Background

Aniek is currently pursuing a PhD at the department of Medical Informatics where she investigates how different types of explanations can help to overcome the transparency problem of AI in health care. More generally, research interests include explainable AI, causality, and methods research to support the trustworthy implementation of AI in clinical practice. Aniek is actively contributing to EHDEN/OHDSI and co-lead of the the OHDSI NL chapter.

Previously she obtained two bachelors in Econometrics and Economics (2017) and a master Business Analytics and Quantitative Marketing (2019) from Erasmus University Rotterdam. She wrote her master thesis on the causal effects of binary, continuous and multivariate treatments using propensity score methods. She worked as a research assistant at the Erasmus School of Health Policy and Management, where she investigated ethnic inequalities in deceased donor kidney allocation and the productivity of Dutch hospitals.

Publications

Jacqueline Höllig*, Aniek F. Markus*, Jef de Slegte, Prachi Bagave. [accepted for publication in xAI 2023]. Semantic Meaningfulness: Evaluating Counterfactual Approaches for Real-World Plausibility and Feasibility. 

Markus, A. F., Fridgeirsson, E. A., Kors, J. A., Verhamme, K. M., & Rijnbeek, P. R. (2023). Challenges of Estimating Global Feature Importance in Real-World Health Care Data. Studies in Health Technology and Informatics, 1057-1061. https://doi.org/10.3233/shti230346.

Markus, A. F., Strauss, V. Y., Burn, E., Li, X., Delmestri, A., Reich, C., ... & Jödicke, A. M. (2023). Characterising the treatment of thromboembolic events after COVID-19 vaccination in 4 European countries and the US: An international network cohort study. Frontiers in Pharmacology, 14, 1118203. https://doi.org/10.3389/fphar.2023.1118203.

Markus, A. F., Rijnbeek, P. R., & Reps. J. M. (2022). Why predicting risk can’t identify ‘risk factors’: empirical assessment of model stability in machine learning across observational health databases. In Machine Learning for Healthcare 2022 (pp.1-25). PMLR. (links to full text and video).

Markus, A. F., Verhamme, K. M., Kors, J. A., & Rijnbeek, P. R. (2022). TreatmentPatterns: An R package to facilitate the standardized development and analysis of treatment patterns across disease domains. Computer Methods and Programs in Biomedicine, 107081. https://doi.org/10.1016/j.cmpb.2022.107081

Dohmen, P., van Ineveld, M., Markus, A., van der Hagen, L., & van de Klundert, J. (2022). Does competition improve hospital performance: a DEA based evaluation from the Netherlands. The European Journal of Health Economics, 1-19. https://doi.org/10.1007/s10198-022-01529-8

Markus, A. F., Kors, J. A., & Rijnbeek, P. R. (2021). The role of explainability in creating trustworthy artificial intelligence for health care: A comprehensive survey of the terminology, design choices, and evaluation strategies. Journal of Biomedical Informatics, 113, 103655. https://doi.org/10.1016/j.jbi.2020.103655

Van de Klundert, J., van der Hagen, L., & Markus, A. (2021). Eliminating Transplant Waiting Time Inequities-with an application to Kidney Allocation in the USA. European Journal of Operational Research. https://doi.org/10.1016/j.ejor.2021.09.033

Williams, R. D.*, Markus, A. F.*, Yang, C., Duarte Salles, T., Falconer, T., Jonnagaddala, J., . . . Rijnbeek, P. R. (2020). Seek COVER: using a disease proxy to rapidly develop and validate a personalized risk calculator for COVID-19 outcomes in an international network. BMC Medical Research Methodology, 22(1), 35. https://doi.org/10.1186/s12874-022-01505-z

Presentations

• Medical Informatics Europe 2023: Challenges of Estimating Global Feature Importance in Real-World Health Care Data.

• Machine Learning for Healthcare 2022 & OHDSI Europe Symposium 2022: Why predicting risk can’t identify ‘risk factors’: empirical assessment of model stability in machine learning across observational health databases

• BeRS-GSK Clinical Science Awards in Pulmonology: real-world treatment patterns of newly diagnosed asthma patients

Poster presentations 

• Understanding the Size of the Feature Importance Disagreement Problem in Real-World Data (ICML Workshop 2023 - IMLH)

Authors: Aniek F. Markus, Egill A. Fridgeirsson, Jan A. Kors, Katia M.C. Verhamme, Jenna M. Reps, Peter R. Rijnbeek

https://openreview.net/forum?id=FKjFUEV63f

• Semantic Meaningfulness: Evaluating Counterfactual Approaches for Real-World Plausibility and Feasibility

  (ICML Workshop 2023 - Counterfactuals in Minds & Machines)

Authors: Aniek F. Markus*, Jacqueline Höllig*, Jef de Slegte, Prachi Bagave

https://drive.google.com/file/d/1tD6nLdQQzvE64ktEwswi1kMSnT6rPKuQ/view

• Explaining patient-level prediction models using permutation feature importance and SHAP (OHDSI 2022 Global Symposium)

Authors: Aniek F. Markus, Egill A. Fridgeirsson, Jan A. Kors, Katia M.C. Verhamme, Peter R. Rijnbeek

https://www.ohdsi.org/2022showcase-74/

• Treatment Patterns: An R package to analyze treatment patterns of a study population of interest (OHDSI 2021 Global Symposium)

Authors: Aniek F. Markus, Peter R. Rijnbeek, Jan A. Kors, Katia Verhamme

https://www.ohdsi.org/2021-global-symposium-showcase-70/

• Learning under constraints with EXPLORE (OHDSI 2021 Global Symposium)

Authors: Aniek F. Markus, Jan A. Kors, Peter R. Rijnbeek

https://www.ohdsi.org/2021-global-symposium-showcase-49/

• Real-world treatment patterns of newly diagnosed patients with asthma and/or COPD (ERS International Congress 2021, ICPE 2021) 

Authors: Aniek Markus, Peter Rijnbeek, Jan Kors, Guy Brusselle, Ed Burn, Daniel Prieto-Alhambra, Katia Verhamme

https://www.emjreviews.com/real-world-treatment-patterns-of-newly-diagnosed-patients-with-asthma-and-or-chronic-obstructive-pulmonary-disease-j160121/

• Real-world treatment patterns of newly diagnosed asthma patients (OHDSI 2020 Global Symposium)

Authors: Aniek Markus, Peter Rijnbeek, Jan Kors, Guy Brusselle, Katia Verhamme

https://www.ohdsi.org/2020-global-symposium-showcase-92/