Eptacog beta, a recombinant factor VIIa bypassing agent, has demonstrated safety and efficacy in the management of bleeding events (BEs) in people with hemophilia and inhibitors. Data describing eptacog beta use in patients receiving emicizumab prophylaxis remains limited. This interim analysis of the American Thrombosis and Hemostasis Network 16 study, a phase 4, multicenter, US based, open-label study, evaluates the safety and real-world effectiveness of eptacog beta for the treatment of BEs experienced on emicizumab prophylaxis. Nineteen participants with hemophilia A and inhibitors who agreed to treat BEs with eptacog beta were included. Eptacog beta dosing was determined by the treating physician and participant. During the interim observational period, 9 of 19 participants (47%) experienced breakthrough BEs. Thirty-three BEs were treated using eptacog beta, with 1 participant contributing 18 BEs. Initial eptacog beta doses ranged from 56.8 to 245.1 μg/kg. A single eptacog beta dose was used to manage 66.7% of BEs. All events resolved without concomitant hemostatic medications. Bleeds treated with an initial eptacog beta dose ≥76 μg/kg had higher single-dose effectiveness and required fewer total doses than bleeds treated with an initial dose <76 μg/kg; differences were not statistically significant. Two participants were treated with eptacog beta perioperatively for 3 minor surgical procedures, and 1 participant was also treated with concomitant tranexamic acid. These observations demonstrate that eptacog beta was effectively used across a range of initial doses for bleed management and perioperative hemostasis by participants receiving emicizumab prophylaxis. No treatment-related adverse events, such as thrombosis, thrombotic microangiopathy, or immune responses, were observed. This trial was registered at www.clinicaltrials.gov as #NCT04647227.
BACKGROUND:Inherited platelet function disorders (IPFDs) are rare, heterogeneous conditions that pose diagnostic and management challenges. While bleeding in Glanzmann thrombasthenia (GT) and Bernard-Soulier syndrome (BSS) is well characterized, milder or unclassified IPFDs remain poorly defined. OBJECTIVE:To characterize the bleeding phenotype, treatment patterns, and diagnostic distribution of IPFDs across the United States using the national ATHNdataset. METHODS:We conducted a retrospective cohort study using the ATHNdataset, a deidentified registry maintained by the American Thrombosis and Hemostasis Network. Clinical outcomes, including bleeding events, laboratory data, treatments, and procedures, were analyzed for participants with IPFDs between 2013 and 2022 and with active follow-up from January 2021 to December 2022. RESULTS:Among 2302 individuals with IPFDs, 8.1% as GT, 2.4% as BSS, 7.0% as granule defects, and 81.6% as IPFD-other. Among 985 participants with active follow-up, 236 bleeding events were reported across 251 patients. The most common events were epistaxis (42.8%), followed by soft tissue (14.4%) and oral bleeding (13.9%). Notably, intracranial hemorrhage occurred in 8 patients and joint bleeds in 82, reflecting significant morbidity across all subtypes. Median ISTH-BAT scores were elevated-13 in GT, 16 in dense-granule defects, and 7 in unclassified IPFDs-exceeding reported population norms. Regarding hemostatic management, antifibrinolytics were used in over half of all patients, with desmopressin and platelet transfusions being used less frequently. CONCLUSION:By defining the clinical spectrum, treatment utilization, and residual diagnostic uncertainty across IPFDs, this study underscores the importance of improving diagnostic precision and care for patients with platelet function disorders in the modern era.
ABSTRACT:Artificial intelligence (AI) and its subdiscipline, machine learning (ML), have the potential to revolutionize health care, including hematology. The diagnosis and treatment of hematologic disorders depend on the integration of diverse data sources, such as imaging, pathology, omics, and laboratory parameters. The increasing volume and complexity of patient data have made clinical decision-making more challenging. AI/ML hold significant potential for enhancing diagnostic accuracy, risk stratification, and treatment response prediction through advanced modeling techniques. Generative AI, a recent advancement within the broader field of AI, is poised to have a profound impact on health care and hematology. Generative AI can enhance the development of novel therapeutic strategies, improve diagnostic workflows by generating high-fidelity images or pathology reports, and facilitate more personalized approaches to patient management. Its ability to augment clinical decision-making and streamline research represents a significant leap forward in the field. However, despite this potential, few AI/ML tools have been fully implemented in clinical practice due to challenges related to data quality, equity, advanced infrastructure, and the establishment of robust evaluation metrics. Despite its promise, AI implementation in hematology faces critical challenges, including bias, data quality issues, and a lack of regulatory frameworks and safety standards that keep pace with rapid technological advancements. In this review, we provide an overview of the current state of AI/ML in hematology as of 2025, identify existing gaps, and offer insights into future developments.
ABSTRACT Background The Natural History Study of the Safety, Effectiveness, and Practice of Treatment for People with Haemophilia (ATHN 7) monitors use of contemporary haemophilia therapies, including emicizumab, a bispecific antibody substituting for activated factor (F)VIII in people with haemophilia A (HA). Aim To report participant characteristics and real‐world safety and effectiveness of emicizumab in ATHN 7. Methods ATHN 7 is a prospective observational cohort study conducted across 26 American Thrombosis and Haemostasis Network (ATHN)‐affiliated sites. People with HA receiving emicizumab were eligible for inclusion in this analysis. Clinical information was collected quarterly through participant interview and medical record review. Safety was evaluated by documenting adverse events (AEs); effectiveness was assessed by annualized bleeding rates (ABRs). Results At data cut‐off (31st December 2023), 257 participants were receiving emicizumab; 63 (24.5%) had FVIII inhibitors at baseline; 84.4% had severe HA. In total, 109 (42.4%) participants were <12 years old. Median (range) emicizumab exposure duration was 116.4 (0.1–206.6) weeks. Overall, 40 AEs were reported in 13 (5.1%) participants; a total of 33 injection‐site reactions were reported in 7 (2.7%) participants. No thromboses or thrombotic microangiopathy were reported. There was one fatality from haemorrhagic shock, deemed unrelated to emicizumab. Median (range) ABR for treated bleeds was 0.25 (0–8.18) for participants with FVIII inhibitors and 0.51 (0–16.25) for participants without FVIII inhibitors. Conclusion In people with HA treated with emicizumab, no new safety signals were identified. ABRs were similar for participants with or without FVIII inhibitors, across different severities of HA. Trial Registration ClinicalTrials.gov identifier: NCT03619863
