A5076465763- Multiple Myeloma Research and Treatments
- Biomedical Text Mining and Ontologies
- Protein Degradation and Inhibitors
- Radiomics and Machine Learning in Medical Imaging
- Digital Imaging for Blood Diseases
- Lung Cancer Treatments and Mutations
- Machine Learning in Healthcare
- Erythropoietin and Anemia Treatment
- Gene expression and cancer classification
- AI in cancer detection
- Topic Modeling
- Bioinformatics and Genomic Networks
- Head and Neck Cancer Studies
- Semantic Web and Ontologies
- Data Visualization and Analytics
- Computational Drug Discovery Methods
- Lung Cancer Research Studies
- Cancer Immunotherapy and Biomarkers
- Artificial Intelligence in Healthcare
- Data Quality and Management
- Chronic Myeloid Leukemia Treatments
- Hematopoietic Stem Cell Transplantation
- vaccines and immunoinformatics approaches
- Software Engineering Techniques and Practices
- Software System Performance and Reliability
Leipzig University
2018-2025
King's College Hospital
2023
King's College London
2023
Klinik und Poliklinik für Neurologie
2022
University Hospital Leipzig
2022
Universität Hamburg
2017
This study introduces a system for predicting disease progression events in multiple myeloma patients from the CoMMpass (N = 1186). Utilizing hybrid neural network architecture, our model predicts future blood work historical lab results with high accuracy, significantly outperforming baseline estimators key parameters. Disease are annotated forecasted data, these significant reliability. We externally validated using GMMG-MM5 dataset 504), and could reproduce main of study. Our approach...
The treatment landscape for multiple myeloma (MM) has experienced substantial progress over the last decade. Despite efficacy of new substances, patient responses tend to still be highly unpredictable. With increasing cognitive burden that is introduced through a complex and evolving landscape, data-driven assistance tools are becoming more popular. Model-based approaches, such as digital twins (DT), enable simulation probable set input parameters based on retrospective observations. In...
Abstract Identifying patients who may benefit from autologous stem cell transplantation (ASCT) in newly diagnosed multiple myeloma is crucial, especially the era of effective induction and consolidation strategies. We analyzed data 12763 enrolled German Registry for Hematopoietic Stem Cell Transplantation Therapy (DRST), distinguishing those underwent single ( n = 8736) or tandem ASCT 4027) 1998 to 2021. Our findings show that median age at first increased over time, while use declined. The...
A software development screencast is a video that captures the screen of developer working on particular task and explaining implementation details. Due to increased popularity screencasts e.g., YouTube, we study how what extent they can be used as additional source knowledge answer developers' questions, for example about use specific API. We first difference between other types using frame analysis. When comparing frames with Cosine algorithm, developers expect ten in top 20 out 100...
New diagnostic methods and novel therapeutic agents spawn additional heterogeneous information, leading to an increasingly complex decision-making process for optimal treatment of cancer. A great amount information is collected in organ-specific multidisciplinary tumor boards (MDTBs). By considering the patient's properties, molecular pathological test results, comorbidities, MDTB has consent evidence-based decision. Immunotherapies are important today's cancer treatment, resulting detailed...
Making complex medical decisions is becoming an increasingly challenging task due to the growing amount of available evidence consider and higher demand for personalized treatment patient care. IT systems provision clinical decision support (CDS) can provide sustainable relief if are automatically evaluated processed. In this paper, we propose approach quantifying similarity between new previously recorded cases enable significant knowledge transfer reasoning tasks on a patient-level....
Model-based decision support systems promise to be a valuable addition oncological treatments and the implementation of personalized therapies. For integration sharing models, involved must able communicate with each other. In this paper, we propose modularized architecture dedicated for probabilistic models into existing hospital environments. These interconnect via web services provide model processing capabilities clinical information systems. Along lines IHE profiles from other...
The ability to accurately predict disease progression is paramount for optimizing multiple myeloma patient care. This study introduces a hybrid neural network architecture, combining Long Short-Term Memory networks with Conditional Restricted Boltzmann Machine, future blood work of affected patients from series historical laboratory results. We demonstrate that our model can replicate the statistical moments time ($0.95~\pm~0.01~\geq~R^2~\geq~0.83~\pm~0.03$) and forecast features high...
Aufgrund des stetigen Informationszuwachs in der Medizin müssen Entscheidungsfindung immer mehr Faktoren gleichzeitig berücksichtigt werden. Zum Ausgleich damit verbundenen höheren Belastung bei Ärztinnen und Ärzten werden zunehmend computergestützte Lösungen entwickelt evaluiert. Die Kombination intelligenter Anwendungen mit einem evidenzbasierten Anspruch erfordert spezifische Systemarchitekturen. Diese im vorliegenden Artikel näher vorgestellt erläutert. Durch die strukturierte...
Abstract Due to the broad spectrum of individual functionalities, current hospital information systems in most cases do not offer quick access or proper assistance assessment. This results extensive use raw value representations and need process evaluate those cognitively through physician. can result an error-prone ineffective process, especially complex chronic treatment scenarios. With example scenario laboratory assessment head neck oncology, we have evaluated requirements for support...
Treatment decisions in oncology are demanding and affect survival, general health, quality of life. Expert systems can handle the complexity oncological field. We propose application a hybrid modeling approach for decision support models consisting expert-based implementation model structure machine-learning (ML) based parameter generation. demonstrate our treatment oropharyngeal cancer.We created clinical on Bayesian Networks iteratively optimized its characteristics using structured...
Introduction Oncological decision-making processes are becoming increasingly complex with advances in diagnostics and more individual therapy options. In the case of head neck tumors (HNC), this requires new information processing techniques suitable models to support process tumor board (HNTB) molecular (MTB). For purpose, a pathological model was developed on basis digital patient for laryngeal carcinoma (LC).
The increasing complexity of cancer diagnostics and more personalized treatment options, also in head neck oncology, require new techniques patient information processing systems to support the decision-making process Head tumor board (HN-TB). For this purpose, a digital model larynx (LC) based on Bayes ' networks (BN) was developed.
Einleitung Die zunehmende Komplexität der Krebsdiagnostik und individuellere Therapieoptionen, auch in Kopf-Hals-Onkologie, erfordern neue Techniken Patienteninformationsverarbeitung Systeme zur Unterstützung des Entscheidungsprozesses im Kopf-Hals-Tumorboard (HN-TB). Dazu wurde ein digitales Patientenmodell (DPM) für das Larynxkarzinom (LC) auf Basis Bayes‘scher Netzwerke (BN) entwickelt positiv evaluiert.
Introduction The increasing complexity of cancer diagnostics and more individualized treatment options, also in head neck oncology, require new patient information processing techniques decision support systems the tumor board (HN-TB). Therefore, a digital model (DPM) for laryngeal carcinoma (LC) was developed on basis Bayesian networks (BN) positively evaluated.
BackgroundArtificial intelligence (AI)-based systems have the potential to revolutionize healthcare worldwide and are already increasing accuracy efficiency of diagnosis treatment in various medical disciplines, including hematology. The equipped interpret large amounts data guide early prognosis assessment, as well decision-making process for hematologic diseases. recent success AI-based has been driven by both rapid performance improvement computer technology establishment new learning...