Beyond the In-Practice CBC: The Research CBC Parameters-Driven Machine Learning Predictive Modeling for Early Differentiation among Leukemias

A targeted and timely treatment can be a beneficial tool for patients with hematological emergencies (particularly acute leukemias). The key challenges in the early diagnosis of leukemias and related hematological disorders are their symptom-sharing nature and prolonged turnaround time as well as the expertise needed in reporting confirmatory tests. The present study made use of the potential morphological and immature fraction-related parameters (research items or cell population data) generated during complete blood cell count (CBC), through artificial intelligence (AI)/machine learning (ML) predictive modeling for early (at the pre-microscopic level) differentiation of various types of leukemias: acute from chronic as well as myeloid from lymphoid. The routine CBC parameters along with research CBC items from a hematology analyzer in the diagnosis of 1577 study subjects with hematological neoplasms were collected. The statistical and data visualization tools, including heat-map and principal component analysis (PCA,) helped in the evaluation of the predictive capacity of research CBC items. Next, research CBC parameter-driven artificial neural network (ANN) predictive modeling was developed to use the hidden trend (disease’s signature) by increasing the auguring accuracy of these potential morphometric parameters in differentiation of leukemias. The classical statistics for routine and research CBC parameters showed that as a whole, all study items are significantly deviated among various types of leukemias (study groups). The CPD parameter-driven heat-map gave clustering (separation) of myeloid from lymphoid leukemias, followed by the segregation (nodding) of the acute from the chronic class of that particular lineage. Furthermore, acute promyelocytic leukemia (APML) was also well individuated from other types of acute myeloid leukemia (AML). The PCA plot guided by research CBC items at notable variance vindicated the aforementioned findings of the CPD-driven heat-map. Through training of ANN predictive modeling, the CPD parameters successfully differentiate the chronic myeloid leukemia (CML), AML, APML, acute lymphoid leukemia (ALL), chronic lymphoid leukemia (CLL), and other related hematological neoplasms with AUC values of 0.937, 0.905, 0.805, 0.829, 0.870, and 0.789, respectively, at an agreeably significant (10.6%) false prediction rate. Overall practical results of using our ANN model were found quite satisfactory with values of 83.1% and 89.4.7% for training and testing datasets, respectively. We proposed that research CBC parameters could potentially be used for early differentiation of leukemias in the hematology–oncology unit. The CPD-driven ANN modeling is a novel practice that substantially strengthens the predictive potential of CPD items, allowing the clinicians to be confident about the typical trend of the “disease fingerprint” shown by these automated potential morphometric items.

Acute Lymphoblastic Leukemia Presenting as Pituitary Apoplexy: A Case Report and Review of the Literature

Thrombocytopenia as a precipitating factor for pituitary apoplexy (PA) is very rare event. There are only five reported cases of PA secondary to thrombocytopenia caused by underlying haematological malignancy. Herein, we report a case of 60-year-old male presenting with acute-onset headache, bilateral vision loss, and ptosis. Computed tomography and magnetic resonance imaging revealed findings indicative of pituitary adenoma with apoplexy. He was noted to have thrombocytopenia, and bone marrow evaluation revealed precursor B-lineage CALLA-positive acute lymphoblastic leukemia. Accordingly, he was started on dexamethasone and vincristine but succumbed to Acinetobacter baumanii-related hospital-acquired pneumonia two weeks after initiation of chemotherapy. We performed a literature search and found five cases of pituitary apoplexy secondary to haematological malignancy-related thrombocytopenia. The usual age of presentation was in the 6th to 7th decade, and there was slight male preponderance. The underlying pituitary adenoma was either nonfunctioning or a prolactinoma, and in majority, the apoplexy event occurred after the diagnosis of haematological malignancy. The platelet counts at the time of PA were less than 30 × 109/L in all, and the malignancy subtypes were acute or chronic myeloid leukemia and chronic lymphoid leukemia. The current case highlights the importance of careful evaluation for the cause of thrombocytopenia in a case of PA.

Determining Acute Leukemia Lineage Using Mie Map Red Blood Cell

The determination of myeloid and lymphoid lineage is essential for the diagnosis and therapy of acute leukemia. Immunophenotyping is the gold standard to determine the lineage of acute leukemia, but it is still constrained and relatively expensive. Mie Map RBC in the ADVIA 2120i is a parameter that can give additional information about myeloid and lymphoid lineage but has never been studied before. It is expected that Mie Map RBC can be used to differentiate the lineage of acute myeloid and lymphoid leukemia if immunophenotyping is not present. This study aimed to analyze the diagnostic value of Mie Map RBC with ADVIA 2120i towards immunophenotyping in determining myeloid and lymphoid lineage in acute leukemia. Child and adult patients diagnosed with acute leukemia (n=30) that had peripheral blood smear and bone marrow aspiration with blasts > 20% were examined using ADVIA 2120i. The Mie Map RBC lineage results were compared to the lineage of immunophenotyping. The sensitivity and specificity of the Mie Map RBC myeloid series are respectively 60.00%, 93.33%. The sensitivity and specificity of the Mie Map RBC lymphoid series are respectively 93.33% and 60.00%. The diagnostic accuracy value of Mie Map RBC is 76.67%. The determination of acute leukemia myeloid series lineage has high specificity. If there is no population outside the matrix of Mie Map RBC, it highly suggests myeloid series. On the other hand, the determination of acute leukemia lymphoid series lineage has a relatively low specificity meaning that the population outside the matrix of Mie Map RBC does not always suggest a lymphoid lineage

Quinacrine-CASIN combination overcomes chemoresistance in human acute lymphoid leukemia

Chemoresistance posts a major hurdle for treatment of acute leukemia. There is increasing evidence that prolonged and intensive chemotherapy often fails to eradicate leukemic stem cells, which are protected by the bone marrow niche and can induce relapse. Thus, new therapeutic approaches to overcome chemoresistance are urgently needed. By conducting an ex vivo small molecule screen, here we have identified Quinacrine (QC) as a sensitizer for Cytarabine (AraC) in treating acute lymphoblastic leukemia (ALL). We show that QC enhances AraC-mediated killing of ALL cells, and subsequently abrogates AraC resistance both in vitro and in an ALL-xenograft model. However, while combo AraC+QC treatment prolongs the survival of primary transplanted recipients, the combination exhibits limited efficacy in secondary transplanted recipients, consistent with the survival of niche-protected leukemia stem cells. Introduction of Cdc42 Activity Specific Inhibitor, CASIN, enhances the eradication of ALL leukemia stem cells by AraC+QC and prolongs the survival of both primary and secondary transplanted recipients without affecting normal long-term human hematopoiesis. Together, our findings identify a small-molecule regimen that sensitizes AraC-mediated leukemia eradication and provide a potential therapeutic approach for better ALL treatment.

Clofarabine-fludarabine-busulfan in HCT for pediatric leukemia: an effective, low toxicity, TBI-free conditioning regimen

We prospectively studied CloFluBu-conditioning in allogeneic Hematopoietic Cell Therapy (HCT) for lymphoid- and myeloid malignancies, and hypothesized that CloFluBu provides a less toxic alternative to conventional conditioning regimens, with adequate anti-leukemic activity. All patients receiving their first HCT, from 2011-2019, were included and received CloFluBu. Primary endpoint was Event Free Survival (EFS). Secondary endpoints were Overall Survival (OS), Graft-versus-Host-Disease (GvHD)-Relapse-Free Survival (GRFS), Treatment Related Mortality (TRM), Cumulative Incidence of Relapse (CIR), acute and chronic GvHD, and veno-occlusive disease (VOD). Cox Proportional Hazard- and Fine and Gray competing-risk models were used for data analysis. 155 Children were included; 60 acute lymphoid leukemia (ALL), 69 acute myeloid leukemia (AML), and 26 other malignancies (mostly MDS-EB). Median age was 9.7 (0.5-18.6) years. Estimated 2-yr EFS was 72.0% ± 6.0 in ALL, and 62.4% ± 6.0 in AML patients. TRM in the whole cohort was 11.0% ± 2.6, incidence of aGvHD III-IV at 6 months was 12.3% ± 2.7, extensive chronic GvHD at 2-yr was 6.4% ± 2.1. Minimal residual disease-positivity prior to HCT was associated with higher CIR, both in ALL and AML. CloFluBu showed limited toxicity and encouraging EFS. CloFluBu is a potentially less toxic alternative to conventional conditioning regimens. Randomized prospective studies are needed.

Transformation of the acute myeloid leukemia to acute B cell lymphoblastic leukemia with CAR-T cell therapy: a case report and review of the literature

Lineage conversion is used to describe acute myeloid or lymphoid leukemia becomes the opposite at relapse.We report a 4-year-old child with acute myeloid leukemia who was converted to acute lymphoblastic leukemia at relapse and received chimeric antigen receptor T (cell) therapy for reference.

Transformation of the acute myeloid leukemia to acute B cell lymphoblastic leukemia with CAR-T cell therapy: a case report and review of the literature

Lineage conversion is used to describe acute myeloid or lymphoid leukemia becomes the opposite at relapse.We report a 4-year-old child with acute myeloid leukemia who was converted to acute lymphoblastic leukemia at relapse and received chimeric antigen receptor T (cell) therapy for reference.

Palbociclib and Ponatinib Suppress Acute Myeloid Leukemia in Patient-Derived Xenograft

Aims: Palbociclib, a breast cancer approved CDK4/6 inhibitor, and ponatinib, a BCR/ABL1 inhibitor with a multi-kinase activity approved for chronic myeloid and acute lymphoid leukemia, were previously shown to be effective in vitro against acute myeloid leukemia (AML). Here, we aimed to test this effect in a patient-derived xenograft model. Methods: Two newly diagnosed AMLs (AML #1: myelomonocytic AML, intermediate cytogenetic risk; AML #2: AML with myelodysplasia-related changes, poor cytogenetic risk) were xenotransplanted into NOD SCID gamma mice. Treatment was initiated at detection of approximately 5-20% hCD45+ cells in mouse peripheral blood (PB). Palbociclib, ponatinib, vehicle, and venetoclax as a comparative treatment, were administered orally for 3 weeks, 5 days per week. Chemotherapy (cytarabine+doxorubicine, AraC/Dox) 5+3 regimen served as a positive control. Azacitidine served as another comparative drug and was administered subcutaneously, five days per week in 3 cycles - 1 week on, 1 week off. Results: Significant reduction of disease burden and prolongation of overall survival (OS) were seen with palbociclib and the reference treatment venetoclax in both AMLs, and with chemotherapy in AML#1 (Fig. 1). Ponatinib prolonged OS in AML#1 but failed to provide reduction of disease burden in PB. Interestingly, azacitidine induced the longest remission (<1% hCD45+ cells in PB), for almost 10 weeks, but only in 2/4 mice for AML#2. Treatment toxicity manifested by weight decrease was only seen with chemotherapy (AML#1: 24% weight loss, p = 0.0001; AML#2: 19% loss, p = 0.04), and was also accompanied with early mouse mortality in 3/4 mice for AML#2. None of the tested treatments lead to complete AML eradication and a gradual relapse was seen in PB. The AML infiltration was higher in bone marrow than in spleen at final analysis at relapse (AML#1, 83 vs 73% of hCD45+ cells, mean, p = 0.02; AML#2, 95 vs 65%, p = 0.0001). No changes in AML phenotype were observed between treated and vehicle mice in case of AML#1, except for azacitidine which decreased monocyte (SSCdim, CD45high; 94 vs 96%, mean, p = 0.03), CD34+ (2 vs 5%, p = 0.01) and primitive CD34+CD38- cell (0.1 vs 0.3%, p = 0.005) percentages. For AML#2, blast (SSClow, CD45dim) percentage compared to vehicle (70%) was decreased by chemotherapy (24%, p = 0.01) and increased by venetoclax (80%, p = 0.03) and azacitidine (87%, p = 0.03); monocytes (6% for vehicle) were decreased by chemotherapy (1%, p = 0.004), venetoclax (3%, p = 0.01), and azacitidine (0%, p = 0.008); CD34+ cells were increased by venetoclax (59 vs 39%, p = 0.02). Summary: Palbociclib, and partially ponatinib, demonstrated AML suppression in vivo. This encourages further investigation of their efficacy in different AML subtypes and in combination with other drugs. Funding: Supported by MUNI/A/1595/2020. Figure 1 Figure 1. Disclosures Mayer: AOP Orphan Pharmaceuticals: Research Funding.

Decreased IL-10 accelerates B-cell leukemia/lymphoma in a mouse model of pediatric lymphoid leukemia

Exposures to a wide repertoire of common childhood infections and strong inflammatory responses to those infections are associated with risk of pediatric B-cell acute lymphoblastic leukemia (B-ALL) in opposing directions. Neonatal inflammatory markers are also related to risk by unknown mechanism(s). Here, we demonstrate that IL-10 deficiency, which is associated with childhood B-ALL, indirectly impairs B lymphopoiesis and increases B-cell DNA damage in association with a module of 6 proinflammatory/myeloid-associated cytokines (IL-1α, IL-6, IL-12p40, IL-13, MIP-1β/CCL4, and G-CSF). Importantly, antibiotics attenuated inflammation and B-cell defects in preleukemic Cdkn2a-/-Il10-/- mice. In an ETV6-RUNX1+ (E6R1+) Cdkn2a-/- mouse model of B-ALL, decreased levels of IL-10 accelerated B cell neoplasms in a dose dependent manner, and altered the mutational profile of these neoplasms. Our results illuminate a mechanism through which a low level of IL-10 can create risk of leukemic transformation and support developing evidence that microbial dysbiosis contributes to pediatric B-ALL.