Alexander Janssen

Mr. Alexander Janssen

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 August 2022 in Pharmaceutics
Verified
Journal Article
Open access
PDF file
AJAlexander Janssen
Alexander Janssen
FBFrank C. Bennis
Frank C. Bennis
RMRon A. A. Mathôt
Ron A. A. Mathôt
Pharmacometrics is a multidisciplinary field utilizing mathematical models of physiology, pharmacology, and disease to describe and quantify the interactions between medication and patient. As these models become more and more advanced, the need for advanced data analysis tools grows. Recently, there has been much interest in the adoption of machine learning (ML) algorithms. These algorithms offer strong function approximation capabilities and might reduce the time spent on model development. However, ML tools are not yet an integral part of the pharmacometrics workflow. The goal of this work is to discuss how ML algorithms have been applied in four stages of the pharmacometrics pipeline: data preparation, hypothesis generation, predictive modelling, and model validation. We will also discuss considerations before the use of ML algorithms with respect to each topic. We conclude by summarizing applications that hold potential for adoption by pharmacometricians.

24 June 2022 in CPT: Pharmacometrics & Systems Pharmacology
Verified
Journal Article
Open access
AJAlexander Janssen
Alexander Janssen
MHMark Hoogendoorn
Mark Hoogendoorn
MCMarjon H. Cnossen
Marjon H. Cnossen
RMRon A. A. Mathôt
Ron A. A. Mathôt
TCthe OPTI‐CLOT Study Group and SYMPHONY Consortium
the OPTI‐CLOT Study Group and SYMPHONY Consortium
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.

27 May 2022 in CPT: Pharmacometrics & Systems Pharmacology
Verified
Journal Article
Open access
AJAlexander Janssen
Alexander Janssen
FLFrank W. G. Leebeek
Frank W. G. Leebeek
MCMarjon H. Cnossen
Marjon H. Cnossen
RMRon A. A. Mathôt
Ron A. A. Mathôt
TCthe OPTI‐CLOT study group and SYMPHONY consortium
the OPTI‐CLOT study group and SYMPHONY consortium
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.

19 February 2024 in Clinical Pharmacology & Therapeutics
Verified
Journal Article
Open access
AJAlexander Janssen
Alexander Janssen
LSLouk Smalbil
Louk Smalbil
FBFrank C. Bennis
Frank C. Bennis
MCMarjon H. Cnossen
Marjon H. Cnossen
RMRon A. A. Mathôt
Ron A. A. Mathôt
TCthe OPTI‐CLOT study group and SYMPHONY consortium
the OPTI‐CLOT study group and SYMPHONY consortium
In rare diseases, such as hemophilia A, the development of accurate population pharmacokinetic (PK) models is often hindered by the limited availability of data. Most PK models are specific to a single recombinant factor VIII (rFVIII) concentrate or measurement assay, and are generally unsuited for answering counterfactual (“what‐if”) queries. Ideally, data from multiple hemophilia treatment centers are combined but this is generally difficult as patient data are kept private. In this work, we utilize causal inference techniques to produce a hybrid machine learning (ML) PK model that corrects for differences between rFVIII concentrates and measurement assays. Next, we augment this model with a generative model that can simulate realistic virtual patients as well as impute missing data. This model can be shared instead of actual patient data, resolving privacy issues. The hybrid ML‐PK model was trained on chromogenic assay data of lonoctocog alfa and predictive performance was then evaluated on an external data set of patients who received octocog alfa with FVIII levels measured using the one‐stage assay. The model presented higher accuracy compared with three previous PK models developed on data similar to the external data set (root mean squared error = 14.6 IU/dL vs. mean of 17.7 IU/dL). Finally, we show that the generative model can be used to accurately impute missing data (< 18% error). In conclusion, the proposed approach introduces interesting new possibilities for model development. In the context of rare disease, the introduction of generative models facilitates sharing of synthetic data, enabling the iterative improvement of population PK models.

8 November 2025 in Journal of Thrombosis and Haemostasis
Verified
Journal Article
Open access
KZKonrad van der Zwet
Konrad van der Zwet
AVAmber D.W. de Vos
Amber D.W. de Vos
MCMarjon H. Cnossen
Marjon H. Cnossen
FHFloor C.J.I. Heubel-Moenen
Floor C.J.I. Heubel-Moenen
SSSaskia Schols
Saskia Schols
DKDavid Keeling
David Keeling
Emicizumab provides effective prophylaxis in hemophilia A (HA), but its cost puts a burden on healthcare systems. Pharmacokinetic-pharmacodynamic analyses suggest that emicizumab is effective at lower trough concentrations (Ctrough) than the mean 55 μg/ml reported on conventional dosing. Interim analysis comparing bleeding control during 6 months' of conventional emicizumab dosing versus pharmacokinetic (PK) guided dosing in participants with HA, targeting a Ctrough of 30 ± 5 μg/ml. The DosEmi study (NCT06320626) is an ongoing multicenter, open-label, crossover, Dutch trial. Eligible were participants ≥ 16 years using emicizumab for ≥12 months with good bleeding control (≤2 treated bleeds/6 months, none spontaneous). This planned interim analysis compared 6 months' bleeding on conventional dosing versus PK-guided dosing. Study continuation criteria were ≤15% decrease in the proportion without treated bleeds, maximum 2 spontaneous bleeds overall observed, and <1.0 increase in bleeds/year (ABR). In 26 participants with severe HA PK-guided dosing reduced emicizumab consumption by 39% (range 13-50%). The proportion of participants without treated bleeds was 69% during conventional versus 58% during PK-guided dosing (risk difference +11%, p= 0.254); while the proportion without joint bleeds remained stable 85% vs 88% respectively (risk difference -4%, p=0.500). ABR remained low (0.7 versus 0.9, p=0.132), including one spontaneous muscle bleed (emicizumab concentration 52.5 μg/ml). These interim-results suggest that bleeding control on PK-guided reduced dosing of emicizumab (target Ctrough 30±5 μg/mL) is similar to conventional dosing. All pre-specified criteria for study continuation and inclusion of participants <16 years were met.

26 March 2024 in Journal of Pharmacokinetics and Pharmacodynamics
Verified
Journal Article
Open access
PDF file
AJAlexander Janssen
Alexander Janssen
FBFrank C. Bennis
Frank C. Bennis
MCMarjon H. Cnossen
Marjon H. Cnossen
RMRon A. A. Mathôt
Ron A. A. Mathôt
FCfor the OPTI-CLOT Study Group and SYMPHONY Consortium
for the OPTI-CLOT Study Group and SYMPHONY Consortium
Conventional pharmacokinetic (PK) models contain several useful inductive biases guiding model convergence to more realistic predictions of drug concentrations. Implementing similar biases in standard neural networks can be challenging, but might be fundamental for model robustness and predictive performance. In this study, we build on the deep compartment model (DCM) architecture by introducing constraints that guide the model to explore more physiologically realistic solutions. Using a simulation study, we show that constraints improve robustness in sparse data settings. Additionally, predicted concentration–time curves took on more realistic shapes compared to unconstrained models. Next, we propose the use of multi-branch networks, where each covariate can be connected to specific PK parameters, to reduce the propensity of models to learn spurious effects. Another benefit of this architecture is that covariate effects are isolated, enabling model interpretability through the visualization of learned functions. We show that all models were sensitive to learning false effects when trained in the presence of unimportant covariates, indicating the importance of selecting an appropriate set of covariates to link to the PK parameters. Finally, we compared the predictive performance of the constrained models to previous relevant population PK models on a real-world data set of 69 haemophilia A patients. Here, constrained models obtained higher accuracy compared to the standard DCM, with the multi-branch network outperforming previous PK models. We conclude that physiological-based constraints can improve model robustness. We describe an interpretable architecture which aids model trust, which will be key for the adoption of machine learning-based models in clinical practice.