Leonie Schürmeyer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Leonie Schürmeyer has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Kirsten Schorning
Department of Statistics, TU Dortmund University, Dortmund, Germany
3 shared publications - Jan Georg Hengstler
Department of Toxicology, Faculty of Chemistry, TU Dortmund, 44227 Dortmund, Germany
2 shared publications - Jörg Rahnenführer
Department of Statistics, TU Dortmund University, Dortmund, Germany
2 shared publications - Tim Brecklinghaus
Department of Toxicology, Leibniz Research Centre for Working Environment and Human Factors (IfADo), Dortmund, Germany
2 shared publications - Wiebke Albrecht
Leibniz Research Centre for Working Environment and Human Factors at the Technical University of Dortmund (IfADo), Dortmund, Germany
2 shared publications Bernd‐Wolfgang Igl
Global Experimental Medicine, Data and Analytics Boehringer Ingelheim Pharma GmbH & Co. KG Baden‐Wuerttemberg Germany
1 shared publication
Latest Publications
- Open Access
- 28 September 2026
- Published by Wiley in Biometrical Journal
- Vol. 68 (5) , e70186
Optimal Designs for Identifying Effective Doses in Drug Combination Studies
We consider the optimal design problem for identifying effective dose combinations within drug combination studies where the effect of the combination of two drugs is investigated. Drug combination studies are becoming increasingly important as they investigate potential interaction effects rather than the individual impacts of the drugs. In this situation, identifying effective dose combinations that yield a prespecified effect is of special interest. If nonlinear surface models are used to describe the dose combination–response relationship, these effective dose combinations, also called isoboles, result in specific contour lines of the fitted response model. Consequently, accurately estimating these effective dose combinations is crucial. We propose a novel design criterion that targets the precise estimation of these effective dose combinations. In particular, an optimal design minimizes the width of the confidence band of the contour lines of interest. Optimal design theory is developed for this problem, including equivalence theorems and efficiency bounds. The performance of the optimal design is illustrated in different examples modeling dose combination data by various nonlinear surface models. It is demonstrated that the proposed optimal design for identifying effective dose combinations yields a more precise estimation of the effective dose combinations than ray or factorial designs, which are commonly used in practice. This particularly holds true for a case study motivated by data from an oncological dose combination study.
- 28 September 2026
- Published by Wiley in Biometrical Journal
- Vol. 68 (5) , e70186
Open AccessOptimal Designs for Identifying Effective Doses in Drug Combination Studies
We consider the optimal design problem for identifying effective dose combinations within drug combination studies where the effect of the combination of two drugs is investigated. Drug combination studies are becoming increasingly important as they investigate potential interaction effects rather than the individual impacts of the drugs. In this situation, identifying effective dose combinations that yield a prespecified effect is of special interest. If nonlinear surface models are used to describe the dose combination–response relationship, these effective dose combinations, also called isoboles, result in specific contour lines of the fitted response model. Consequently, accurately estimating these effective dose combinations is crucial. We propose a novel design criterion that targets the precise estimation of these effective dose combinations. In particular, an optimal design minimizes the width of the confidence band of the contour lines of interest. Optimal design theory is developed for this problem, including equivalence theorems and efficiency bounds. The performance of the optimal design is illustrated in different examples modeling dose combination data by various nonlinear surface models. It is demonstrated that the proposed optimal design for identifying effective dose combinations yields a more precise estimation of the effective dose combinations than ray or factorial designs, which are commonly used in practice. This particularly holds true for a case study motivated by data from an oncological dose combination study.
- Open Access
- 19 August 2025
- Published by Springer Nature in Archives of Toxicology
- Vol. 99 (11) , 4439-4454
Adjustment for day-to-day variability in the estimation of effective concentrations for the assessment of mixture toxicity
Humans are exposed to a multitude of substances at the same time; thus, toxicity assessment for mixtures of several substances and not only for the individual substances is critical. An important challenge in testing the mixture effects of many substances in vitro is the variability between individual experiments, also named ‘day-to-day variability’. Two steps, each consisting of independent experiments, are needed when mixtures are tested. In the first experimental step, for each substance, the concentration–response relationship is usually measured with 6–10 concentrations for at least 3 experiments, and EC20 values, i.e., the concentration where a fitted curve intersects with a viability value of 80%, are determined. These values are used as reference values and in the second experimental step, the mixture of several substances is based on these individual EC20 values. Since the mixture experiments are new, independent experiments, typically conducted on different days, day-to-day variability can lead to deviations in the cytotoxicity at the reference EC20 concentration, i.e., to higher or lower observed viabilities. In this work, a procedure is proposed, how a single concentration per substance tested in the same experiment as the mixture can be used to reliably adjust for day-to-day variability. In the here-established procedure, a specific additive model denoted as ‘budget approach’ is introduced as a reference model to explore potential positive or negative interaction effects between substances.
- 19 August 2025
- Published by Springer Nature in Archives of Toxicology
- Vol. 99 (11) , 4439-4454
Open AccessAdjustment for day-to-day variability in the estimation of effective concentrations for the assessment of mixture toxicity
Humans are exposed to a multitude of substances at the same time; thus, toxicity assessment for mixtures of several substances and not only for the individual substances is critical. An important challenge in testing the mixture effects of many substances in vitro is the variability between individual experiments, also named ‘day-to-day variability’. Two steps, each consisting of independent experiments, are needed when mixtures are tested. In the first experimental step, for each substance, the concentration–response relationship is usually measured with 6–10 concentrations for at least 3 experiments, and EC20 values, i.e., the concentration where a fitted curve intersects with a viability value of 80%, are determined. These values are used as reference values and in the second experimental step, the mixture of several substances is based on these individual EC20 values. Since the mixture experiments are new, independent experiments, typically conducted on different days, day-to-day variability can lead to deviations in the cytotoxicity at the reference EC20 concentration, i.e., to higher or lower observed viabilities. In this work, a procedure is proposed, how a single concentration per substance tested in the same experiment as the mixture can be used to reliably adjust for day-to-day variability. In the here-established procedure, a specific additive model denoted as ‘budget approach’ is introduced as a reference model to explore potential positive or negative interaction effects between substances.
- Open Access
- 16 November 2024
- Published by Springer Nature in Archives of Toxicology
- Vol. 99 (1) , 357-376
Design of optimal concentrations for in vitro cytotoxicity experiments
Concentration-dependent cytotoxicity experiments are frequently used in toxicology. Although it has been reported that an adequate choice of concentrations improves the quality of the statistical inference substantially, a recent literature review of three major toxicological journals has shown that the corresponding methods are rarely used in toxicological practice. In this study the performance of different sets of concentrations, also called designs, are analyzed, while the overall goal is to promote the advantages of optimal design procedures and to present a user-friendly guideline for planning new cytotoxicity concentration-response experiments. We compare the frequently used log-equidistant design to a Bayesian design, which is constructed by methods of optimum design theory. Using both a dense data set of concentration-cytotoxicity data of valproic acid (VPA) and regular assay data of 104 substances, the performance of the different designs is analyzed in two scenarios, where detailed previous knowledge on VPA is available or not. The results show that it is critical to apply a specific design strategy to determine optimal concentrations for cytotoxicity testing. In particular, the Bayesian design technique with and without incorporating pre-existing knowledge of a specific test substance resulted in a more precise statistical inference than the other used designs. Finally, we present a guideline for upcoming experiments and an accessible user-friendly Shiny app (see http://shiny.statistik.tu-dortmund.de:8080/app/occe).
- 16 November 2024
- Published by Springer Nature in Archives of Toxicology
- Vol. 99 (1) , 357-376
Open AccessDesign of optimal concentrations for in vitro cytotoxicity experiments
Concentration-dependent cytotoxicity experiments are frequently used in toxicology. Although it has been reported that an adequate choice of concentrations improves the quality of the statistical inference substantially, a recent literature review of three major toxicological journals has shown that the corresponding methods are rarely used in toxicological practice. In this study the performance of different sets of concentrations, also called designs, are analyzed, while the overall goal is to promote the advantages of optimal design procedures and to present a user-friendly guideline for planning new cytotoxicity concentration-response experiments. We compare the frequently used log-equidistant design to a Bayesian design, which is constructed by methods of optimum design theory. Using both a dense data set of concentration-cytotoxicity data of valproic acid (VPA) and regular assay data of 104 substances, the performance of the different designs is analyzed in two scenarios, where detailed previous knowledge on VPA is available or not. The results show that it is critical to apply a specific design strategy to determine optimal concentrations for cytotoxicity testing. In particular, the Bayesian design technique with and without incorporating pre-existing knowledge of a specific test substance resulted in a more precise statistical inference than the other used designs. Finally, we present a guideline for upcoming experiments and an accessible user-friendly Shiny app (see http://shiny.statistik.tu-dortmund.de:8080/app/occe).
- Open Access
- 19 October 2023
- Published by Springer Nature in BMC Bioinformatics
- Vol. 24 (1) , 1-21
Designs for the simultaneous inference of concentration–response curves
Background: An important problem in toxicology in the context of gene expression data is the simultaneous inference of a large number of concentration–response relationships. The quality of the inference substantially depends on the choice of design of the experiments, in particular, on the set of different concentrations, at which observations are taken for the different genes under consideration. As this set has to be the same for all genes, the efficient planning of such experiments is very challenging. We address this problem by determining efficient designs for the simultaneous inference of a large number of concentration–response models. For that purpose, we both construct aD-optimality criterion for simultaneous inference and aK-means procedure which clusters the support points of the locallyD-optimal designs of the individual models.Results: We show that a planning of experiments that addresses the simultaneous inference of a large number of concentration–response relationships yields a substantially more accurate statistical analysis. In particular, we compare the performance of the constructed designs to the ones of other commonly used designs in terms ofD-efficiencies and in terms of the quality of the resulting model fits using a real data example dealing with valproic acid. For the quality comparison we perform an extensive simulation study.Conclusions: The design maximizing theD-optimality criterion for simultaneous inference improves the inference of the different concentration–response relationships substantially. The design based on theK-means procedure also performs well, whereas a log-equidistant design, which was also included in the analysis, performs poorly in terms of the quality of the simultaneous inference. Based on our findings, theD-optimal design for simultaneous inference should be used for upcoming analyses dealing with high-dimensional gene expression data.
- 19 October 2023
- Published by Springer Nature in BMC Bioinformatics
- Vol. 24 (1) , 1-21
Open AccessDesigns for the simultaneous inference of concentration–response curves
Background: An important problem in toxicology in the context of gene expression data is the simultaneous inference of a large number of concentration–response relationships. The quality of the inference substantially depends on the choice of design of the experiments, in particular, on the set of different concentrations, at which observations are taken for the different genes under consideration. As this set has to be the same for all genes, the efficient planning of such experiments is very challenging. We address this problem by determining efficient designs for the simultaneous inference of a large number of concentration–response models. For that purpose, we both construct aD-optimality criterion for simultaneous inference and aK-means procedure which clusters the support points of the locallyD-optimal designs of the individual models.Results: We show that a planning of experiments that addresses the simultaneous inference of a large number of concentration–response relationships yields a substantially more accurate statistical analysis. In particular, we compare the performance of the constructed designs to the ones of other commonly used designs in terms ofD-efficiencies and in terms of the quality of the resulting model fits using a real data example dealing with valproic acid. For the quality comparison we perform an extensive simulation study.Conclusions: The design maximizing theD-optimality criterion for simultaneous inference improves the inference of the different concentration–response relationships substantially. The design based on theK-means procedure also performs well, whereas a log-equidistant design, which was also included in the analysis, performs poorly in terms of the quality of the simultaneous inference. Based on our findings, theD-optimal design for simultaneous inference should be used for upcoming analyses dealing with high-dimensional gene expression data.