Abstract
In population pharmacokinetic (PK) models, interindividual variability is explained by implementation of covariates in the model. The widely used forward stepwise selection method is sensitive to bias, which may lead to an incorrect inclusion of covariates. Alternatives, such as the full fixed effects model, reduce this bias but are dependent on the chosen implementation of each covariate. As the correct functional forms are unknown, this may still lead to an inaccurate selection of covariates. Machine learning (ML) techniques can potentially be used to learn the optimal functional forms for implementing covariates directly from data. A recent study suggested that using ML resulted in an improved selection of influential covariates. However, how do we select the appropriate functional form for including these covariates? In this work, we use SHapley Additive exPlanations (SHAP) to infer the relationship between covariates and PK parameters from ML models. As a case-study, we use data from 119 patients with hemophilia A receiving clotting factor VIII concentrate peri-operatively. We fit both a random forest and a XGBoost model to predict empirical Bayes estimated clearance and central volume from a base nonlinear mixed effects model. Next, we show that SHAP reveals covariate relationships which match previous findings. In addition, we can reveal subtle effects arising from combinations of covariates difficult to obtain using other methods of covariate analysis. We conclude that the proposed method can be used to extend ML-based covariate selection, and holds potential as a complete full model alternative to classical covariate analyses.
| Original language | English |
|---|---|
| Pages (from-to) | 1100-1110 |
| Number of pages | 11 |
| Journal | CPT: Pharmacometrics and Systems Pharmacology |
| Volume | 11 |
| Issue number | 8 |
| DOIs | |
| Publication status | Published - Aug 2022 |
Bibliographical note
Funding Information: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 (eg, 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 Center Rotterdam, project leadership and coordination, Sanquin Diagnostics, Sanquin Research, Amsterdam University Medical Centers, University Medical Center Groningen, University Medical Center Utrecht, Leiden University Medical Center, Radboud University Medical Center, 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 Center Rotterdam, Rotterdam; R.A.A. Mathôt (co‐leading investigator), K. Fijnvandraat, M. Coppens, Amsterdam University Medical Center, Amsterdam, University Medical Center, Amsterdam; K. Meijer, University Medical Center 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 Center Utrecht, Utrecht; E.A.M. Beckers, Maastricht University Medical Center, 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 Center 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 Center 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 Haemophilia Centre, Institute of Infection and Immunity, School of Medicine, Cardiff University, Cardiff; R. Liesner, Great Ormond Street Haemophilia 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 Haematology, The Royal London Hospital Barts Health NHS Trust, London; and D. Keeling, Oxford Haemophilia and Thrombosis Centre, Oxford University Hospitals, Churchill Hospital, Oxford.
Funding 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 †
Funding Information:
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 (eg, 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 Center Rotterdam, project leadership and coordination, Sanquin Diagnostics, Sanquin Research, Amsterdam University Medical Centers, University Medical Center Groningen, University Medical Center Utrecht, Leiden University Medical Center, Radboud University Medical Center, 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 Center Rotterdam, Rotterdam; R.A.A. Mathôt (co-leading investigator), K. Fijnvandraat, M. Coppens, Amsterdam University Medical Center, Amsterdam, University Medical Center, Amsterdam; K. Meijer, University Medical Center 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 Center Utrecht, Utrecht; E.A.M. Beckers, Maastricht University Medical Center, 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 Center 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 Center 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 Haemophilia Centre, Institute of Infection and Immunity, School of Medicine, Cardiff University, Cardiff; R. Liesner, Great Ormond Street Haemophilia 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 Haematology, The Royal London Hospital Barts Health NHS Trust, London; and D. Keeling, Oxford Haemophilia and Thrombosis Centre, Oxford University Hospitals, Churchill Hospital, Oxford.
Publisher Copyright:
© 2022 The Authors. CPT: Pharmacometrics & Systems Pharmacology published by Wiley Periodicals LLC on behalf of American Society for Clinical Pharmacology and Therapeutics.