CC BY 4.0 · Thromb Haemost 2022; 122(06): 913-925
DOI: 10.1055/s-0041-1739514
Coagulation and Fibrinolysis

Predictive Modeling Identifies Total Bleeds at 12-Weeks Postswitch to N8-GP Prophylaxis as a Predictor of Treatment Response

1   Katharine Dormandy Haemophilia and Thrombosis Centre, Royal Free Hospital, London, United Kingdom
,
Kingsley Hampton
2   Department of Cardiovascular Science, University of Sheffield, Sheffield, United Kingdom
,
Victor Jiménez-Yuste
3   Department of Hematology, La Paz University Hospital-IdiPaz, Autónoma University, Madrid, Spain
,
Guy Young
4   Hemostasis and Thrombosis Center, Cancer and Blood Disorders Institute, Children's Hospital Los Angeles, University of Southern California Keck School of Medicine, Los Angeles, California, United Sates
,
Soraya Benchikh el Fegoun
5   Global Medical Affairs Biopharm, Novo Nordisk Health Care AG, Zürich, Switzerland
,
Aidan Cooper
6   Predictive Analytics, Real World Solutions, IQVIA, London, United Kingdom
,
Erik Scalfaro
7   Real World Insights, IQVIA, Basel, Switzerland
,
8   Department of Hematology, Hemostasis, Oncology and Stem Cell Transplantation, Hannover Medical School, Hanover, Germany
› Author Affiliations
Funding This analysis and medical writing support for the article was funded by Novo Nordisk A/S (Bagsværd, Denmark).

Abstract

Background Predicting annualized bleeding rate (ABR) during factor VIII (FVIII) prophylaxis for severe hemophilia A (SHA) is important for long-term outcomes. This study used supervised machine learning-based predictive modeling to identify predictors of long-term ABR during prophylaxis with an extended half-life FVIII.

Methods Data were from 166 SHA patients who received N8-GP prophylaxis (50 IU/kg every 4 days) in the pathfinder 2 study. Predictive models were developed to identify variables associated with an ABR of ≤1 versus >1 during the trial's main phase (median follow-up of 469 days). Model performance was assessed using area under the receiver operator characteristic curve (AUROC). Pre-N8-GP prophylaxis models learned from data collected at baseline; post-N8-GP prophylaxis models learned from data collected up to 12-weeks postswitch to N8-GP, and predicted ABR at the end of the outcome period (final year of treatment in the main phase).

Results The predictive model using baseline variables had moderate performance (AUROC = 0.64) for predicting observed ABR. The most performant model used data collected at 12-weeks postswitch (AUROC = 0.79) with cumulative bleed count up to 12 weeks as the most informative variable, followed by baseline von Willebrand factor and mean FVIII at 30 minutes postdose. Univariate cumulative bleed count at 12 weeks performed equally well to the 12-weeks postswitch model (AUROC = 0.75). Pharmacokinetic measures were indicative, but not essential, to predict ABR.

Conclusion Cumulative bleed count up to 12-weeks postswitch was as informative as the 12-week post-switch predictive model for predicting long-term ABR, supporting alterations in prophylaxis based on treatment response.

Author Contributions

All authors made substantial contributions to the conception and design, acquisition of data, or analysis and interpretation of data; took part in drafting the article or revising it critically for important intellectual content; gave final approval of the version to be published; and agree to be accountable for all aspects of the work. The underlying data included in the analyses have been verified by A. Cooper and E. Scalfaro.


Note

Novo Nordisk is the proprietary owner of all raw data analyzed. Transformed data used for machine learning model development are available from the corresponding author, P.C., upon reasonable request and subject to approval by Novo Nordisk. Underlying data from the pathfinder 2 trial, which formed the data source for this analysis, will be shared with bona fide researchers submitting a research proposal requesting access to data. The access request proposal form and the access criteria can be found at novonordisk-trials.com. Data will be available permanently after research completion and approval of product and product use in both the European Union and United States on a specialized Statistical Analysis System data platform. The analyses available for use will be those as approved by the Independent Review Board according to the IRB Charter (see novonordisk-trials.com). Individual participant data will be shared in datasets in a de-identified/-anonymized format. In addition, the study protocol and redacted Clinical Study Report will be available according to Novo Nordisk data sharing commitments.


Supplementary Material



Publication History

Received: 16 April 2021

Accepted: 03 October 2021

Article published online:
05 December 2021

© 2021. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://creativecommons.org/licenses/by/4.0/)

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 
  • References

  • 1 Chowdary P. Extended half-life recombinant products in haemophilia clinical practice - expectations, opportunities and challenges. Thromb Res 2020; 196: 609-617
  • 2 Srivastava A, Santagostino E, Dougall A. et al. WFH guidelines for the management of hemophilia, 3rd edition. Haemophilia 2020; 26 (Suppl. 06) 1-158
  • 3 Wyrwich KW, Krishnan S, Auguste P. et al. Changes in health-related quality of life with treatment of longer-acting clotting factors: results in the A-LONG and B-LONG clinical studies. Haemophilia 2016; 22 (06) 866-872
  • 4 Valentino LA, Pipe SW, Collins PW. et al. Association of peak factor VIII levels and area under the curve with bleeding in patients with haemophilia A on every third day pharmacokinetic-guided prophylaxis. Haemophilia 2016; 22 (04) 514-520
  • 5 Albánez S, Ogiwara K, Michels A. et al. Aging and ABO blood type influence von Willebrand factor and factor VIII levels through interrelated mechanisms. J Thromb Haemost 2016; 14 (05) 953-963
  • 6 Marchesini E, Morfini M, Valentino L. Recent advances in the treatment of hemophilia: a review. Biologics 2021; 15: 221-235
  • 7 Warren BB, Thornhill D, Stein J. et al. Young adult outcomes of childhood prophylaxis for severe hemophilia A: results of the Joint Outcome Continuation Study. Blood Adv 2020; 4 (11) 2451-2459
  • 8 Konkle BA, Skinner M, Iorio A. Hemophilia trials in the twenty-first century: defining patient important outcomes. Res Pract Thromb Haemost 2019; 3 (02) 184-192
  • 9 Collins PW, Blanchette VS, Fischer K. et al; rAHF-PFM Study Group. Break-through bleeding in relation to predicted factor VIII levels in patients receiving prophylactic treatment for severe hemophilia A. J Thromb Haemost 2009; 7 (03) 413-420
  • 10 Tiede A, Abdul Karim F, Jiménez-Yuste V. et al. Factor VIII activity and bleeding risk during prophylaxis for severe hemophilia A: a population pharmacokinetic model. Haematologica 2021; 106 (07) 1902-1909
  • 11 Alexander Jr J, Edwards RA, Brodsky M. et al. Using time series analysis approaches for improved prediction of pain outcomes in subgroups of patients with painful diabetic peripheral neuropathy. PLoS One 2018; 13 (12) e0207120
  • 12 Alexander Jr J, Edwards RA, Manca L. et al. Integrating machine learning with microsimulation to classify hypothetical, novel patients for predicting pregabalin treatment response based on observational and randomized data in patients with painful diabetic peripheral neuropathy. Pragmat Obs Res 2019; 10: 67-76
  • 13 Watson JA, Holmes CC. Machine learning analysis plans for randomised controlled trials: detecting treatment effect heterogeneity with strict control of type I error. Trials 2020; 21 (01) 156
  • 14 Chowdary P, Fischer K, Collins PW. et al. Modeling to predict factor VIII levels associated with zero bleeds in patients with severe hemophilia A initiated on tertiary prophylaxis. Thromb Haemost 2020; 120 (05) 728-736
  • 15 Chowdary P, Carcao M, Holme PA. et al. Fixed doses of N8-GP prophylaxis maintain moderate-to-mild factor VIII levels in the majority of patients with severe hemophilia A. Res Pract Thromb Haemost 2019; 3 (03) 542-554
  • 16 Mahlangu J, Powell JS, Ragni MV. et al; A-LONG Investigators. Phase 3 study of recombinant factor VIII Fc fusion protein in severe hemophilia A. Blood 2014; 123 (03) 317-325
  • 17 Reding MT, Ng HJ, Poulsen LH. et al. Safety and efficacy of BAY 94-9027, a prolonged-half-life factor VIII. J Thromb Haemost 2017; 15 (03) 411-419
  • 18 Curry N, Albayrak C, Escobar M. et al. Once-weekly prophylaxis with glycoPEGylated recombinant factor VIII (N8-GP) in severe haemophilia A: safety and efficacy results from pathfinder 2 (randomized phase III trial). Haemophilia 2019; 25 (03) 373-381
  • 19 Giangrande P, Abdul Karim F, Nemes L. et al. Long-term safety and efficacy of N8-GP in previously treated adults and adolescents with hemophilia A: final results from pathfinder2. J Thromb Haemost 2020; 18 (Suppl. 01) 5-14
  • 20 Giangrande P, Andreeva T, Chowdary P. et al; Pathfinder™2 Investigators. Clinical evaluation of glycoPEGylated recombinant FVIII: efficacy and safety in severe haemophilia A. Thromb Haemost 2017; 117 (02) 252-261
  • 21 Lundberg S, Lee S-I. A unified approach to interpreting model predictions. Paper presented at: 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, California, United States. December 4–9, 2017: 1-10
  • 22 Breiman L. Random Forests. Mach Learn 2001; 45 (01) 5-32
  • 23 Molnar C. Interpretable Machine Learning. A Guide for Making Black Box Models Explainable. In: Lulu; 2019. Accessed October 10, 2021 at: https://christophm.github.io/interpretable-ml-book/
  • 24 Lalezari S, Martinowitz U, Windyga J. et al. Correlation between endogenous VWF:Ag and PK parameters and bleeding frequency in severe haemophilia A subjects during three-times-weekly prophylaxis with rFVIII-FS. Haemophilia 2014; 20 (01) e15-e22
  • 25 Tiede A, Cid AR, Goldmann G. et al. Body mass index best predicts recovery of recombinant factor VIII in underweight to obese patients with severe haemophilia A. Thromb Haemost 2020; 120 (02) 277-288
  • 26 Manco-Johnson MJ, Abshire TC, Shapiro AD. et al. Prophylaxis versus episodic treatment to prevent joint disease in boys with severe hemophilia. N Engl J Med 2007; 357 (06) 535-544
  • 27 Krishnan S, Vietri J, Furlan R, Duncan N. Adherence to prophylaxis is associated with better outcomes in moderate and severe haemophilia: results of a patient survey. Haemophilia 2015; 21 (01) 64-70
  • 28 Broderick CR, Herbert RD, Latimer J. et al. Association between physical activity and risk of bleeding in children with hemophilia. JAMA 2012; 308 (14) 1452-1459
  • 29 Booth J, Oladapo A, Walsh S. et al. Real-world comparative analysis of bleeding complications and health-related quality of life in patients with haemophilia A and haemophilia B. Haemophilia 2018; 24 (05) e322-e327
  • 30 Berntorp E, Spotts G, Patrone L, Ewenstein BM. Advancing personalized care in hemophilia A: ten years' experience with an advanced category antihemophilic factor prepared using a plasma/albumin-free method. Biologics 2014; 8: 115-127
  • 31 Iorio A. Using pharmacokinetics to individualize hemophilia therapy. Hematology (Am Soc Hematol Educ Program) 2017; 2017 (01) 595-604
  • 32 Den Uijl IE, Mauser Bunschoten EP, Roosendaal G. et al. Clinical severity of haemophilia A: does the classification of the 1950s still stand?. Haemophilia 2011; 17 (06) 849-853
  • 33 van Dijk K, Fischer K, van der Bom JG, Grobbee DE, van den Berg HM. Variability in clinical phenotype of severe haemophilia: the role of the first joint bleed. Haemophilia 2005; 11 (05) 438-443