Maximilian Pilz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Maximilian Pilz has a total of 274 co-authors. Here are the top co-authors by number of shared publications:
- Meinhard Kieser
Institute of Medical Biometry University of Heidelberg Heidelberg Germany
16 shared publications - Carolin Herrmann
Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Institute of Biometry and Clinical Epidemiology, Berlin, Germany
8 shared publications - Geraldine Rauch
Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Institute of Biometry and Clinical Epidemiology, Berlin, Germany
8 shared publications Jürgen Hoffmann
University of Heidelberg, Department of Oral and Maxillofacial Surgery, Im Neuenheimer Feld 400, Heidelberg, D-69120, Germany
7 shared publications- Oliver Ristow
Klinik und Poliklinik für Mund‑, Kiefer- und Gesichtschirurgie, Universitätsklinikum Heidelberg, Heidelberg, Deutschland
6 shared publications - Thomas Rückschloß
University of Heidelberg, Department of Oral and Maxillofacial Surgery, Im Neuenheimer Feld 400, Heidelberg, D-69120, Germany
6 shared publications
Latest Publications
- Open Access
- 10 October 2026
- Published by Springer Nature in Health Care Management Science
- Vol. 29 (4) , 50
Prototyping and evaluation of a clinical decision support system in long-term care in German nursing homes
Demographic change in Germany is increasing the demand for professional long-term care. Given rising requirements and simultaneous staff shortages, the need for digital systems is growing to effectively support nursing staff and mitigate staffing bottlenecks. This article introduces a hybrid clinical decision support system (CDSS) designed to generate actionable intervention recommendations by combining structured data and narrative nursing documentation. The CDSS consists of three interacting components: (1) knowledge models that encode state-of-the-art nursing knowledge, (2) a rule-based expert system that applies these models to generate individualized nursing interventions within the application fields mobility and pain management, and (3) a large language model (LLM) that extracts indicators that are necessary for knowledge-based decision-making from free-text entries to fill documentation gaps. A prototype was implemented and descriptively evaluated in two German nursing homes. Overall, 72% of the CDSS recommendations were rated as “correct” by nursing professionals, meaning appropriate for the care situation. In a separate evaluation, the LLM achieved 76% agreement rate in extracting care-relevant information from narratives. These results suggest that a hybrid architecture integrating expert knowledge, rule-based logic, and language models may have the potential to enhance nursing planning in long-term care settings.
- 10 October 2026
- Published by Springer Nature in Health Care Management Science
- Vol. 29 (4) , 50
Open AccessPrototyping and evaluation of a clinical decision support system in long-term care in German nursing homes
Demographic change in Germany is increasing the demand for professional long-term care. Given rising requirements and simultaneous staff shortages, the need for digital systems is growing to effectively support nursing staff and mitigate staffing bottlenecks. This article introduces a hybrid clinical decision support system (CDSS) designed to generate actionable intervention recommendations by combining structured data and narrative nursing documentation. The CDSS consists of three interacting components: (1) knowledge models that encode state-of-the-art nursing knowledge, (2) a rule-based expert system that applies these models to generate individualized nursing interventions within the application fields mobility and pain management, and (3) a large language model (LLM) that extracts indicators that are necessary for knowledge-based decision-making from free-text entries to fill documentation gaps. A prototype was implemented and descriptively evaluated in two German nursing homes. Overall, 72% of the CDSS recommendations were rated as “correct” by nursing professionals, meaning appropriate for the care situation. In a separate evaluation, the LLM achieved 76% agreement rate in extracting care-relevant information from narratives. These results suggest that a hybrid architecture integrating expert knowledge, rule-based logic, and language models may have the potential to enhance nursing planning in long-term care settings.
- Open Access
- 29 September 2026
- Published by Wiley in Pharmaceutical Statistics
- Vol. 25 (6) , e70129
A Practical Guide to Optimal Adaptive Two‐Stage Designs for Various Endpoint Types
Adaptive designs are frequently used to adjust sample sizes based on interim data, ensuring reliable conclusions while protecting resources. To maximize trial efficiency, design parameters can be optimized to minimize an objective function (e.g., the expected sample size) while rigorously controlling overall error rates or further operating characteristics. However, existing methodological guidance for optimal adaptive designs mainly focuses on normally distributed data or discrete optimizations for binary data, leaving a limited practical framework to practitioners who work with other common endpoint types. We address this by demonstrating how the asymptotic normal approximations of standard test statistics enable the optimization framework to be systematically applied across diverse endpoint types, including binary and time‐to‐event data. Furthermore, we highlight critical pitfalls in using optimal adaptive designs for two‐sided testing. The results demonstrate that optimizing design parameters can substantially decrease expected sample sizes and improve conditional power compared to standard group‐sequential designs. Using this guidance, we aim to enable researchers to efficiently plan clinical trials in a broad spectrum of clinical settings, a factor that is especially crucial in rare disease research where only limited patient populations are available.
- 29 September 2026
- Published by Wiley in Pharmaceutical Statistics
- Vol. 25 (6) , e70129
Open AccessA Practical Guide to Optimal Adaptive Two‐Stage Designs for Various Endpoint Types
Adaptive designs are frequently used to adjust sample sizes based on interim data, ensuring reliable conclusions while protecting resources. To maximize trial efficiency, design parameters can be optimized to minimize an objective function (e.g., the expected sample size) while rigorously controlling overall error rates or further operating characteristics. However, existing methodological guidance for optimal adaptive designs mainly focuses on normally distributed data or discrete optimizations for binary data, leaving a limited practical framework to practitioners who work with other common endpoint types. We address this by demonstrating how the asymptotic normal approximations of standard test statistics enable the optimization framework to be systematically applied across diverse endpoint types, including binary and time‐to‐event data. Furthermore, we highlight critical pitfalls in using optimal adaptive designs for two‐sided testing. The results demonstrate that optimizing design parameters can substantially decrease expected sample sizes and improve conditional power compared to standard group‐sequential designs. Using this guidance, we aim to enable researchers to efficiently plan clinical trials in a broad spectrum of clinical settings, a factor that is especially crucial in rare disease research where only limited patient populations are available.
- Open Access
- 4 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8808
Statistical Methods for Assessing Diagnostic Agreement
With the rise of artificial intelligence (AI), an increasing number of AI-based diagnostic tools are being developed. Before clinical implementation, these tools must be validated against existing gold standards. This requires trials that quantify the agreement between AI predictions and reference measurements. However, designing such agreement studies poses methodological challenges that differ substantially from classical superiority trials. This paper aims to provide statistical methods for assessing diagnostic agreement. Methods were categorized according to the measurement scale of the data (nominal, ordinal, continuous)—with a separate group for methods that apply across several scales—and according to the number of raters or measurements involved. A decision tree is provided as a simplified educational framework for method selection rather than as a general method-selection algorithm: design features such as repeated measurements, clustering, spectrum effects, dependence between raters, and an imperfect reference method are not encoded in it and are discussed separately, together with the circularity and confounding issues specific to the validation of AI-based tools. For each method, we summarized assumptions, appropriate use cases, interpretation of results, and available open-source software for sample size calculation and analysis, and we illustrate the sample size calculations in three fully worked examples covering binary, ordinal, and continuous outcomes. We further distinguish conditional inference about one fixed, frozen model version from the broader generalization to a class of algorithms or to future model versions, which require additional sources of algorithmic and dataset variability to be represented in the design and analysis. We conclude by outlining open methodological questions—including Bayesian approaches to agreement estimation, methods for complex AI outputs, agreement models for clustered and repeated-measures designs, and the limited software support for Gwet’s AC1/AC2 sample size planning—that warrant further work as diagnostic technologies and statistical methodology continue to evolve.
- 4 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8808
Open AccessStatistical Methods for Assessing Diagnostic Agreement
With the rise of artificial intelligence (AI), an increasing number of AI-based diagnostic tools are being developed. Before clinical implementation, these tools must be validated against existing gold standards. This requires trials that quantify the agreement between AI predictions and reference measurements. However, designing such agreement studies poses methodological challenges that differ substantially from classical superiority trials. This paper aims to provide statistical methods for assessing diagnostic agreement. Methods were categorized according to the measurement scale of the data (nominal, ordinal, continuous)—with a separate group for methods that apply across several scales—and according to the number of raters or measurements involved. A decision tree is provided as a simplified educational framework for method selection rather than as a general method-selection algorithm: design features such as repeated measurements, clustering, spectrum effects, dependence between raters, and an imperfect reference method are not encoded in it and are discussed separately, together with the circularity and confounding issues specific to the validation of AI-based tools. For each method, we summarized assumptions, appropriate use cases, interpretation of results, and available open-source software for sample size calculation and analysis, and we illustrate the sample size calculations in three fully worked examples covering binary, ordinal, and continuous outcomes. We further distinguish conditional inference about one fixed, frozen model version from the broader generalization to a class of algorithms or to future model versions, which require additional sources of algorithmic and dataset variability to be represented in the design and analysis. We conclude by outlining open methodological questions—including Bayesian approaches to agreement estimation, methods for complex AI outputs, agreement models for clustered and repeated-measures designs, and the limited software support for Gwet’s AC1/AC2 sample size planning—that warrant further work as diagnostic technologies and statistical methodology continue to evolve.
- Open Access
- 12 August 2026
- Published by Springer Nature in Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine
- Vol. 34 (1) , 134
Effect of an app-guided advanced cardiac life support algorithm on teamwork, non-technical skills, and workload in simulated in-hospital cardiac arrest: a randomized controlled feasibility trial
- 12 August 2026
- Published by Springer Nature in Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine
- Vol. 34 (1) , 134
Open AccessEffect of an app-guided advanced cardiac life support algorithm on teamwork, non-technical skills, and workload in simulated in-hospital cardiac arrest: a randomized controlled feasibility trial
- Open Access
- 20 May 2026
- Published by Elsevier in Journal of Cranio-Maxillofacial Surgery
- Vol. 54 (8) , 104606
Primary versus secondary microvascular bony jaw reconstruction in patients with oral squamous cell carcinoma and adjuvant therapy – a retrospective cohort study
- 20 May 2026
- Published by Elsevier in Journal of Cranio-Maxillofacial Surgery
- Vol. 54 (8) , 104606
Open AccessPrimary versus secondary microvascular bony jaw reconstruction in patients with oral squamous cell carcinoma and adjuvant therapy – a retrospective cohort study
- Open Access
- 18 October 2025
- Published by Springer Nature in BMC Cancer
- Vol. 25 (1) , 1-21
Digital and AI-assisted multimodal supportive care, combining physical activity, nutrition, and pain management during chemotherapy for advanced pancreatic cancer patients: study protocol of the European multicenter randomized controlled trial of the RELEVIUM project
Background: Multimodal care, including nutritional support, physical exercise, and pain management, is essential to address complex therapeutic challenges in advanced pancreatic cancer. There is an increasing prevalence worldwide in pancreatic cancer and the disease is often diagnosed late leading to limited treatment options and poor prognosis. Advanced pancreatic cancer patients experience a wide range of adverse symptoms that affect their quality of life and require comprehensive and interdisciplinary patient care early in treatment. Integrating digital health, particularly through remote monitoring, plays a vital role in addressing the therapeutic challenges and improving data-driven clinical decision-making. Therefore, the European project RELEVIUM examines the effect of a personalized, digitally assisted multimodal supportive care intervention on health-related quality of life in patients with pancreatic cancer aiming to improve early access to multidisciplinary, cost-effective palliative care. Methods: In cancer centers in Estonia, Israel, and Germany, 132 patients will be randomly assigned in the prospective randomized controlled trial RELEVIUM-RCT into two groups. Both groups receive standard chemotherapy. The control group follows usual care, while the intervention group receives personalized, digitally assisted multimodal support integrated into usual care. The intervention includes guidance and monitoring on pain, nutrition, fatigue, sarcopenia, and physical activity. Patients track their physical activities, nutritional behavior and rate pain and fatigue daily via a smartwatch and mobile app. The physician analyses these longitudinal data on a dashboard and counsels the patients every two weeks during clinical visits, assisted by an interdisciplinary team and digital support system. The primary endpoint of the study is health-related quality of life including factors such as time until a definitive deterioration in selected dimensions (physical functioning and/or appetite loss) assessed at 8 weeks. Secondary endpoints include longitudinal analyses of efficacy related to pain, physical function, nutrition, sarcopenia, and socioeconomic factors. Discussion: The RELEVIUM-RCT investigates the efficacy of digital health support for individuals with advanced pancreatic cancer in conjunction with conventional treatments in three European countries. Longitudinal data on the interplay of chemotherapy toxicity, fatigue, pain, physical activity, and nutrition will provide valuable extended insights on multimodal pancreatic cancer care. Moreover, this data can help demonstrate the benefits of digital health in clinical decision-making, ultimately contributing to improved quality of care in Europe. Trial registration: Registry: German Clinical Trials Register; Registration number: DRKS00037143; Date of registration: 5th of June 2025. Graphical
- 18 October 2025
- Published by Springer Nature in BMC Cancer
- Vol. 25 (1) , 1-21
Open AccessDigital and AI-assisted multimodal supportive care, combining physical activity, nutrition, and pain management during chemotherapy for advanced pancreatic cancer patients: study protocol of the European multicenter randomized controlled trial of the RELEVIUM project
Background: Multimodal care, including nutritional support, physical exercise, and pain management, is essential to address complex therapeutic challenges in advanced pancreatic cancer. There is an increasing prevalence worldwide in pancreatic cancer and the disease is often diagnosed late leading to limited treatment options and poor prognosis. Advanced pancreatic cancer patients experience a wide range of adverse symptoms that affect their quality of life and require comprehensive and interdisciplinary patient care early in treatment. Integrating digital health, particularly through remote monitoring, plays a vital role in addressing the therapeutic challenges and improving data-driven clinical decision-making. Therefore, the European project RELEVIUM examines the effect of a personalized, digitally assisted multimodal supportive care intervention on health-related quality of life in patients with pancreatic cancer aiming to improve early access to multidisciplinary, cost-effective palliative care. Methods: In cancer centers in Estonia, Israel, and Germany, 132 patients will be randomly assigned in the prospective randomized controlled trial RELEVIUM-RCT into two groups. Both groups receive standard chemotherapy. The control group follows usual care, while the intervention group receives personalized, digitally assisted multimodal support integrated into usual care. The intervention includes guidance and monitoring on pain, nutrition, fatigue, sarcopenia, and physical activity. Patients track their physical activities, nutritional behavior and rate pain and fatigue daily via a smartwatch and mobile app. The physician analyses these longitudinal data on a dashboard and counsels the patients every two weeks during clinical visits, assisted by an interdisciplinary team and digital support system. The primary endpoint of the study is health-related quality of life including factors such as time until a definitive deterioration in selected dimensions (physical functioning and/or appetite loss) assessed at 8 weeks. Secondary endpoints include longitudinal analyses of efficacy related to pain, physical function, nutrition, sarcopenia, and socioeconomic factors. Discussion: The RELEVIUM-RCT investigates the efficacy of digital health support for individuals with advanced pancreatic cancer in conjunction with conventional treatments in three European countries. Longitudinal data on the interplay of chemotherapy toxicity, fatigue, pain, physical activity, and nutrition will provide valuable extended insights on multimodal pancreatic cancer care. Moreover, this data can help demonstrate the benefits of digital health in clinical decision-making, ultimately contributing to improved quality of care in Europe. Trial registration: Registry: German Clinical Trials Register; Registration number: DRKS00037143; Date of registration: 5th of June 2025. Graphical
- Open Access
- 26 January 2025
- Published by Wiley in Statistics in Medicine
- Vol. 44 (3-4) , e10294
Comments on “Sample Size Adaptation Designs and Efficiency Comparison With Group Sequential Designs”
- 26 January 2025
- Published by Wiley in Statistics in Medicine
- Vol. 44 (3-4) , e10294
Open AccessComments on “Sample Size Adaptation Designs and Efficiency Comparison With Group Sequential Designs”
- Open Access
- 1 November 2024
- Published by Springer Nature in Systematic Reviews
- Vol. 13 (1) , 1-14
Semi-automated title-abstract screening using natural language processing and machine learning
Background: Title-abstract screening in the preparation of a systematic review is a time-consuming task. Modern techniques of natural language processing and machine learning might allow partly automatization of title-abstract screening. In particular, clear guidance on how to proceed with these techniques in practice is of high relevance. Methods: This paper presents an entire pipeline how to use natural language processing techniques to make the titles and abstracts usable for machine learning and how to apply machine learning algorithms to adequately predict whether or not a publication should be forwarded to full text screening. Guidance for the practical use of the methodology is given. Results: The appealing performance of the approach is demonstrated by means of two real-world systematic reviews with meta analysis. Conclusions: Natural language processing and machine learning can help to semi-automatize title-abstract screening. Different project-specific considerations have to be made for applying them in practice.
- 1 November 2024
- Published by Springer Nature in Systematic Reviews
- Vol. 13 (1) , 1-14
Open AccessSemi-automated title-abstract screening using natural language processing and machine learning
Background: Title-abstract screening in the preparation of a systematic review is a time-consuming task. Modern techniques of natural language processing and machine learning might allow partly automatization of title-abstract screening. In particular, clear guidance on how to proceed with these techniques in practice is of high relevance. Methods: This paper presents an entire pipeline how to use natural language processing techniques to make the titles and abstracts usable for machine learning and how to apply machine learning algorithms to adequately predict whether or not a publication should be forwarded to full text screening. Guidance for the practical use of the methodology is given. Results: The appealing performance of the approach is demonstrated by means of two real-world systematic reviews with meta analysis. Conclusions: Natural language processing and machine learning can help to semi-automatize title-abstract screening. Different project-specific considerations have to be made for applying them in practice.
- 23 May 2024
- Published by The R Foundation
MetaNLP: Natural Language Processing for Meta Analysis
- Open Access
- 3 May 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-10
Statistical analysis of three data sources for Covid-19 monitoring in Rhineland-Palatinate, Germany
In Rhineland-Palatinate, Germany, a system of three data sources has been established to track the Covid-19 pandemic. These sources are the number of Covid-19-related hospitalizations, the Covid-19 genecopies in wastewater, and the prevalence derived from a cohort study. This paper presents an extensive comparison of these parameters. It is investigated whether wastewater data and a cohort study can be valid surrogate parameters for the number of hospitalizations and thus serve as predictors for coming Covid-19 waves. We observe that this is possible in general for the cohort study prevalence, while the wastewater data suffer from a too large variability to make quantitative predictions by a purely data-driven approach. However, the wastewater data and the cohort study prevalence are able to detect hospitalizations waves in a qualitative manner. Furthermore, a detailed comparison of different normalization techniques of wastewater data is provided.
- 3 May 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-10
Open AccessStatistical analysis of three data sources for Covid-19 monitoring in Rhineland-Palatinate, Germany
In Rhineland-Palatinate, Germany, a system of three data sources has been established to track the Covid-19 pandemic. These sources are the number of Covid-19-related hospitalizations, the Covid-19 genecopies in wastewater, and the prevalence derived from a cohort study. This paper presents an extensive comparison of these parameters. It is investigated whether wastewater data and a cohort study can be valid surrogate parameters for the number of hospitalizations and thus serve as predictors for coming Covid-19 waves. We observe that this is possible in general for the cohort study prevalence, while the wastewater data suffer from a too large variability to make quantitative predictions by a purely data-driven approach. However, the wastewater data and the cohort study prevalence are able to detect hospitalizations waves in a qualitative manner. Furthermore, a detailed comparison of different normalization techniques of wastewater data is provided.