Acute myeloid leukemia (AML) is associated with poor outcomes in older adults. A major goal of treatment is to balance quality of life and functional independence with disease control. With the approval of new, more tolerable regimens, more older adults are able to receive AML-directed therapy. Among these options are hypomethylating agents (HMAs), specifically azacitidine and decitabine. HMAs have become an integral part of AML therapy over the last two decades. These agents are used either as monotherapy or nowadays more commonly in combination with other agents such as the Bcl-2 inhibitor venetoclax. Biological AML characteristics, such as molecular and cytogenetic risk factors, play crucial roles in guiding treatment decisions. In patients with high-risk AML, HMAs are increasingly used rather than intensive chemotherapy, although further trials based on a risk-adapted approach using patient- and disease-related factors are needed. Here, we review trials and evidence for the use of HMA monotherapy and combination therapy in the management of older adults with AML. Furthermore, we discuss the use of HMAs and HMA combination therapies in AML, mechanisms of action, their incorporation into hematopoietic stem cell transplantation strategies, and their use in patients with comorbidities and reduced organ function.

Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.