for the number of leukemic cells persistent in a patient. Manual MRD assessment from Multiparameter Flow Cytometry (FCM) data after treatment is time-consuming and subjective. In this work, we present an automated method to compute the MRD value directly from FCM data. We present a novel neural network approach based on the transformer architecture that learns to directly identify blast cells in a sample. We train our method in a supervised manner and evaluate it on publicly available ALL FCM data from three different clinical centers. Our method reaches a median F1 score of ≈0.94 when evaluated on 519 B-ALL samples and shows better results than existing methods on 4 different datasets.

UMAP Based Anomaly Detection for Minimal Residual Disease Quantification within Acute Myeloid Leukemia.

Leukemia is the most frequent malignancy in children and adolescents, with acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML) as the most common subtypes. Minimal residual disease (MRD) measured by flow cytometry (FCM) has proven to be a strong prognostic factor in ALL as well as in AML. Machine learning techniques have been emerging in the field of automated MRD quantification with the objective of superseding subjective and time-consuming manual analysis of FCM-MRD data. In contrast to ALL, where supervised multi-class classification methods have been successfully deployed for MRD detection, AML poses new challenges: AML is rarer (with fewer available training data) than ALL and much more heterogeneous in its immunophenotypic appearance, where one-class classification (anomaly detection) methods seem more suitable. In this work, a new semi-supervised approach based on the UMAP algorithm for MRD detection utilizing only labels of blast free FCM samples is presented. The method is tested on a newly gathered set of AML FCM samples and results are compared to state-of-the-art methods. We reach a median F1-score of 0.794, while providing a transparent classification pipeline with explainable results that facilitates inter-disciplinary work between medical and technical experts. This work shows that despite several issues yet to overcome, the merits of automated MRD quantification can be fully exploited also in AML.