Martin Mücke
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
Martin Mücke has a total of 297 co-authors. Here are the top co-authors by number of shared publications:
Rupert Conrad
Department of Psychosomatic Medicine and Psychotherapy, University Hospital Bonn, Bonn, Germany
9 shared publicationsD. Emmert
Center for Rare Diseases Bonn (ZSEB), University Hospital Bonn, Bonn, Germany
8 shared publicationsJulia Sellin
Institute for Digitalization and General Medicine, Center for Rare Diseases Aachen (ZSEA), Medical Faculty, RWTH Aachen University
8 shared publications- Julia Sellin
Institute for Digitalization and General Medicine, Medical Faculty, RWTH Aachen University, Aachen, Germany
7 shared publications R. Conrad
Klinik und Poliklinik für Psychosomatische Medizin und Psychotherapie, Universitätsklinikum Bonn, Bonn, Deutschland
7 shared publicationsT. Rasche
Zentrum für Seltene Erkrankungen Bonn (ZSEB), Universitätsklinikum Bonn, Bonn, Deutschland
6 shared publications
Latest Publications
- Open Access
- 30 October 2026
- Published by Springer Nature in Orphanet Journal of Rare Diseases
Study of COVID-19 outcomes in patients with rare diseases in Germany [SCOPE-RD], part 2
Background: People with rare diseases often require continuous and specialized medical care. The COVID-19 pandemic has strained healthcare systems worldwide, but only limited data is available on its specific impact on patients with rare diseases. The aim of this study was to assess the burden of the pandemic on people with rare diseases in Germany, identify gaps in their healthcare, and provide a foundation for future strategies to support this vulnerable group during pandemics. Methods: A retrospective, representative cross-sectional analysis was conducted using statutory health insurance (SHI) claims data from approximately 4.9 million insured individuals between 2017 and 2022. Patients with rare diseases were identified based on specific ICD-10-GM codes. Results: The study presents initial results regarding mortality, disease burden, healthcare resource utilization, and healthcare costs associated with patients with rare diseases with and without SARS-CoV-2 infection. A total of 14,912 patients with rare diseases were identified, of whom 2,378 (16%) contracted COVID-19 between 2020 and 2022. Patients with COVID-19 incurred higher healthcare costs, particularly in 2020 and 2021, with average costs nearly twice as high as those without COVID-19. Healthcare resource utilization, including hospitalizations and emergency visits, was higher in the COVID-19 group. Additionally, these patients exhibited increased psychological stress and a higher need for pain medication. Conclusion: Within the analyzed cohort, patients with rare diseases who contracted COVID-19 showed higher mortality, disease burden, healthcare resource utilization, and healthcare costs than those who did not. As this descriptive analysis included no external comparator group, the findings characterize the burden of COVID-19 within the population of people with rare diseases, in the context of published data on the general population and people with chronic diseases, rather than establishing an effect specific to rare diseases in general. They nonetheless underline the vulnerability of this group and the need for tailored strategies in future pandemics.
- 30 October 2026
- Published by Springer Nature in Orphanet Journal of Rare Diseases
Open AccessStudy of COVID-19 outcomes in patients with rare diseases in Germany [SCOPE-RD], part 2
Background: People with rare diseases often require continuous and specialized medical care. The COVID-19 pandemic has strained healthcare systems worldwide, but only limited data is available on its specific impact on patients with rare diseases. The aim of this study was to assess the burden of the pandemic on people with rare diseases in Germany, identify gaps in their healthcare, and provide a foundation for future strategies to support this vulnerable group during pandemics. Methods: A retrospective, representative cross-sectional analysis was conducted using statutory health insurance (SHI) claims data from approximately 4.9 million insured individuals between 2017 and 2022. Patients with rare diseases were identified based on specific ICD-10-GM codes. Results: The study presents initial results regarding mortality, disease burden, healthcare resource utilization, and healthcare costs associated with patients with rare diseases with and without SARS-CoV-2 infection. A total of 14,912 patients with rare diseases were identified, of whom 2,378 (16%) contracted COVID-19 between 2020 and 2022. Patients with COVID-19 incurred higher healthcare costs, particularly in 2020 and 2021, with average costs nearly twice as high as those without COVID-19. Healthcare resource utilization, including hospitalizations and emergency visits, was higher in the COVID-19 group. Additionally, these patients exhibited increased psychological stress and a higher need for pain medication. Conclusion: Within the analyzed cohort, patients with rare diseases who contracted COVID-19 showed higher mortality, disease burden, healthcare resource utilization, and healthcare costs than those who did not. As this descriptive analysis included no external comparator group, the findings characterize the burden of COVID-19 within the population of people with rare diseases, in the context of published data on the general population and people with chronic diseases, rather than establishing an effect specific to rare diseases in general. They nonetheless underline the vulnerability of this group and the need for tailored strategies in future pandemics.
- Open Access
- 20 October 2026
- Published by Elsevier in SSRN Electronic Journal
Insulin Dose–ResponseAlignment for Glucose Forecasting in Type 1 Diabetes
Supervised models trained on observational clinical logs often learn spurious correlations. Held-out prediction error can remain low while the fitted mapping contradicts expected pharmacology, such as predicting that insulin raises glucose. A dose–response curve (DRC) defines expected physiological behaviour when a treatment dose is varied while holding other factors fixed. In a fitted model, this response is an individual conditional expectation (ICE). Existing explainable artificial intelligence methods can diagnose an unphysiological ICE but cannot repair it. We introduce DOCAS (dose–response curve alignment via synthetic augmentation). Given a target DRC, DOCAS adds synthetic do(·) instances labelled with the curve's incremental effect and trains the chosen architecture once on the combined data. Alignment error (AE) is the root-mean-square gap between each test-context ICE and the target DRC. In type 1 diabetes glucose forecasting, the established UVa/Padova simulator supplies the insulin DRC that we use as the target. Across OhioT1DM (n = 12) and AZT1D (n = 24), DOCAS reduced the 60-minute AE from 38.13 to 2.79 mg/dL and from 49.30 to 4.13 mg/dL, respectively (89–93% across horizons), at RMSE increases of 2.7–4.4%. In an in-silico decision-support evaluation, an aligned model raised the mean correction bolus from 1.09 to 2.23 U and post-decision time in range from 73.61% to 76.01% without inducing hypoglycaemia under an explicit safety guard. These results indicate that aligning the treatment response is as important as minimizing prediction error when a forecaster is used for dosing decisions.
- 20 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessInsulin Dose–ResponseAlignment for Glucose Forecasting in Type 1 Diabetes
Supervised models trained on observational clinical logs often learn spurious correlations. Held-out prediction error can remain low while the fitted mapping contradicts expected pharmacology, such as predicting that insulin raises glucose. A dose–response curve (DRC) defines expected physiological behaviour when a treatment dose is varied while holding other factors fixed. In a fitted model, this response is an individual conditional expectation (ICE). Existing explainable artificial intelligence methods can diagnose an unphysiological ICE but cannot repair it. We introduce DOCAS (dose–response curve alignment via synthetic augmentation). Given a target DRC, DOCAS adds synthetic do(·) instances labelled with the curve's incremental effect and trains the chosen architecture once on the combined data. Alignment error (AE) is the root-mean-square gap between each test-context ICE and the target DRC. In type 1 diabetes glucose forecasting, the established UVa/Padova simulator supplies the insulin DRC that we use as the target. Across OhioT1DM (n = 12) and AZT1D (n = 24), DOCAS reduced the 60-minute AE from 38.13 to 2.79 mg/dL and from 49.30 to 4.13 mg/dL, respectively (89–93% across horizons), at RMSE increases of 2.7–4.4%. In an in-silico decision-support evaluation, an aligned model raised the mean correction bolus from 1.09 to 2.23 U and post-decision time in range from 73.61% to 76.01% without inducing hypoglycaemia under an explicit safety guard. These results indicate that aligning the treatment response is as important as minimizing prediction error when a forecaster is used for dosing decisions.
- Open Access
- 25 April 2026
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 26 (1)
Predicting disease outcomes from remote monitoring using machine learning: a systematic review
Background: Chronic conditions cause millions of deaths annually worldwide. Remote patient monitoring using wearable devices and sensors, combined with machine learning (ML), offers promising strategies for disease management. However, diverse methodological approaches and study designs impede comparability and the development of best practice guidelines. Methods: A systematic review was conducted following the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines. Four scientific databases were searched for relevant prospective studies published between 2014 and 2024. Studies had to use ML to predict disease outcomes of chronic conditions in remotely monitored patients. The studies were tagged for characteristics such as health outcomes, dataset, monitored parameters, and algorithms. Results: From 6668 initially identified studies, 76 met inclusion criteria. 73.7% of studies were considered to have a high risk of bias, mainly due to methodological shortcomings in the Analysis domain. Parkinson’s disease was most frequently monitored, followed by diabetes and chronic obstructive pulmonary disease (COPD). Wearable devices were the predominant remote sensors, with accelerometer data being the most common parameter. Tree-based algorithms were most frequent, and studies using leave-one-out cross-validation showed significantly higher accuracy. Feature engineering and publication year were also significantly associated with model performance. Conclusion: This review highlights both progress and challenges in applying ML to chronic disease monitoring. While conditions like Parkinson’s, COPD, and diabetes are well-represented, others such as liver and kidney diseases are underexplored. Future research should prioritize standardization of methodologies, model interpretability, and ethical considerations including data privacy and algorithmic fairness. When properly implemented, ML-driven remote monitoring has the potential to enhance patient care, reduce complications, and deepen our understanding of chronic conditions. However, addressing challenges in reproducibility, generalizability, and clinical integration is crucial for advancing the field.
- 25 April 2026
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 26 (1)
Open AccessPredicting disease outcomes from remote monitoring using machine learning: a systematic review
Background: Chronic conditions cause millions of deaths annually worldwide. Remote patient monitoring using wearable devices and sensors, combined with machine learning (ML), offers promising strategies for disease management. However, diverse methodological approaches and study designs impede comparability and the development of best practice guidelines. Methods: A systematic review was conducted following the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines. Four scientific databases were searched for relevant prospective studies published between 2014 and 2024. Studies had to use ML to predict disease outcomes of chronic conditions in remotely monitored patients. The studies were tagged for characteristics such as health outcomes, dataset, monitored parameters, and algorithms. Results: From 6668 initially identified studies, 76 met inclusion criteria. 73.7% of studies were considered to have a high risk of bias, mainly due to methodological shortcomings in the Analysis domain. Parkinson’s disease was most frequently monitored, followed by diabetes and chronic obstructive pulmonary disease (COPD). Wearable devices were the predominant remote sensors, with accelerometer data being the most common parameter. Tree-based algorithms were most frequent, and studies using leave-one-out cross-validation showed significantly higher accuracy. Feature engineering and publication year were also significantly associated with model performance. Conclusion: This review highlights both progress and challenges in applying ML to chronic disease monitoring. While conditions like Parkinson’s, COPD, and diabetes are well-represented, others such as liver and kidney diseases are underexplored. Future research should prioritize standardization of methodologies, model interpretability, and ethical considerations including data privacy and algorithmic fairness. When properly implemented, ML-driven remote monitoring has the potential to enhance patient care, reduce complications, and deepen our understanding of chronic conditions. However, addressing challenges in reproducibility, generalizability, and clinical integration is crucial for advancing the field.
- Open Access
- 6 March 2026
- Published by Taylor & Francis in Medical Education Online
- Vol. 31 (1) , 2639835
Assessing the integration of digitalization and AI in general medicine curricula in German-speaking Europe: a comprehensive survey
The integration of digitalisation, including artificial intelligence (AI), is becoming increasingly important in healthcare. It is transforming areas such as diagnostics, therapeutic planning and patient monitoring. However, research indicates that many medical students and physicians feel unprepared to use these technologies in their daily practice. This study provides insights into the opportunities and challenges of integrating digitalisation and AI into medical curricula with a focus on general medicine curricula in German-speaking European countries. The objectives are to assess the perceived importance of digital and AI topics in medical education, evaluate the status of their integration into general medicine curricula and identify the challenges of their implementation. A sequential mixed-methods approach was used. First, a qualitative analysis of documents from university websites was conducted. Subsequently, 59 general medicine departments in Austria, Germany and Switzerland were invited to participate in a quantitative anonymous online survey. Descriptive statistics were analysed using SPSS 30.0. The survey was completed by half of Austrian universities and more than one-third of the German universities. None of the Swiss universities responded, resulting in a total response rate of 28.3%. The results reveal discrepancies between perceived importance and actual implementation, indicating a clear need for more courses on digitalisation and AI in medicine for medical students. Identified challenges with impact on limited implementation (especially of AI-related topics) were curriculum overload, a lack of qualified lecturers, lack of materials and a lack of resources. General medicine is the largest segment of healthcare services in Austria and Germany. Respondents highlighted a strong demand for digitalisation and AI to be integrated into general medicine curricula, which is consistent with other studies and the current literature. Our results underscore the urgent need for the systematic inclusion of competencies regarding digital tools and AI to adequately prepare future physicians for real-world challenges.
- 6 March 2026
- Published by Taylor & Francis in Medical Education Online
- Vol. 31 (1) , 2639835
Open AccessAssessing the integration of digitalization and AI in general medicine curricula in German-speaking Europe: a comprehensive survey
The integration of digitalisation, including artificial intelligence (AI), is becoming increasingly important in healthcare. It is transforming areas such as diagnostics, therapeutic planning and patient monitoring. However, research indicates that many medical students and physicians feel unprepared to use these technologies in their daily practice. This study provides insights into the opportunities and challenges of integrating digitalisation and AI into medical curricula with a focus on general medicine curricula in German-speaking European countries. The objectives are to assess the perceived importance of digital and AI topics in medical education, evaluate the status of their integration into general medicine curricula and identify the challenges of their implementation. A sequential mixed-methods approach was used. First, a qualitative analysis of documents from university websites was conducted. Subsequently, 59 general medicine departments in Austria, Germany and Switzerland were invited to participate in a quantitative anonymous online survey. Descriptive statistics were analysed using SPSS 30.0. The survey was completed by half of Austrian universities and more than one-third of the German universities. None of the Swiss universities responded, resulting in a total response rate of 28.3%. The results reveal discrepancies between perceived importance and actual implementation, indicating a clear need for more courses on digitalisation and AI in medicine for medical students. Identified challenges with impact on limited implementation (especially of AI-related topics) were curriculum overload, a lack of qualified lecturers, lack of materials and a lack of resources. General medicine is the largest segment of healthcare services in Austria and Germany. Respondents highlighted a strong demand for digitalisation and AI to be integrated into general medicine curricula, which is consistent with other studies and the current literature. Our results underscore the urgent need for the systematic inclusion of competencies regarding digital tools and AI to adequately prepare future physicians for real-world challenges.
- Open Access
- 2 February 2024
- Published by Springer Nature in Der Schmerz
- Vol. 38 (1) , 3-5
Seltene Erkrankungen und Schmerzen – ein oft übersehenes Zusammenspiel
- 2 February 2024
- Published by Springer Nature in Der Schmerz
- Vol. 38 (1) , 3-5
Open AccessSeltene Erkrankungen und Schmerzen – ein oft übersehenes Zusammenspiel
- 1 January 2024
- Published by Springer Nature
- p. 205-219
Fatigue
- 1 January 2024
- Published by Georg Thieme Verlag KG
Grundlagen der Schmerztherapie und Symptomlinderung
- 1 January 2024
- Published by Georg Thieme Verlag KG
Grundlagen der Schmerztherapie und Symptomlinderung
- 14 September 2023
- Published by SAGE Publications in Palliative Medicine
- Vol. 37 (8) , 1044-1046
Waking up from fatigue: The hidden burden of fatigue
- 14 September 2023
- Published by SAGE Publications in Palliative Medicine
- Vol. 37 (8) , 1044-1046
Waking up from fatigue: The hidden burden of fatigue
- Open Access
- 10 June 2023
- Published by Springer Nature in Oral and Maxillofacial Surgery
- Vol. 28 (1) , 457
Correction to: Suggestion of a new standard in measuring the mandible via MRI and an overview of reference values in young women
- 10 June 2023
- Published by Springer Nature in Oral and Maxillofacial Surgery
- Vol. 28 (1) , 457
Open AccessCorrection to: Suggestion of a new standard in measuring the mandible via MRI and an overview of reference values in young women
- Open Access
- 26 April 2023
- Published by Springer Nature in Oral and Maxillofacial Surgery
- Vol. 28 (1) , 373-383
Suggestion of a new standard in measuring the mandible via MRI and an overview of reference values in young women
Purpose: Adult idiopathic condylar resorption (AICR) mainly affects young women, but generally accepted diagnostic standards are lacking. Patients often need temporomandibular joint (TMJ) surgery, and often jaw anatomy is assessed by CT as well as MRI to observe both bone and soft tissue. This study aims to establish reference values for mandible dimensions in women from MRI only and correlate them to, e.g., laboratory parameters and lifestyle, to explore new putative parameters relevant in AICR. MRI-derived reference values could reduce preoperative effort by allowing physicians to rely on only the MRI without additional CT scan. Methods: We analyzed MRI data from a previous study (LIFE-Adult-Study, Leipzig, Germany) of 158 female participants aged 15–40 years (as AICR typically affects young women). The MR images were segmented, and standardized measuring of the mandibles was established. We correlated morphological features of the mandible with a large variety of other parameters documented in the LIFE-Adult study. Results: We established new reference values for mandible morphology in MRI, which are consistent with previous CT-based studies. Our results allow assessment of both mandible and soft tissue without radiation exposure. Correlations with BMI, lifestyle, or laboratory parameters could not be observed. Of note, correlation between SNB angle, a parameter often used for AICR assessment, and condylar volume, was also not observed, opening up the question if these parameters behave differently in AICR patients. Conclusion: These efforts constitute a first step towards establishing MRI as a viable method for condylar resorption assessment.
- 26 April 2023
- Published by Springer Nature in Oral and Maxillofacial Surgery
- Vol. 28 (1) , 373-383
Open AccessSuggestion of a new standard in measuring the mandible via MRI and an overview of reference values in young women
Purpose: Adult idiopathic condylar resorption (AICR) mainly affects young women, but generally accepted diagnostic standards are lacking. Patients often need temporomandibular joint (TMJ) surgery, and often jaw anatomy is assessed by CT as well as MRI to observe both bone and soft tissue. This study aims to establish reference values for mandible dimensions in women from MRI only and correlate them to, e.g., laboratory parameters and lifestyle, to explore new putative parameters relevant in AICR. MRI-derived reference values could reduce preoperative effort by allowing physicians to rely on only the MRI without additional CT scan. Methods: We analyzed MRI data from a previous study (LIFE-Adult-Study, Leipzig, Germany) of 158 female participants aged 15–40 years (as AICR typically affects young women). The MR images were segmented, and standardized measuring of the mandibles was established. We correlated morphological features of the mandible with a large variety of other parameters documented in the LIFE-Adult study. Results: We established new reference values for mandible morphology in MRI, which are consistent with previous CT-based studies. Our results allow assessment of both mandible and soft tissue without radiation exposure. Correlations with BMI, lifestyle, or laboratory parameters could not be observed. Of note, correlation between SNB angle, a parameter often used for AICR assessment, and condylar volume, was also not observed, opening up the question if these parameters behave differently in AICR patients. Conclusion: These efforts constitute a first step towards establishing MRI as a viable method for condylar resorption assessment.