Mimicking clinical trials with synthetic acute myeloid leukemia patients using generative artificial intelligence.

Clinical research relies on high-quality patient data, however, obtaining big data sets is costly and access to existing data is often hindered by privacy and regulatory concerns. Synthetic data generation holds the promise of effectively bypassing these boundaries allowing for simplified data accessibility and the prospect of synthetic control cohorts. We employed two different methodologies of generative artificial intelligence - CTAB-GAN+ and normalizing flows (NFlow) - to synthesize patient data derived from 1606 patients with acute myeloid leukemia, a heterogeneous hematological malignancy, that were treated within four multicenter clinical trials. Both generative models accurately captured distributions of demographic, laboratory, molecular and cytogenetic variables, as well as patient outcomes yielding high performance scores regarding fidelity and usability of both synthetic cohorts (n = 1606 each). Survival analysis demonstrated close resemblance of survival curves between original and synthetic cohorts. Inter-variable relationships were preserved in univariable outcome analysis enabling explorative analysis in our synthetic data. Additionally, training sample privacy is safeguarded mitigating possible patient re-identification, which we quantified using Hamming distances. We provide not only a proof-of-concept for synthetic data generation in multimodal clinical data for rare diseases, but also full public access to synthetic data sets to foster further research.

Prognostic impact of CEBPA mutational subgroups in adult AML.

Despite recent refinements in the diagnostic and prognostic assessment of CEBPA mutations in AML, several questions remain open, i.e. implications of different types of basic region leucin zipper (bZIP) mutations, the role of co-mutations and the allelic state. Using pooled primary data analysis on 1010 CEBPA-mutant adult AML patients, a comparison was performed taking into account the type of mutation (bZIP: either typical in-frame insertion/deletion (InDel) mutations (bZIPInDel), frameshift InDel or nonsense mutations inducing translational stop (bZIPSTOP) or single base-pair missense alterations (bZIPms), and transcription activation domain (TAD) mutations) and the allelic state (single (smCEBPA) vs. double mutant (dmCEBPA)). Only bZIPInDel patients had significantly higher rates of complete remission and longer relapse free and overall survival (OS) compared with all other CEBPA-mutant subgroups. Moreover, co-mutations in bZIPInDel patients (e.g. GATA2, FLT3, WT1 as well as ELN2022 adverse risk aberrations) had no independent impact on OS, whereas in non-bZIPInDel patients, grouping according to ELN2022 recommendations added significant prognostic information. In conclusion, these results demonstrate bZIPInDel mutations to be the major independent determinant of outcome in CEBPA-mutant AML, thereby refining current classifications according to WHO (including all dmCEBPA and smCEBPA bZIP) as well as ELN2022 and ICC recommendations (including CEBPA bZIPms).

VEXAS syndrome: complete molecular remission after hypomethylating therapy.

The VEXAS syndrome, a genetically defined autoimmune disease, associated with various hematological neoplasms has been attracting growing attention since its initial description in 2020. While various therapeutic strategies have been explored in case studies, the optimal treatment strategy is still under investigation and allogeneic cell transplantation is considered the only curative treatment. Here, we describe 2 patients who achieved complete molecular remission of the underlying UBA1 mutant clone outside the context of allogeneic HCT. Both patients received treatment with the hypomethylating agent azacitidine, and deep molecular remission triggered treatment de-escalation and even cessation with sustained molecular remission in one of them. Prospective studies are necessary to clarify which VEXAS patients will benefit most from hypomethylating therapy and to understand the variability in the response to different treatment strategies.

Mutated IKZF1 is an independent marker of adverse risk in acute myeloid leukemia.

Genetic lesions of IKZF1 are frequent events and well-established markers of adverse risk in acute lymphoblastic leukemia. However, their function in the pathophysiology and impact on patient outcome in acute myeloid leukemia (AML) remains elusive. In a multicenter cohort of 1606 newly diagnosed and intensively treated adult AML patients, we found IKZF1 alterations in 45 cases with a mutational hotspot at N159S. AML with mutated IKZF1 was associated with alterations in RUNX1, GATA2, KRAS, KIT, SF3B1, and ETV6, while alterations of NPM1, TET2, FLT3-ITD, and normal karyotypes were less frequent. The clinical phenotype of IKZF1-mutated AML was dominated by anemia and thrombocytopenia. In both univariable and multivariable analyses adjusting for age, de novo and secondary AML, and ELN2022 risk categories, we found mutated IKZF1 to be an independent marker of adverse risk regarding complete remission rate, event-free, relapse-free, and overall survival. The deleterious effects of mutated IKZF1 also prevailed in patients who underwent allogeneic hematopoietic stem cell transplantation (n = 519) in both univariable and multivariable models. These dismal outcomes are only partially explained by the hotspot mutation N159S. Our findings suggest a role for IKZF1 mutation status in AML risk modeling.

Measurable residual disease monitoring in patients with acute myeloid leukemia treated with lower-intensity therapy: Roadmap from an ELN-DAVID expert panel.

With the availability of effective targeted agents, significant changes have occurred in the management of patients with acute myeloid leukemia (AML) over the past several years, particularly for those considered unfit for intensive chemotherapy. While testing for measurable residual disease (MRD) is now routinely performed in patients treated with intensive chemotherapy to refine prognosis and, possibly, inform treatment decision-making, its value in the context of lower-intensity regimens is unclear. As such regimens have gained in popularity and can be associated with higher response rates, the need to better define the role of MRD assessment and the appropriate time points and assays used for this purpose has increased. This report outlines a roadmap for MRD testing in patients with AML treated with lower-intensity regimens. Experts from the European LeukemiaNet (ELN)-DAVID AML MRD working group reviewed all available data to propose a framework for MRD testing in future trials and clinical practice. A Delphi poll served to optimize consensus. Establishment of uniform standards for MRD assessments in lower-intensity regimens used in treating patients with AML is clinically relevant and important for optimizing testing and, ultimately, improving treatment outcomes of these patients.

Activation of distinct inflammatory pathways in subgroups of LR-MDS.

Aberrant innate immune signaling has been identified as a potential key driver of the complex pathophysiology of myelodysplastic neoplasms (MDS). This study of a large, clinically and genetically well-characterized cohort of treatment-naïve MDS patients confirms intrinsic activation of inflammatory pathways in general mediated by caspase-1, interleukin (IL)-1ß and IL-18 in low-risk (LR)-MDS bone marrow and reveals a previously unrecognized heterogeneity of inflammation between genetically defined LR-MDS subgroups. Principal component analysis resolved two LR-MDS phenotypes with low (cluster 1) and high (cluster 2) levels of IL1B gene expression, respectively. Cluster 1 contained 14/17 SF3B1-mutated cases, while cluster 2 contained 8/8 del(5q) cases. Targeted gene expression analysis of sorted cell populations showed that the majority of the inflammasome-related genes, including IL1B, were primarily expressed in the monocyte compartment, consistent with a dominant role in determining the inflammatory bone marrow environment. However, the highest levels of IL18 expression were found in hematopoietic stem and progenitor cells (HSPCs). The colony forming activity of healthy donor HSPCs exposed to monocytes from LR-MDS was increased by the IL-1ß-neutralizing antibody canakinumab. This work reveals distinct inflammatory profiles in LR-MDS that are of likely relevance to the personalization of emerging anti-inflammatory therapies.

Unsupervised meta-clustering identifies risk clusters in acute myeloid leukemia based on clinical and genetic profiles.

BACKGROUND: Increasingly large and complex biomedical data sets challenge conventional hypothesis-driven analytical approaches, however, data-driven unsupervised learning can detect inherent patterns in such data sets. METHODS: While unsupervised analysis in the medical literature commonly only utilizes a single clustering algorithm for a given data set, we developed a large-scale model with 605 different combinations of target dimensionalities as well as transformation and clustering algorithms and subsequent meta-clustering of individual results. With this model, we investigated a large cohort of 1383 patients from 59 centers in Germany with newly diagnosed acute myeloid leukemia for whom 212 clinical, laboratory, cytogenetic and molecular genetic parameters were available. RESULTS: Unsupervised learning identifies four distinct patient clusters, and statistical analysis shows significant differences in rate of complete remissions, event-free, relapse-free and overall survival between the four clusters. In comparison to the standard-of-care hypothesis-driven European Leukemia Net (ELN2017) risk stratification model, we find all three ELN2017 risk categories being represented in all four clusters in varying proportions indicating unappreciated complexity of AML biology in current established risk stratification models. Further, by using assigned clusters as labels we subsequently train a supervised model to validate cluster assignments on a large external multicenter cohort of 664 intensively treated AML patients. CONCLUSIONS: Dynamic data-driven models are likely more suitable for risk stratification in the context of increasingly complex medical data than rigid hypothesis-driven models to allow for a more personalized treatment allocation and gain novel insights into disease biology.

There are various ways in which clinicians can predict the risk of disease progression in patients with leukemia, helping them to treat the patients accordingly. However, these approaches are usually designed by human experts and might not fully capture the complexity of a patient's disease. Here, with a large cohort of patients with acute myeloid leukemia, we design an unsupervised machine learning model ­ a type of computer model that learns from patterns in data without human input­to separate these patients into subgroups according to risk. We identify four distinct groups which differ with regards to patient genetics, laboratory values, and clinical characteristics. These groups have differences in response to treatment and patient survival, and we validate our findings in another dataset. Our approach might help clinicians to better predict outcomes in patients with leukemia and make decisions on treatment.

UBTF tandem duplications are rare but recurrent alterations in adult AML and associated with younger age, myelodysplasia, and inferior outcome.

Tandem-duplication mutations of the UBTF gene (UBTF-TDs) coding for the upstream binding transcription factor have recently been described in pediatric patients with acute myeloid leukemia (AML) and were found to be associated with particular genetics (trisomy 8 (+8), FLT3-internal tandem duplications (FLT3-ITD), WT1-mutations) and inferior outcome. Due to limited knowledge on UBTF-TDs in adult AML, we screened 4247 newly diagnosed adult AML and higher-risk myelodysplastic syndrome (MDS) patients using high-resolution fragment analysis. UBTF-TDs were overall rare (n = 52/4247; 1.2%), but significantly enriched in younger patients (median age 41 years) and associated with MDS-related morphology as well as significantly lower hemoglobin and platelet levels. Patients with UBTF-TDs had significantly higher rates of +8 (34% vs. 9%), WT1 (52% vs. 7%) and FLT3-ITD (50% vs. 20.8%) co-mutations, whereas UBTF-TDs were mutually exclusive with several class-defining lesions such as mutant NPM1, in-frame CEBPAbZIP mutations as well as t(8;21). Based on the high-variant allele frequency found and the fact that all relapsed patients analyzed (n = 5) retained the UBTF-TD mutation, UBTF-TDs represent early clonal events and are stable over the disease course. In univariate analysis, UBTF-TDs did not represent a significant factor for overall or relapse-free survival in the entire cohort. However, in patients under 50 years of age, who represent the majority of UBTF-mutant patients, UBTF-TDs were an independent prognostic factor for inferior event-free (EFS), relapse-free (RFS) and overall survival (OS), which was confirmed by multivariable analyses including established risk factors such as age and ELN2022 genetic risk groups (EFS [HR: 2.20; 95% CI 1.52-3.17, p < 0.001], RFS [HR: 1.59; 95% CI 1.02-2.46, p = 0.039] and OS [HR: 1.64; 95% CI 1.08-2.49, p = 0.020]). In summary, UBTF-TDs appear to represent a novel class-defining lesion not only in pediatric AML but also younger adults and are associated with myelodysplasia and inferior outcome in these patients.

Assessment of acute myeloid leukemia molecular measurable residual disease testing in an interlaboratory study.

The European LeukaemiaNet (ELN) measurable residual disease (MRD) working group has published consensus guidelines to standardize molecular genetic MRD testing of the t(8;21)(q22;q22.1) RUNX1::RUNX1T1, inv(16)(p13.1q22) CBFB::MYH11, t(15;17)(q24.1;q21.2) PML::RARA, and NPM1 type A markers. A study featuring 29 international laboratories was performed to assess interlaboratory variation in testing and the subsequent interpretation of results, both crucial to patient safety. Most participants in this study were able to detect, accurately quantify, and correctly interpret MRD testing results, with a level of proficiency expected from a clinical trial or standard-of-care setting. However, a few testing and interpretive errors were identified that, in a patient setting, would have led to misclassification of patient outcomes and inappropriate treatment pathways being followed. Of note, a high proportion of participants reported false-positive results in the NPM1 marker-negative sample. False-positive results may have clinical consequences, committing patients to unneeded additional chemotherapy and/or transplant with the attendant risk of morbidity and mortality, which therefore highlights the need for ongoing external quality assessment/proficiency testing in this area. Most errors identified in the study were related to the interpretation of results. It was noted that the ELN guidance lacks clarity for certain clinical scenarios and highlights the requirement for urgent revision of the guidelines to elucidate these issues and related educational efforts around the revisions to ensure effective dissemination.

Allogeneic Hematopoietic Cell Transplantation vs Standard Consolidation Chemotherapy in Patients With Intermediate-Risk Acute Myeloid Leukemia: A Randomized Clinical Trial.

Importance: The ideal postremission strategy in intermediate-risk acute myeloid leukemia (AML) in first complete remission (CR) has been a matter of debate. Objective: To explore the optimal therapy for patients with intermediate-risk AML after first complete remission. Design, Settings, and Participants: This investigator-initiated, open-label, 2-armed, phase 3 randomized clinical trial assessed patients at 16 hospitals in Germany from February 2, 2011, until July 1, 2018. Key eligibility criteria included cytogenetically defined intermediate-risk AML according to Medical Research Council classification, first CR or CR with incomplete blood cell count recovery after conventional induction therapy, age of 18 to 60 years, and availability of a human leukocyte antigen (HLA)-matched sibling or unrelated donor. A detailed statistical analysis plan was written and finalized on July 7, 2020. Data were exported for analysis on April 13, 2021. Interventions: Patients were randomized 1:1 to receive allogeneic hematopoietic cell transplantation (HCT) or high-dose cytarabine for consolidation and salvage HCT only in case of relapse. Strata for randomization included age (18-40 vs 41-60 years), NPM1 and CEBPA variation status, and donor type (unrelated vs related). Main Outcomes and Measures: End points included overall-survival as the primary outcome and disease-free survival, cumulative incidence of relapse, treatment-related mortality, and quality of life measured according to the Medical Outcomes Study 36-Item Short-Form Health Survey as secondary outcomes. Results: A total of 143 patients (mean [SD] age, 48.2 [9.8] years; 81 [57%] male) with AML who fulfilled the eligibility criteria were randomized. In the intention-to-treat analysis, the probability of survival at 2 years was 74% (95% CI, 62%-83%) after primary allogeneic HCT and 84% (95% CI, 73%-92%) after consolidation chemotherapy (P = .22). Disease-free survival after HCT at 2 years was 69% (95% CI, 57%-80%) compared with 40% (95% CI, 28%-53%) after consolidation chemotherapy (P = .001). Allogeneic HCT during the first CR was associated with a cumulative incidence of relapse at 2 years of 20% (95% CI, 13%-31%) compared with 58% (95% CI, 47%-71%; P < .001). Nonrelapse mortality at 2 years after primary allogeneic HCT was 9% (95% CI, 5%-19%) and 2% (95% CI, 0%-11%) after consolidation chemotherapy (P = .005). Similar outcomes were observed when analyses were confined to the 96 patients at intermediate risk according to the European Leukemia Network classification. Most importantly, all 41 patients relapsing after consolidation chemotherapy (36 hematologic, 4 molecular, and 1 extramedullary) proceeded to allogeneic HCT. No significant differences in health-related quality of life measures were observed between groups. Conclusions and Relevance: Primary allogeneic HCT during first CR was not associated with superior overall survival compared with consolidation chemotherapy in patients 60 years or younger with intermediate-risk AML during the first CR and an available donor. Trial Registration: ClinicalTrials.gov Identifier: NCT01246752.

Impact of trisomy 19 on outcome according to genetic makeup in patients with acute myeloid leukemia.

We retrospectively studied 97 acute myeloid leukemia patients with trisomy 19 (median age at diagnosis 57 years; range, 17- 83 years) treated between 2001 and 2019 within two multicenter study groups. Trisomy 19 occurred alone in ten (10.5%) patients, with additional abnormalities being present in non-complex karyotypes in eight (8%) patients and in complex karyotypes in 79 (82%) patients. Altogether, karyotypes characterized by trisomies only were present in 27 (28%) patients. Data on response and outcome of intensively treated patients were available for 92 cases. The median follow-up was 6.4 years (95% confidence interval [95% CI]: 2.9-9.0 years). The complete remission (CR) rate after induction therapy was 52% (48 patients); the early death rate was 10% (n=9). Notably, patients with trisomy 19 as the sole abnormality had a CR rate of 89%. Allogeneic hematopoietic stem cell transplantation (allo-HCT) was performed in 34 (35%) patients (CR, n=19; active disease, n=15). Five-year relapse-free and overall survival rates were 26% (95% CI: 16-43%) and 20% (95% CI: 13-31%), respectively. Overall survival rates were significantly higher in patients with trisomy 19 as the sole abnormality or within karyotypes characterized by trisomies only (P=0.05). An Andersen-Gill model including allo-HCT as a time-dependent covariable on overall survival revealed that trisomy 19 as the sole abnormality or within karyotypes characterized by trisomies only was a favorable factor (hazard ratio [HR]=0.47; P=0.021); higher age at diagnosis had an adverse impact (10 years difference; HR=1.29; P=0.002), whereas allo-HCT did not have a beneficial impact (odds ratio=1.45; P=0.21). In our cohort, patients with trisomy 19 as the sole abnormality or within karyotypes characterized by trisomies only had a high CR rate and better clinical outcome.

Large case-control study indicates no association of KIR genotype and risk of developing acute myeloid leukemia.

Immunogenetic association studies may give rise to new hypotheses on the immune surveillance of cancer. We hypothesized that certain combinations of killer immunoglobulin-like receptor (KIR) and HLA genotypes may enhance natural killer (NK) cell immunity against nascent acute myeloid leukemia (AML) and, thereby, lead to a skewed genotype distribution among patients. For this purpose, we analyzed KIR and HLA genotypes of 1767 German patients with AML and compared the results with that of the data of 51 890 German volunteers who had registered with German bone marrow donor file (DKMS). Patient samples were retrieved from the Collaborative Biobank and the biorepository of the Study Alliance Leukemia. All samples were genotyped with high-resolution amplicon-based next-generation sequencing. Because of the large number of controls, this study was very sensitive to detect the impact of KIR genotype. Knowledge on KIRs and their cognate HLA ligands allowed for testing of several hypotheses of NK cell-mediated endogenous leukemia surveillance. We did not find significant differences between the 2 cohorts in regard to the presence or absence of single KIR genes. When grouped based on telomeric or centromeric gene content, the major haplotypes A/A, A/B, and B/B were equally distributed among patients and control subjects. Using information on KIRs and their HLA ligands, we further tested receptor-ligand models and summation models without revealing markedly significant differences between patients and controls, albeit we observed a trend pointing at a minor protective effect of a low number of inhibitory KIR/KIR-ligand pairs. The results suggest that the KIR/KIR-ligand genotype has no effect on the susceptibility for the development of de novo AML.

Alterations of cohesin complex genes in acute myeloid leukemia: differential co-mutations, clinical presentation and impact on outcome.

Functional perturbations of the cohesin complex with subsequent changes in chromatin structure and replication are reported in a multitude of cancers including acute myeloid leukemia (AML). Mutations of its STAG2 subunit may predict unfavorable risk as recognized by the 2022 European Leukemia Net recommendations, but the underlying evidence is limited by small sample sizes and conflicting observations regarding clinical outcomes, as well as scarce information on other cohesion complex subunits. We retrospectively analyzed data from a multi-center cohort of 1615 intensively treated AML patients and identified distinct co-mutational patters for mutations of STAG2, which were associated with normal karyotypes (NK) and concomitant mutations in IDH2, RUNX1, BCOR, ASXL1, and SRSF2. Mutated RAD21 was associated with NK, mutated EZH2, KRAS, CBL, and NPM1. Patients harboring mutated STAG2 were older and presented with decreased white blood cell, bone marrow and peripheral blood blast counts. Overall, neither mutated STAG2, RAD21, SMC1A nor SMC3 displayed any significant, independent effect on clinical outcomes defined as complete remission, event-free, relapse-free or overall survival. However, we found almost complete mutual exclusivity of genetic alterations of individual cohesin subunits. This mutual exclusivity may be the basis for therapeutic strategies via synthetic lethality in cohesin mutated AML.

Impact of treatment intensity on infectious complications in patients with acute myeloid leukemia.

BACKGROUND: Infectious complications reflect a major challenge in the treatment of patients with acute myeloid leukemia (AML). Both induction chemotherapy and epigenetic treatment with hypomethylating agents (HMA) are associated with severe infections, while neutropenia represents a common risk factor. Here, 220 consecutive and newly diagnosed AML patients were analyzed with respect to infectious complications dependent on treatment intensity and antifungal prophylaxis applied to these patients. PATIENTS AND METHODS: We retrospectively analyzed 220 patients with newly diagnosed AML at a tertiary care hospital between August 2016 and December 2020. The median age of AML patients undergoing induction chemotherapy (n = 102) was 61 years (25-76 years). Patients receiving palliative AML treatment (n = 118) had a median age of 75 years (53-91 years). We assessed the occurrence of infectious complication including the classification of pulmonary invasive fungal disease (IFD) according to the EORTC/MSG criteria at diagnosis and until day 100 after initiation of AML treatment. Furthermore, admission to intensive care unit (ICU) and subsequent outcome was analyzed for both groups of AML patients, respectively. RESULTS: AML patients subsequently allocated to palliative AML treatment have a significantly higher risk of pneumonia at diagnosis compared to patients undergoing induction chemotherapy (37.3% vs. 13.7%, P < 0.001) including a higher probability of atypical pneumonia (22.0% vs. 10.8%, P = 0.026). Furthermore, urinary tract infections are more frequent in the palliative subgroup at the time of AML diagnosis (5.1% vs. 0%, P = 0.021). Surprisingly, the incidence of pulmonary IFD is significantly lower after initiation of palliative AML treatment compared to the occurrence after induction chemotherapy (8.4% vs. 33.3%, P < 0.001) despite only few patients of the palliative treatment group received Aspergillus spp.-directed antifungal prophylaxis. The overall risk for infectious complications at AML diagnosis is significantly higher for palliative AML patients at diagnosis while patients undergoing induction chemotherapy have a significantly higher risk of infections after initiation of AML treatment. In addition, there is a strong correlation between the occurrence of pneumonia including atypical pneumonia and pulmonary IFD and the ECOG performance status at diagnosis in the palliative AML patient group. Analysis of intensive care unit (ICU) treatment (e.g. in case of sepsis or pneumonia) for both subgroups reveals a positive outcome in 10 of 15 patients (66.7%) with palliative AML treatment and in 15 of 18 patients (83.3%) receiving induction chemotherapy. Importantly, the presence of infections and the ECOG performance status at diagnosis significantly correlate with the overall survival (OS) of palliative AML patients (315 days w/o infection vs. 69 days with infection, P 0.0049 and 353 days for ECOG < 1 vs. 50 days for ECOG > 2, P < 0.001, respectively) in this intent-to-treat analysis. CONCLUSION: The risk and the pattern of infectious complications at diagnosis and after initiation of AML therapy depends on age, ECOG performance status and subsequent treatment intensity. A comprehensive diagnostic work-up for identification of pulmonary IFD is indispensable for effective treatment of pneumonia in AML patients. The presence of infectious complications at diagnosis contributes to an inferior outcome in elderly AML patients.

Prediction of complete remission and survival in acute myeloid leukemia using supervised machine learning.

Achievement of complete remission signifies a crucial milestone in the therapy of acute myeloid leukemia (AML) while refractory disease is associated with dismal outcomes. Hence, accurately identifying patients at risk is essential to tailor treatment concepts individually to disease biology. We used nine machine learning (ML) models to predict complete remission and 2-year overall survival in a large multicenter cohort of 1,383 AML patients who received intensive induction therapy. Clinical, laboratory, cytogenetic and molecular genetic data were incorporated and our results were validated on an external multicenter cohort. Our ML models autonomously selected predictive features including established markers of favorable or adverse risk as well as identifying markers of so-far controversial relevance. De novo AML, extramedullary AML, double-mutated CEBPA, mutations of CEBPA-bZIP, NPM1, FLT3-ITD, ASXL1, RUNX1, SF3B1, IKZF1, TP53, and U2AF1, t(8;21), inv(16)/t(16;16), del(5)/del(5q), del(17)/del(17p), normal or complex karyotypes, age and hemoglobin concentration at initial diagnosis were statistically significant markers predictive of complete remission, while t(8;21), del(5)/del(5q), inv(16)/t(16;16), del(17)/del(17p), double-mutated CEBPA, CEBPA-bZIP, NPM1, FLT3-ITD, DNMT3A, SF3B1, U2AF1, and TP53 mutations, age, white blood cell count, peripheral blast count, serum lactate dehydrogenase level and hemoglobin concentration at initial diagnosis as well as extramedullary manifestations were predictive for 2-year overall survival. For prediction of complete remission and 2-year overall survival areas under the receiver operating characteristic curves ranged between 0.77-0.86 and between 0.63-0.74, respectively in our test set, and between 0.71-0.80 and 0.65-0.75 in the external validation cohort. We demonstrated the feasibility of ML for risk stratification in AML as a model disease for hematologic neoplasms, using a scalable and reusable ML framework. Our study illustrates the clinical applicability of ML as a decision support system in hematology.

Characteristics and outcome of patients with acute myeloid leukemia and trisomy 4.

We retrospectively studied 125 patients with acute myeloid leukemia and trisomy 4 (median age at diagnosis, 58 years; range, 16-77 years) treated between 2000 and 2019 within a multicenter study. Trisomy 4 was the sole abnormality in 28 (22%) patients and additional abnormalities were present in 97 (78%) patients. Twenty-two (22%) and 15 (15%) of 101 tested patients harbored NPM1 and FLT3-ITD mutations. Two (3%) of 72 tested patients had double CEBPA mutations. Data on response to intensive anthracycline-based induction therapy were available for 119 patients. Complete remission was achieved in 67% (n=80) and the early death rate was 5% (n=6). Notably, patients with trisomy 4 as sole abnormality had a complete remission rate of 89%. Allogeneic hematopoietic cell transplantation was performed in 40 (34%) patients, of whom 19 were transplanted in first complete remission. The median follow-up of the intensively treated cohort was 5.76 years (95% confidence interval [95% CI]: 2.99-7.61 years). The 5-year overall survival and relapse-free survival rates were 30% (95% CI: 22-41%) and 27% (95% CI: 18-41%), respectively. An Andersen-Gill regression model on overall survival revealed that favorable-risk according to the European LeukemiaNet classification (hazard ratio [HR]=0.34; P=0.006) and trisomy 4 as sole abnormality (HR=0.41; P=0.01) were favorable factors, whereas age with a difference of 10 years (HR=1.15; P=0.11), female gender (HR=0.74; P=0.20) and allogeneic hematopoietic cell transplantation (HR=0.64; P=0.14) did not have an significant impact. In our cohort, patients with trisomy 4 as their sole abnormality had a high complete remission rate and favorable clinical outcome. Allogeneic hematopoietic cell transplantation did not seem to improve overall survival.

Retained functional normal and preleukemic HSCs at diagnosis are associated with good prognosis in DNMT3AmutNPM1mut AMLs.

Acute myeloid leukemia (AML) is a heterogeneous disease characterized by high rate of relapse and mortality. Current chemotherapies whilst successful in eradicating blasts, are less effective in eliminating relapse-causing leukemic stem cells (LSCs). Although LSCs are usually identified as CD34+CD38- cells, there is significant heterogeneity in surface marker expression, and CD34- LSCs exist particularly in NPM1mut AMLs. By analyzing diagnostic primary DNMT3AmutNPM1mut AML samples, we suggest a novel flow cytometry sorting strategy particularly useful for CD34neg AML subtypes. To enrich for LSCs independently of CD34 status, positive selection for GPR56 and negative selection for NKG2D ligands are used. We show that the functional reconstitution capacity of CD34- and CD34+ LSCs as well as their transcriptomes are very similar which support phenotypic plasticity. Furthermore, we show that although CD34+ subpopulations can contain next to LSCs also normal and/or preleukemic hematopoietic stem cells (HSCs), this is not the case in CD34-GPR56+NKG2DL- enriched LSCs which thus can be isolated with high purity. Finally, we show that patients with AML, who retain at the time of diagnosis a reserve of normal and/or preleukemic HSCs in their bone marrow able to reconstitute immunocompromised mice, have significantly longer relapse-free and overall survival than patients with AML in whom functional HSCs are no longer detectable.

Overlapping features of therapy-related and de novo NPM1-mutated AML.

NPM 1-mutated acute myeloid leukemia (AML) shows unique features. However, the characteristics of "therapy-related" NPM1-mutated AML (t-NPM1 AML) are poorly understood. We compared the genetics, transcriptional profile, and clinical outcomes of t-NPM1 AML, de novo NPM1-mutated AML (dn-NPM1 AML), and therapy-related AML (t-AML) with wild-type NPM1 (t-AML). Normal karyotype was more frequent in t-NPM1 AML (n = 78/96, 88%) and dn-NPM1 (n = 1986/2394, 88%) than in t-AML (n = 103/390, 28%; P < .001). DNMT3A and TET2 were mutated in 43% and 40% of t-NPM1 AML (n = 107), similar to dn-NPM1 (n = 88, 48% and 30%; P > 0.1), but more frequently than t-AML (n = 162; 14% and 10%; P < 0.001). Often mutated in t-AML, TP53 and PPM1D were wild-type in 97% and 96% of t-NPM1 AML, respectively. t-NPM1 and dn-NPM1 AML were transcriptionally similar, (including HOX genes upregulation). At 62 months of median follow-up, the 3-year overall survival (OS) for t-NPM1 AML (n = 96), dn-NPM1 AML (n = 2394), and t-AML (n = 390) were 54%, 60%, and 31%, respectively. In multivariable analysis, OS was similar for the NPM1-mutated groups (hazard ratio [HR] 0.9; 95% confidence interval [CI], 0.65-1.25; P = .45), but better in t-NPM1 AML than in t-AML (HR, 1.86; 95% CI, 1.30-2.68; P < .001). Relapse-free survival was similar between t-NPM1 and dn-NPM1 AML (HR, 1.02; 95% CI, 0.72-1.467; P = .90), but significantly higher in t-NPM1 AML versus t-AML (HR, 1.77; 95% CI, 1.19-2.64; P = .0045). t-NPM1 and dn-NPM1 AML have overlapping features, suggesting that they should be classified as a single disease entity.