The European LeukemiaNet (ELN) genetic risk classifications were developed based on data from younger adults receiving intensive chemotherapy. Emerging analyses from patients receiving less-intensive therapies prompted a proposal for an ELN genetic risk classification specifically for this patient population.
Hyperleukocytosis (HL) per se is a laboratory abnormality, commonly defined by a white blood cell count >100 000/µL, caused by leukemic cell proliferation. Not the high blood count itself, but complications such as leukostasis, tumor lysis syndrome, and disseminated intravascular coagulation put the patient at risk and require therapeutic intervention. The risk of complications is higher in acute than in chronic leukemias, and particularly leukostasis occurs more often in acute myeloid leukemia (AML) for several reasons. Only a small proportion of AML patients present with HL, but these patients have a particularly dismal prognosis because of (1) a higher risk of early death resulting from HL complications; and (2) a higher probability of relapse and death in the long run. Whereas initial high blood counts and high lactate dehydrogenase as an indicator for high proliferation are part of prognostic scores guiding risk-adapted consolidation strategies, HL at initial diagnosis must be considered a hematologic emergency and requires rapid action of the admitting physician in order to prevent early death.
Biallelic mutations of the CEBPA gene (CEBPAbi) define a distinct entity associated with favorable prognosis; however, the role of monoallelic mutations (CEBPAsm) is poorly understood. We retrospectively analyzed 4708 adults with acute myeloid leukemia (AML) who had been recruited into the Study Alliance Leukemia trials, to investigate the prognostic impact of CEBPAsm. CEBPA mutations were identified in 240 patients (5.1%): 131 CEBPAbi and 109 CEBPAsm (60 affecting the N-terminal transactivation domains [CEBPAsmTAD] and 49 the C-terminal DNA-binding or basic leucine zipper region [CEBPAsmbZIP]). Interestingly, patients carrying CEBPAbi or CEBPAsmbZIP shared several clinical factors: they were significantly younger (median, 46 and 50 years, respectively) and had higher white blood cell (WBC) counts at diagnosis (median, 23.7 × 109/L and 35.7 × 109/L) than patients with CEBPAsmTAD (median age, 63 years, median WBC 13.1 × 109/L; P < .001). Co-mutations were similar in both groups: GATA2 mutations (35.1% CEBPAbi; 36.7% CEBPAsmbZIP vs 6.7% CEBPAsmTAD; P < .001) or NPM1 mutations (3.1% CEBPAbi; 8.2% CEBPAsmbZIP vs 38.3% CEBPAsmTAD; P < .001). CEBPAbi and CEBPAsmbZIP, but not CEBPAsmTAD were associated with significantly improved overall (OS; median 103 and 63 vs 13 months) and event-free survival (EFS; median, 20.7 and 17.1 months vs 5.7 months), in univariate and multivariable analyses. Additional analyses revealed that the clinical and molecular features as well as the favorable survival were confined to patients with in-frame mutations in bZIP (CEBPAbZIP-inf). When patients were classified according to CEBPAbZIP-inf and CEBPAother (including CEBPAsmTAD and non-CEBPAbZIP-inf), only patients bearing CEBPAbZIP-inf showed superior complete remission rates and the longest median OS and EFS, arguing for a previously undefined prognostic role of this type of mutation.
The evaluation of bone marrow morphology by experienced hematopathologists is essential in the diagnosis of acute myeloid leukemia (AML); however, it suffers from a lack of standardization and inter-observer variability. Deep learning (DL) can process medical image data and provides data-driven class predictions. Here, we apply a multi-step DL approach to automatically segment cells from bone marrow images, distinguish between AML samples and healthy controls with an area under the receiver operating characteristic (AUROC) of 0.9699, and predict the mutation status of Nucleophosmin 1 (NPM1)—one of the most common mutations in AML—with an AUROC of 0.92 using only image data from bone marrow smears. Utilizing occlusion sensitivity maps, we observed so far unreported morphologic cell features such as a pattern of condensed chromatin and perinuclear lightening zones in myeloblasts of NPM1-mutated AML and prominent nucleoli in wild-type NPM1 AML enabling the DL model to provide accurate class predictions.