Publication Number: 1287

 

Abstract Title : Long-term outcomes with emicizumab prophylaxis in patients with hemophilia a in China

 

Category: 300s - Hemostasis, Thrombosis and Vascular Wall Biology

 

Review Category: 322. Hemophilia A and B: Clinical and Epidemiological

 

Authors

 

Yuan Xu¹, Ying Wang², Ningling Wang³, Liya He⁴, Jing Ling⁵, Mingwei Jin⁶, Bingshou Xie⁷, Shaohua Le⁸, Meijuan Huang⁸, Jie Peng⁹, Hongbo Cheng¹⁰, Jiao Jin¹¹, Li Zhou³, Zeping Zhou¹², Can Gai¹³, Yujing Zhang¹⁴, Mei Sun¹⁵, Xiaojing Li¹⁶, Jie Yin¹⁷, Yanli Cheng¹⁸, Ailing Xue¹⁹, Weiqun Xu²⁰, Hong Han²¹, Fuhua Zhang²², Weiguo Zhu²³, Shen He²⁴, Hua Zhou²⁵, Lei Zhang¹, Feng Xue¹, Renchi Yang¹

 

¹ Institute of Hematology & Blood Diseases Hospital, Tianjin, China, ² Shenzhen Children's Hospital, Shenzhen, China, ³ the Second Hospital of Anhui Medical University, Hefei, China, ⁴ Guangzhou Women and Children's Medical Center, Guangzhou, China, ⁵ Children's Hospital of Soochow University, Suzhou, China, ⁶ Xuzhou Star Hospital, Xuzhou, China, ⁷ Wenzhou People's Hospital, Wenzhou, China, ⁸ Fujian Medical University Union Hospital, Fuzhou, China, ⁹ Xiangya Hospital, Changsha, China, ¹⁰ Jiangxi Provincial People's Hospital Affiliated to Nanchang University, Nanchang, China, ¹¹ Affiliated Hospital of Guizhou Medical University, Guiyang, China, ¹² The Second Affiliated Hospital of Kunming Medical University, Kunming, China, ¹³ Huaibei People’s Hospital, Huaibei, China, ¹⁴ the Fourth Hospital of Harbin Medical University, Harbin, China, ¹⁵ Qilu Hospital of Shandong University Dezhou Hospital, Dezhou, China., Dezhou, China, ¹⁶ Chengdu New Century Women’s and Children’s Hospital, Chengdu, 610051, China, Chengdu, China, ¹⁷ The First Affiliated Hospital of Soochow University, Suzhou, China., Suzhou, China, ¹⁸ Children’s Hospital of Shanxi, Taiyuan, China, ¹⁹ Zibo Central Hospital, Shandong Zibo 255036, China, Zibo, China, ²⁰ Children's Hospital, Zhejiang University School of Medicine, Hangzhou, China., Hangzhou, China, ²¹ Liyuan Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430077, China, Wuhan, China, ²² Dongying People's Hospital, Dongying 257091, Shandong Province, China., Dongying, China, ²³ Foresea Life Insurance Shaoguan Hospital, Shaoguan, China., Shaoguan, China, ²⁴ Department of Hematology, Kaifeng Center Hospital, Kaifeng, Henan 475000, China., Kaifeng, China, ²⁵ Department of Hematology Oncology, Changzhou Children's Hospital, Changzhou, Jiangsu Province, 213000 China, Changzhou, China

 

Abstract Body

 

Introduction: Emicizumab, a bispecific monoclonal antibody that bridges activated factor IX and factor X, has emerged as an effective prophylactic treatment for patients with hemophilia A (PwHAs). However, real-world responses are heterogeneous, long-term data remain limited, and the determinants of long-term efficacy are unclear.

 

Methods: Data from 132 pediatric and adult PwHAs with/without factor VIII (FVIII) inhibitors who received emicizumab prophylaxis for more than one year from 25 centers in China were pooled to establish a long-term efficacy and safety profile. Annualized bleed rate (ABR) and Annualized joint bleed rate (AJBR) were estimated using the negative binomial regression model. Machine learning models—including the Feature Tokenizer Transformer, random forest, XGBoost, LightGBM, ResNet, and CatBoost—were applied to predict post-emicizumab ABR.

 

Results: A total of 132 patients were enrolled in our study. All patients were followed up for a median of 26.0 months (interquartile range [IQR], 16.0–40.0). Across a median efficacy period of 25.5 months (IQR, 16.0–40.0; data cutoff: May 25, 2025), the model-based ABR (for all bleeds) and treated ABR were 0.81 (95% confidence interval [CI], 0.62–1.07) and 0.30 (0.21-0.42), respectively. ABR declined compared to baseline and then stabilized at <1 in analyses based on 12-month treatment intervals. During months 1 to 12 (n=132), 62.9% of participants had 0 bleeds, 82.6% had no treated bleeds, 90.9% reported no joint bleeds, and 94.7% reported no treated joint bleeds.

 

To determine the factors associated with long-term efficacy, we applied machine learning models. Among them, the Feature Tokenizer Transformer model yielded the best performance (AUC=0.905±0.012). Feature importance was ranked by mean absolute SHapley Additive exPlanations (SHAP) values. The top three predictors of post-emicizumab ABR > 1 were: historical inhibitor status, whether standard loading dose (3 mg/kg for 4 weeks) was administered, and baseline ABR.

 

Injection site reactions were reported in 10 out of 132 patients (7.6%). No deaths, thromboembolic events, or thrombotic microangiopathies were reported during the study period.

 

Conclusions: In this multicenter real-world study, we indicated that emicizumab prophylaxis maintained low bleeding rates in PwHAs of all ages and remains well tolerated. Historical inhibitor status, whether standard loading dose was administered, and baseline ABR were the most informative variables for predicting post-emicizumab ABR > 1.

 

 

 

Keywords: Bleeding and Clotting, Real-World Evidence, Machine Learning, Artificial Intelligence (AI), Diseases, Clinical Research, Patient-Reported Outcomes, Study Population, Human, Research

 

Disclosure : Yuan Xu: None declared, Ying Wang: None declared, Ningling Wang: None declared, Liya He: None declared, Jing Ling: None declared, Mingwei Jin: None declared, Bingshou Xie: None declared, Shaohua Le: None declared, Meijuan Huang: None declared, Jie Peng: None declared, Hongbo Cheng: None declared, Jiao Jin: None declared, Li Zhou: None declared, Zeping Zhou : None declared, Can Gai: None declared, Yujing Zhang: None declared, Mei Sun : None declared, Xiaojing Li: None declared, Jie Yin: None declared, Yanli Cheng: None declared, Ailing Xue: None declared, Weiqun Xu : None declared, Hong Han: None declared, Fuhua Zhang: None declared, Weiguo Zhu : None declared, Shen He: None declared, Hua Zhou: None declared, Lei Zhang: None declared, Feng Xue: None declared, Renchi Yang: Takeda, Consultancy (Includes expert testimony): Yes, Patents & Royalties: No, Ended employment in the past 24 months: No, Research Funding: No, Divested equity in a private or publicly-traded company in the past 24 months: No, Current equity holder in publicly-traded company: No, Current Employment: No, Current holder of stock options in a privately-held company: No, Current equity holder in private company: No, Honoraria: No, Novo Nordisk, Consultancy (Includes expert testimony): Yes, Patents & Royalties: No, Ended employment in the past 24 months: No, Research Funding: No, Divested equity in a private or publicly-traded company in the past 24 months: No, Current equity holder in publicly-traded company: No, Current Employment: No, Current holder of stock options in a privately-held company: No, Current equity holder in private company: No, Honoraria: No, Pfizer, Consultancy (Includes expert testimony): Yes, Patents & Royalties: No, Ended employment in the past 24 months: No, Research Funding: No, Divested equity in a private or publicly-traded company in the past 24 months: No, Current equity holder in publicly-traded company: No, Current Employment: No, Current holder of stock options in a privately-held company: No, Current equity holder in private company: No, Honoraria: No