Pedro Henriques Abreu

Introduction Endometrial carcinoma (EC) is a biologically heterogeneous malignancy, and contemporary molecular classification has improved prognostic stratification. Recently, homologous recombination deficiency (HRD) has gained attention in the context of emerging therapeutic strategies based on PARP inhibitors, highlighting the need to better define its prevalence and define its clinical relevance in EC. Materials and Methods Retrospective observational cohort study of 298 consecutive patients with endometrial carcinoma treated at a tertiary cancer centre. Molecular profiling was performed and patients were classified in risk groups according to the 2025 ESGO–ESTRO–ESP guidelines. Homologous recombination deficiency (HRD) was defined by the presence of pathogenic/likely pathogenic variants in homologous recombination repair genes. We assessed associations between HRD status and clinicopathological characteristics using exact tests. Overall survival (OS), recurrence-free survival (RFS) and progression-free survival (PFS) were analysed using the Kaplan–Meier method. Results Eighteen tumours (6.0%) were classified as HRD-positive. The most frequently affected genes were BRCA1/2 and ATM. HRD-positive tumours were more common among non-endometrioid histologies, high-grade disease, and poor-prognosis molecular subgroups. However, HRD status was not associated with differences in clinical outcomes, with no significant impact on overall survival (median OS 115.9 months vs not reached; p = 0.355), disease-free survival (median DFS 41.6 vs 31.3 months; p = 0.689), progression-free survival (median PFS 8.0 vs 13.8 months; p = 0.252) or platinum sensitivity (p=0.234). Conclusion HRD was rare and associated with aggressive biological features, but it did not have a prognostic value. These findings suggest that integrated molecular classification is paramount for risk stratification in EC, and that HRD, as currently defined, should not be used as an isolated biomarker for clinical decision-making.

Group fairness in machine learning is an important area of research focused on achieving equitable outcomes across different groups defined by sensitive attributes such as race or gender. Federated learning, a decentralized approach to training machine learning models across multiple clients, amplifies the need for fairness methodologies due to its inherent heterogeneous data distributions that can exacerbate biases. The intersection of federated learning and group fairness has attracted significant interest, with 48 research works specifically dedicated to addressing this issue. However, no comprehensive survey has specifically focused on group fairness in Federated Learning. In this work, we analyze the key challenges of this topic, propose practices for its identification and benchmarking, and create a novel taxonomy based on criteria such as data partitioning, location, and strategy. Furthermore, we analyze broader concerns, review how different approaches handle the complexities of various sensitive attributes, examine common datasets and applications, and discuss the ethical, legal, and policy implications of group fairness in FL. We conclude by highlighting key areas for future research, emphasizing the need for more methods to address the complexities of achieving group fairness in federated systems.

In the evolving field of machine learning, ensuring group fairness has become a critical concern, prompting the development of algorithms designed to mitigate bias in decision-making processes. Group fairness refers to the principle that a model’s decisions should be equitable across different groups defined by sensitive attributes such as gender or race, ensuring that individuals from privileged groups and unprivileged groups are treated fairly and receive similar outcomes. However, achieving fairness in the presence of group-specific concept drift remains an unexplored frontier, and our research represents pioneering efforts in this regard. Group-specific concept drift refers to situations where one group experiences concept drift over time, while another does not, leading to a decrease in fairness even if accuracy (ACC) remains fairly stable. Within the framework of federated learning (FL), where clients collaboratively train models, its distributed nature further amplifies these challenges since each client can experience group-specific concept drift independently while still sharing the same underlying concept, creating a complex and dynamic environment for maintaining fairness. The most significant contribution of our research is the formalization and introduction of the problem of group-specific concept drift and its distributed counterpart, shedding light on its critical importance in the field of fairness. In addition, leveraging insights from prior research, we adapt an existing distributed concept drift adaptation algorithm to tackle group-specific distributed concept drift, which uses a multimodel approach, a local group-specific drift detection mechanism, and continuous clustering of models over time. The findings from our experiments highlight the importance of addressing group-specific concept drift and its distributed counterpart to advance fairness in machine learning.