Evaluating the performance of large language models in haematopoietic stem cell transplantation decision-making.

In a first-of-its-kind study, we assessed the capabilities of large language models (LLMs) in making complex decisions in haematopoietic stem cell transplantation. The evaluation was conducted not only for Generative Pre-trained Transformer 4 (GPT-4) but also conducted on other artificial intelligence models: PaLm 2 and Llama-2. Using detailed haematological histories that include both clinical, molecular and donor data, we conducted a triple-blind survey to compare LLMs to haematology residents. We found that residents significantly outperformed LLMs (p = 0.02), particularly in transplant eligibility assessment (p = 0.01). Our triple-blind methodology aimed to mitigate potential biases in evaluating LLMs and revealed both their promise and limitations in deciphering complex haematological clinical scenarios.

Advances in the understanding of molecular genetics and therapy of Richter transformation in chronic lymphocytic leukemia.

Richter's transformation (RT) is defined as the evolution of chronic lymphocytic leukemia (CLL) or small lymphocytic lymphoma (SLL) into an aggressive lymphoma, most commonly diffuse large B-cell lymphoma. This complication is rare and aggressive, with poor prognosis and dismal survival. Clonal relationship with the underlying CLL/SLL, observed in ∼80% of cases, represents one of the main factors affecting prognosis. Treatment has been historically based on chemoimmunotherapy, but frequent mutations in genes involved in cell survival and proliferation-such as TP53, NOTCH1, MYC, CDKN2A-confer resistance to standard treatments. During the last years, advances in the knowledge of the biological mechanisms underlying RT allowed to identify genetic and molecular lesions that can potentially be targeted by novel selective agents. Pathway and checkpoint inhibitors, bispecific antibodies and CAR T-cell therapy are currently under investigation and represent promising treatment options. This review summarizes current biological evidence and available data on novel therapeutic agents.

Anti-CD38 monoclonal antibody impairs CD34+ mobilization and affects clonogenic potential in multiple myeloma patients.

BACKGROUND: Induction with daratumumab-based regimens followed by autologous stem cell transplantation is the current standard for newly diagnosed multiple myeloma (NDMM) patients eligible for intensive chemotherapy. However, concerns emerged regarding potential negative effects following daratumumab-based treatment on CD34+ mobilization. We here compared CD34+ mobilization and clonogenic potential between daratumumab and non-daratumumab based therapy without upfront plerixafor administration among patients affected by NDMM. MATERIALS AND METHODS: Clinical, mobilization and clonogenic data from 41 consecutively enrolled NDMM patients were analyzed. Patients underwent collection of autologous CD34+ by apheresis at the ASST Grande Ospedale Metropolitano Niguarda, Milan, Italy, from January 2021 to March 2023. Clonogenicity analysis was performed on BFU-E and CFU-GM. RESULTS: Seventy-five percent of daratumumab-treated patients underwent >1 apheresis, compared to 24% of non-daratumumab patients (p=0.0017). Daratumumab-treated patients had significantly lower CD34+ count (mean 38 vs 79/µL, respectively; p=0.0011), with a median CD34+ harvest of 3.98×106/kg (range 1.68-9.18) vs 6.87×106/kg (range 1.63-16.85) in non-daratumumab-treated (p=0.0006). In multivariate analysis the likelihood of undergoing >1 apheresis was significantly higher in older patients (OR 1.2, 95% CI 1-1.4, Z=2.10, p=0.03) and daratumumab-treated patients (OR 15, 95% CI 2.8-129, p=0.004). Moreover, daratumumab-based induction therapy demonstrated an independent negative association with BFU-E colony formation (p=0.0148), even when accounting for patient age and CD34+ levels. DISCUSSION: Our findings underscore the impact of daratumumab-based treatment on CD34+ mobilization in a real-life, upfront plerixafor-free population of NDMM patients. Higher probability of requiring multiple apheresis occurred among daratumumab-treated patients. Interestingly, the observation that daratumumab might negatively impact BFU-E colony formation, independent of CD34+ cell count, offers novel biological perspectives. Appropriate strategies should be adopted by the Apheresis teams to mitigate these potential negative effects.