Background. Acute promyelocytic leukemia (APL) is a subtype of acute myeloid leukemia defined by the presence of a genetic abnormality, namely the PML::RARA gene fusion, as the result of a reciprocal balanced translocation between chromosome 17 and chromosome 15. APL is a veritable emergency in hematology due to the risk of early death and coagulopathy if left untreated; thus, a rapid diagnosis is needed in this hematological malignancy. Needless to say, cytogenetic and molecular biology techniques, i.e., fluorescent in situ hybridization (FISH) and polymerase chain reaction (PCR), are essential in the diagnosis and management of patients diagnosed with APL. In recent years, the use of artificial intelligence (AI) and its brances, machine learning (ML), and deep learning (DL) in the field of medicine, including hematology, has brought to light new avenues for research in the fields of blood cancers. However, to our knowledge, there is no comprehensive evaluation of the potential applications of AI, ML, and DL in APL. Thus, the aim of the current publication was to evaluate the prospective uses of these novel technologies in APL. Methods. We conducted a comprehensive literature search in PubMed/MEDLINE, SCOPUS, and Web of Science and identified 20 manuscripts eligible for the qualitative analysis. Results. The included publications highlight the potential applications of ML, DL, and other AI branches in the diagnosis, evaluation, and management of APL. The examined AI models were based on the use of routine biological parameters, cytomorphology, flow-cytometry and/or OMICS, and demonstrated excellent performance metrics: sensitivity, specificity, accuracy, AUROC, and others. Conclusions. AI can emerge as a relevant tool in the evaluation of APL cases and potentially contribute to more rapid screening and identification of this hematological emergency.

Background: Diffuse large B-cell lymphoma (DLBCL) is a biologically heterogeneous malignancy, with various outcomes despite significant advances in therapeutic options. Current conventional prognostic tools, e.g., the International Prognostic Index (IPI), lack sufficient precision at an individual patient level. However, artificial intelligence (AI), including machine learning (ML) and deep learning (DL), can enable specialists to navigate complex datasets, with the final aim of improving prognostic models for DLBCL. Objectives: This scoping review aims to systematically map the current literature regarding the use of AI/ML techniques in DLBCL outcome prediction and risk stratification. We categorized studies by data modality and computational approach to identify key trends, knowledge gaps, and opportunities for their translation into current practice. Methods: We conducted a structured search of the PubMed/MEDLINE, Scopus, and Cochrane Library databases through July 2025 using terms related to DLBCL, prognosis, and AI/ML. Eligible studies included original papers applying AI/ML to predict survival outcomes, classify risk groups, or identify prognostic subtypes. Studies were categorized based on input modality: clinical, positron emission tomography/computed tomography (PET/CT) imaging, histopathology, transcriptomics, genomics, circulating tumor DNA (ctDNA), and multi-omics data. Narrative synthesis was performed in line with PRISMA-ScR guidelines. Results: From the 215 records screened, 91 studies met the inclusion criteria. Group-wise we report the following categories: clinical risk features (n = 8), PET/CT imaging (n = 30), CT (n = 1), digital pathology (n = 3), conventional histopathology (n = 2), gene expression profiling (n = 19), specific mutational signatures (n = 18), ctDNA (n = 3), microRNA (n = 2), and multi-omics integration (n = 5). The most common techniques reported amongst the papers included ensemble learning, convolutional neural networks (CNNs), and LASSO-based Cox models. Several AI techniques demonstrated superior predictive performance over IPI, with area under the curve (AUC) values frequently exceeding 0.80. Multi-omics models and ctDNA-based predictors showed strong potential for clinical translation, a perspective worth considering in further studies. Conclusions: AI/ML methods are increasingly used in DLBCL to improve prognostic accuracy by leveraging data types with diverse inputs. These approaches allow an enhanced stratification, superior to traditional indices, and support the early identification of high-risk patients, earlier guidance for therapy tailoring, and early trial enrollment for flagged cases. Future investigations should focus on external validation and improvement of model interpretability, with tangible perspectives of integration into real-world workflows and translation from bench to bedside.

Representative microscopic images of bone marrow aspirate from a patient previously diagnosed with high-risk myelodysplastic neoplasm that has recently evolved into acute myeloid leukemia (AML)

Metastatic cancers, particularly those involving bone mar­row metastases, present significant challenges in cli­ni­cal ma­nagement. The presence of bone marrow me­tas­tases cri­ti­cally influences cancer treatment strategies, ne­ces­si­ta­ting comprehensive patient assessments. Diagnostic con­­fir­­ma­­tion involves imaging studies and bone mar­row biop­sy or aspiration, with histopathological and im­mu­no­his­to­che­mi­cal exams. The prognosis for patients with bone mar­row metastases is generally poor. Complications from mye­lo­sup­pres­sion and advanced disease stages further com­pli­cate the ma­nage­ment. This article presents two cases of solid tumors with bone marrow metastases, highlighting the diverse pre­sen­ta­tions of such metastases. These cases emphasize the importance of bone marrow evaluation in patients with solid tumors who exhibit unexplained blood ab­nor­malities, as this assessment is crucial for accurate diag­nosis, informed treat­ment decisions, and improved prognosis.

e24086 Background: While FOLFIRINOX (leucovorin, fluorouracil, irinotecan and oxaliplatin) has been well established for gastrointestinal cancer treatment including pancreatic and colorectal cancer, high grade neutropenia and febrile neutropenia (FN) should be closely monitored due to the myelosuppressive nature of the regimen. The level of evidence remains to be examined for the effect of primary prophylaxis (PP) with granulocyte-colony stimulating factor (G-CSF) on prevention of such severe neutropenia in FOLFIRINOX therapy. Methods: PubMed and Cochrane database were searched for randomized controlled trials and observational studies that compared G-CSF PP to no PP (secondary prophylaxis and no prophylaxis combined) for neutropenia prevention in FOLFIRINOX regimen. Studies were included when the outcomes of neutropenia with higher than grade 3 or FN were reported. Heterogeneity was examined with I ² statistics. A random-effects model was used for outcomes with high heterogeneity. Results: Out of 74 studies searched, we included 8 studies (1 RCT, 1 pooled analysis of RCTs and 6 observational studies) with 920 patients. 422 (45.9%) patients underwent G-CSF PP. The median ages ranged from 53.5 to 66. Male sex was 55.1%. Locally advanced or metastatic pancreatic cancer was the most common cancer type (n = 794, 86.3%), followed by colorectal cancer (n = 86, 9.3%), biliary tract cancer (n = 33, 3.6%), and gastric cancer (n = 7, 0.8%). ECOG performance status score was mostly 0-1 (79.6%) at baseline. Cases of grade 3 or higher neutropenia were significantly less common in patients who received G-CSF as PP upon the start of FOLFIRINOX therapy (Risk ratio (RR) 0.45 [95% confidence interval (CI) 0.32-0.64] (p < 0.00001)). FN also occurred to a significantly less extent in patients with G-CSF PP (RR 0.27 [95% CI 0.13-0.57] (p = 0.0005)). Hazard ratios (HRs) for overall survival (OS) were collected in 4 studies, of which 2 presented HR for OS comparing G-CSF PP group to no G-CSF group (HR 0.75 [95% CI 0.52 – 1.08] (p = 0.12) for Canton 2022; HR 0.46 [95% CI 0.30 - 0.73] (p = 0.001) for Carvalho de Brito 2023) and the other 2 presented HR for OS comparing G-CSF PP group to no PP group (HR 0.566 [95% CI 0.403-0.796] (p = 0.001) for Jung 2020; HR 0.35 [95% CI 0.16-0.76] (p = 0.005) for Moorcraft 2014). All 4 of them favored PP with G-CSF in terms of OS, but statistical significance could not be drawn together due to differences in HR measurement. Conclusions: These findings suggest that PP with G-CSF when starting a FOLFIRINOX regimen significantly reduces cases of severe neutropenia. Long-term efficacy of this preventive measure should be further studied.

Multiple myeloma represents a hematologic malignancy characterized by the abnormal proliferation of plasma cells in the bone marrow. Through this proliferation, the malignant plasma cells disrupt normal blood cell production, subsequently causing the clinical hallmarks of this pathology: bone destruction, anemia, renal impairment and a highly increased susceptibility to infections. Despite the therapeutic options available, multiple myeloma remains an incurable disease (1). The rising use of combination therapies, triplets or quadruplets, by using immunomodulatory drugs, monoclonal antibodies and targeted therapies, elicited improved survival rates and a significant improvement of the quality of life of these patients. However, there is a luring need to precisely quantify the life horizons of these patients, therefore the most recent tool for this estimate has been developed, the R-ISS score. The R-ISS score uses various biomarkers such as serum β2-microglobulin, serum albumin, LDH levels and a more refined tool, the cytogenetic abnormalities list, to predict the outcome of each case. The addition of the precise cytogenetic risk groups boosted the sensitivity of the previous ISS score, but also unveiled the existing discrepancies in accessing modern diagnostic tools across treatment centers (2). Moreover, patient-oriented reports pointed out that from a patient perspective the highest perceived cost had been perceived until the neoplasm diagnostic was established, hence the reluctance for specialized investigations (eg. FISH testing and karyotypes etc.)