Nonlinear mixed effect (NLME) models are the gold standard for the analysis of patient response following drug exposure. However, these types of models are complex and time-consuming to develop. There is great interest in the adoption of machine-learning methods, but most implementations cannot be reliably extrapolated to treatment strategies outside of the training data. In order to solve this problem, we propose the deep compartment model (DCM), a combination of neural networks and ordinary differential equations. Using simulated datasets of different sizes, we show that our model remains accurate when training on small data sets. Furthermore, using a real-world data set of patients with hemophilia A receiving factor VIII concentrate while undergoing surgery, we show that our model more accurately predicts a priori drug concentrations compared to a previous NLME model. In addition, we show that our model correctly describes the changing drug concentration over time. By adopting pharmacokinetic principles, the DCM allows for simulation of different treatment strategies and enables therapeutic drug monitoring.
Bibliographical noteFunding Information:
This research received funding from the Dutch Organization for Scientific Research (NWO) in the framework of the NWA‐ORC Call grant agreement NWA.1160.18.038.
The authors would like to especially thank Frank Bennis for reviewing our work. The SYMPHONY consortium, which aims to orchestrate personalized treatment in patients with bleeding disorders, is a unique collaboration among patients, healthcare professionals, and translational and fundamental researchers specializing in inherited bleeding disorders, as well as experts from multiple disciplines. It aims to identify best treatment choice for each individual based on bleeding phenotype. To achieve this goal, work packages (WP) have been organized according to three themes (e.g., Diagnostics [WPs 3 and 4], Treatment [WPs 5–9], and Fundamental Research [WPs 10–12]). This research received funding from the Netherlands Organization for Scientific Research (NWO) in the framework of the NWA-ORC Call grant agreement NWA.1160.18.038. Principal investigator: M.H. Cnossen; project manager: S.H. Reitsma. Beneficiaries of the SYMPHONY consortium: Erasmus MC and Erasmus MC Sophia Children's Hospital, University Medical Centre Rotterdam, project leadership and coordination, Sanquin Diagnostics, Sanquin Research, Amsterdam University Medical Centers, University Medical Centre Groningen, University Medical Center Utrecht, Leiden University Medical Centre, Radboud University Medical Centre, Netherlands Society of Hemophilia Patients, Netherlands Society for Thrombosis and Hemostasis, Bayer B.V., CSL Behring B.V., and Swedish Orphan Biovitrum (Belgium) BVBA/SPRL. This study was also performed as part of the OPTI-CLOT international multicenter research consortium, “Patient Tailored Pharmacokinetic (PK) Guided Dosing of Clotting Factor Concentrates and Desmopressin in Bleeding Disorders,” which is currently WP 6 within the SYMPHONY consortium. This paper is written on behalf of the international multicenter OPTI-CLOT and To WiN studies that aim to implement a PK-guided approach for the treatment of bleeding disorders using population PK models for desmopressin, factor concentrates, and other alternative drugs. OPTI-CLOT and To WiN study group members are: Steering committee: M.H. Cnossen (principal investigator and chair), F.W.G. Leebeek, Erasmus MC Sophia Children's Hospital and Erasmus MC, University Medical Centre Rotterdam, Rotterdam; R.A.A. Mathôt (co-leading investigator), K. Fijnvandraat, M. Coppens, Amsterdam University Medical Centre, Amsterdam, University Medical Centre, Amsterdam; K. Meijer, University Medical Centre Groningen, Groningen; S.E.M. Schols, Radboud University Medical Centre, Nijmegen; H.C.J. Eikenboom, Leiden University Medical Centre, Leiden; R.E.G. Schutgens, University Medical Centre Utrecht, Utrecht; E.A.M. Beckers, Maastricht University Medical Centre, Maastricht; and P. Ypma, Haga Hospital, The Hague. Principal investigators and local collaborators in the Netherlands: M.J.H.A. Kruip, S. Polinder, Erasmus MC, University Medical Centre Rotterdam, Rotterdam; R.Y.J. Tamminga, University Medical Centre Groningen, Groningen; P. Brons, Radboud University Medical Centre, Nijmegen; K. Fischer, K.P.M. van Galen, University Medical Centre Utrecht, Utrecht; F.C.J.I. Heubel-Moenen, Maastricht University Medical Centre, Maastricht; L. Nieuwenhuizen, Maxima Medical Centre, Eindhoven; M.H.E. Driessens, The Netherlands Hemophilia Patient Society; I. van Vliet, Erasmus MC, University Medical Centre Rotterdam, Rotterdam. OPTI-CLOT/To WiNs: J. Lock, H.C.A.M. Hazendonk, I. van Moort, J.M. Heijdra, M.H.J. Goedhart, W. Al Arashi, Erasmus MC, University Medical Centre Rotterdam, Rotterdam; T. Preijers, N.C.B. de Jager, L.H. Bukkems, M.E. Cloesmeijer, A. Janssen, Amsterdam University Medical Centers, Amsterdam. Principal investigators and local collaborators in the United Kingdom—P.W. Collins, Arthur Bloom Hemophilia Centre, Institute of Infection and Immunity, School of Medicine, Cardiff University, Cardiff; R. Liesner, Great Ormond Street Hemophilia Centre, Great Ormond Street Hospital for Children NHS Trust, London; P. Chowdary, Katharine Dormandy Hemophilia Centre and Thrombosis Unit, Royal Free London NHS Foundation Trust, London; C.M. Millar, Hammersmith Hospital-Imperial College Healthcare NHS Trust, London; D. Hart, Department of Hematology, The Royal London Hospital Barts Health NHS Trust, London; and D. Keeling, Oxford Hemophilia and Thrombosis Centre, Oxford University Hospitals, Churchill Hospital, Oxford.
© 2022 The Authors. CPT: Pharmacometrics & Systems Pharmacology published by Wiley Periodicals LLC on behalf of American Society for Clinical Pharmacology and Therapeutics.