Hematologic malignancies, including acute myeloid leukemia, myelodysplastic syndromes, lymphoma, and multiple myeloma, are characterized by profound biological heterogeneity and highly dynamic treatment trajectories that conventional, static prognostic systems incompletely capture. Cellular therapies, such as chimeric antigen receptor T-cell therapy and hematopoietic stem cell transplantation, offer potentially curative options for relapsed or refractory disease, yet outcomes remain highly variable, and management decisions regarding conditioning intensity, lymphodepletion, immunosuppression, and toxicity surveillance continue to be largely protocol-driven rather than individually adapted. Artificial intelligence (AI) and machine learning (ML) have demonstrated substantial promise in diagnostic support, prognostic stratification, and multimodal data integration across hematologic malignancies, but existing models remain predominantly static and related to pre-treatment in orientation, limiting their utility for real-time clinical guidance. This review summarizes current AI applications in hematologic oncology; critically compares the strengths, limitations, and clinical applicability of major AI model classes, including traditional machine learning, deep learning, multimodal integrative frameworks, reinforcement learning, digital twins, and emerging foundation models and large language models; and proposes an adaptive, multimodal paradigm. We examine key enabling technologies and address the clinical, regulatory, ethical, and implementation challenges that must be resolved before these systems can be deployed at the bedside. We argue that the central challenge facing the field is no longer whether AI can predict outcomes, but whether it can actively guide real-time therapeutic decisions, and that achieving this transition will require interdisciplinary collaboration, prospective validation, and governance frameworks capable of ensuring interpretability, equity, and clinical trustworthiness.

We report a female in her late 80s with high-risk pleomorphic mantle cell lymphoma (MCL) harboring germline ATM mutation and 17p deletion who achieved complete metabolic response with zanubrutinib plus rituximab. Serial peripheral blood next-generation sequencing (NGS) during remission revealed emergence of a molecularly distinct pre-leukemic clone characterized by DNMT3A, TET2, and a TP53 point mutation (p.Tyr220Cys)—distinct from the original 17p deletion. Approximately 20 months after MCL diagnosis, she developed acute myeloid leukemia (AML) with FLT3-TKD and NPM1 mutations, confirming transformation of the pre-leukemic clone. Longitudinal VAF tracking demonstrated complete eradication of MCL-associated mutations (ID3, BIRC3) while the myeloid clone expanded. This case provides direct molecular evidence that AML arose from clonal evolution of a pre-existing hematopoietic clone rather than direct MCL transformation, with implications for understanding second malignancies in BTK inhibitor-treated patients.

Right Temporal Lobe Tuberculoma Presenting as Seizures in a Patient With Pulmonary Tuberculosis - Article abstract #951659

Acute myeloid leukemia (AML) is predominantly a disease of older adults, with a median age at diagnosis of 68–72 years. Management in this population is complicated by adverse cytogenetic and molecular features, higher rates of secondary disease, and patient-specific factors such as comorbidity and frailty. This narrative review synthesizes the current evidence on risk stratification and treatment of AML in adults aged 60 years and older, with dedicated attention to patients aged 60–75 (“fit” older adults) and those older than 75, including octogenarians. The VIALE-A trial established venetoclax plus azacitidine as standard of care for patients ineligible for intensive chemotherapy (composite complete remission 66.4%; median overall survival 14.7 vs. 9.6 months with azacitidine alone). For fit adults aged 60–75, the choice between intensive chemotherapy and venetoclax-based regimens remains under active investigation, with emerging randomized data suggesting comparable outcomes and a possible advantage for venetoclax-based approaches in adverse-risk disease. Risk stratification has evolved beyond the 2022 European LeukemiaNet (ELN) classification, which was developed in intensively treated cohorts; the 2024 ELN genetic risk classification for less-intensive therapy now provides a framework specific to this population. TP53-mutated AML, including multi-hit disease, remains the dominant unmet need across all treatment modalities. Advances in reduced-intensity conditioning have expanded transplant eligibility into the seventh and eighth decades, and molecularly targeted approaches, including FLT3, IDH1/2, and menin inhibitors, are reshaping frontline and relapsed/refractory therapy. This review covers epidemiology, risk stratification, treatment stratified by age, fitness, and genetic subgroup, the role of transplantation and maintenance therapy, and the limitations of the current evidence base for this heterogeneous population.

Background: Tarlatamab, a Delta-like ligand 3 (DLL3)-targeting bispecific T-cell engager (BiTE), has demonstrated significant efficacy in relapsed small cell lung cancer (SCLC) in clinical trials. However, real-world clinical outcomes and its efficacy in extrapulmonary small cell carcinoma (EPSCC) remain sparsely characterized. Methods: We conducted a retrospective, single-institution cohort study of 24 adult patients with moderately pretreated advanced SCLC (n = 19) or EPSCC (n = 5) who received standard-of-care tarlatamab. Endpoints included objective response rate (ORR), progression-free survival (PFS), overall survival (OS), and safety. Results: Patients had received a median of two prior lines of therapy, and 38% had baseline brain metastases. The overall intent-to-treat (ITT) ORR was 25.0%. Among response-evaluable patients (n = 18), the ORR was 33.3%. Efficacy was notably discordant between histologies: the SCLC cohort achieved an ITT ORR of 31.6% (46.2% in evaluable patients), whereas 100% of EPSCC patients experienced progressive disease. Systemic responses were observed in patients with baseline brain metastases (ORR 33.3%). The safety profile was manageable; any-grade CRS and ICANS occurred in 58% and 29% of patients, respectively. Severe (Grade ≥ 3) toxicities were rare, and tocilizumab was utilized therapeutically in 50% of patients for low-grade toxicity. Conclusions: These real-world data are consistent with tarlatamab’s systemic efficacy and tolerability in SCLC. The lack of clinical benefit observed in this small EPSCC cohort raises a hypothesis that requires prospective biomarker-correlated evaluation.