Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

I will start by briefly introducing the concept of precision oncology as well as its modde of action, the molecular tumor board (MTBs), which interdisciplinarily issues individualized evidence-based treatment recommendations for cancer patients. These recommendations encompass patient-drug matches and patient-clinical trial matches. Precision oncology programs are registries, and secondary use of the data aggregated across patients enables cohort analyses via multi-omics characterization as well as the development of novel predictive and prognostic markers, which, in turn, can be used to enrich patients for clinical trials and/or provide the basis for future individualized treatment recommendations in MTBs. Traditionally this whole cycle often uses bulk technologies, but single cell technologies may be at reach for clinical translation soon. One such example is a modern application of flow cytometry, in particular sepctral flow cytometry, which makes use of the full emission spectrum of fluorophores for enhanced deconvolution and consequently higher combinatorial complexity, for the analysis of single cell landscapes as well as cellular interactions.

Speaker:  PD Dr. Dr. Daniel Hübschmann

Biography

PD Dr. Dr. Daniel Hübschmann is a physicist, mathematician, and physician with clinical experience in pediatric oncology. He heads the Innovation and Service Unit at the German Cancer Research Center (DKFZ) as well as the research group Computational Oncology in the Molecular Precision Oncology Program (MPOP) at the National Center for Tumor Diseases (NCT) Heidelberg and the group Pattern Recognition and Digital Medicine at the Heidelberg Institute for Stem cell Technology and Experimental Medicine (HI-STEM). His research focuses on bioinformatics, clinic-multi-omics integration, pattern recognition, machine learning, cancer genomics, DNA repair and cellular interactions and precision medicine. One of his core translational activities, together with his team, is the responsibility for the fast-track bioinformatics workup for molecular tumor boards of patients in several precision oncology programs at NCT Heidelberg.

Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

Artificial intelligence (AI) is increasingly integrated into regulated industrial environments, such as pharmaceutical manufacturing. At a production site for the synthesis of active pharmaceutical ingredients (APIs), an image-based AI system was developed to support microbiological process control. This system applies random forest algorithms trained on microscopic images to assess the morphology of microorganisms involved in biotechnological processes for in-process contamination detection.

The AI system functions as a decision-support tool, enabling laboratory experts to identify signs of contamination or process instability. Through real-time assessment and pattern recognition, it enhances process robustness, reduces the risk of production loss, and supports continuous quality in accordance with Good Manufacturing Practice (GMP) standards.

Unlike generative AI models, this AI is specifically designed for supervised visual analysis, ensuring full human oversight and compliance with relevant regulations. Different aspects matter, such as the development pipeline, training and validation methodology, and integration of the model into an existing GMP framework, illustrating how image-based AI can improve reliability and efficiency in pharmaceutical production without compromising patient safety.

Speaker:  Dr. Yvonne Gladbach

Biography

Dr. Yvonne Saara Gladbach is a Data Scientist in the pharmaceutical industry, currently working at Bayer AG in Bergkamen, Germany, where she develops and implements artificial intelligence (AI) systems for manufacturing processes in regulated pharmaceutical production. She completed her Ph.D. at the University of Heidelberg in collaboration with the University Medical School Rostock, focusing on the integration of multi-omics data for predicting novel drug targets in Acute Lymphoblastic Leukemia (ALL).

Her academic background includes extensive research in bioinformatics, next-generation sequencing (NGS) analysis, and systems biology, with applications to oncology and neurodegenerative diseases. Dr. Gladbach holds an M.Sc. in Bioinformatics from Saarland University, where she developed a bioinformatic pipeline for automated bacterial characterization using MLST schemes. Her interdisciplinary expertise bridges computational biology, machine learning, and pharmaceutical manufacturing, with a strong focus on data integrity and digital transformation in GMP-regulated environments.

Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

Artificial intelligence has the potential to transform neurosurgical practice, yet a significant gap remains between data scientists who develop algorithms and models and clinicians who face real-world problems. The lecture will address the importance of closing this gap to create meaningful, clinically integrated AI tools. Drawing on the experience of the GEIBAC research group at Río Hortega University Hospital, several ongoing projects will be presented, including GlioMap, CereBleed, SonoDetect, SAH-Mortality, and NeuroRIS-AI, which leverage machine/deep learning and computer vision applied to multimodal neuroimaging. The session will highlight practical strategies for interdisciplinary collaboration, data curation, validation, and clinical deployment of AI systems within hospital workflows, aiming to translate computational innovation into improved neurosurgical care.

Speaker:  Dr. Santiago Cepeda

Biography

Dr. Cepeda is a neurosurgeon specialized in brain tumor surgery, trained at Hospital 12 de Octubre in Madrid, and awarded a cum laude PhDfrom Universidad Complutense, where he also completed a postgraduate diploma in translational oncology. He currently serves as coordinator of the brain tumor scientific committee and staff neurosurgeon at R´io Hortega University Hospital. 

He leads the Biomedical Imaging and Computational Analysis Group (GEIBAC), part of the Biomedical Research Institute of Valladolid (IBioVall), and serves as Principal Investigator in nationally and regionally funded R&D projects focused on artificial intelligence and neuroimaging. With expertise in programming and data science, Dr. Cepeda bridges clinical neurosurgery and computational analysis to develop AI-based tools for glioblastoma, intraoperative ultrasound, and neurovascular pathology. https://geibac.uva.es/

Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

Sometimes regulatory science is seen as paperwork. This is a misunderstanding of what it is, what it can science and why it is critical in digital health futures. What is the largest barrier to progress in digitalisation and the implementation of AI-enabled technologies in German university clinics and private hospitals? Is is the absence of appropriate tools and technologies or the absence of the ability to develop them? No. I argue and I present work to show that that it is largely the lack of coordinated efforts that bring implementation science together with practical operational leadership. That bring together quality oversight and regulatory strategy with the development and implementation of tools that are highly focused on patient and doctor needs, and are deeply integrated with each other and with human workflows. I will present work focussed on this theme, and bring in our parallel research themes on cybersecurity and health data sharing.

Speaker:  Prof. Dr. Stephen Gilbert

Biography

Prof. Dr. Gilbert worked in senior MedTech and Digital Heath roles in industry for 5 years, before returning to academia in 2022 in Dresden, Germany as Europe's first full Professor of Medical Device Regulatory Science for AI and Digital Health, where he teaches and conducts research. His research goals are the advancement of regulatory science in digital medicine and AI-enabled medical devices. Innovative digital approaches in healthcare must be accompanied by innovative regulatory and oversight approaches to ensure speed to market, to maximise the access of patients to life saving treatments, while at the same time ensuring safety on market. His team uses data science approaches, literature research. They development new solutions and approaches for the monitoring AI and digital health solutions, and for the evaluation of existing methods and regulatory frameworks.

Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

Speaker: 

Biography

Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

In this talk I will first give a brief summary of the principles governing why we move slowly or fast, and how these principles also affect the way we make decisions. I will then present recent studies in which we investigated how the speed of decision-making is modulated in cortico-subthalamic networks and whether neural control of decision-making speed is related to movement speed. Finally, I will present a behavioural framework for abnormally slow movements as observed in Parkinson’s disease based on concepts from utility theory and optimal control. This framework might be useful for future studies investigating the neural mechanisms underlying changes in decision-making and motor control in Parkinson’s disease and other neuro-psychiatric disorders.

Speaker:  Dr. Damian Herz

Biography

Damian Herz, MD PhD, is a Neurologist and Senior Physician at the University Hospital Heidelberg with vast experience in research including 5 years of post-doctoral training at the University of Oxford, U.K., under supervision of Peter Brown. His translational research focuses on the neurobiological basis of clinical impairment in Parkinson’s disease and how this can be ameliorated using neuromodulation in particular adaptive deep brain stimulation approaches. He has published >50 peer-reviewed manuscripts in high-impact journals such as Nature Communications, Current Biology, Plos Biology, Brain and Annals of Neurology (>4000 citations, H-index: 29). Clinically, he mainly works with patients with Neurodegenerative disorders, in particular Parkinson’s disease, and deep brain stimulation.

Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

Speaker:

Biography

Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

Understanding how genes shape metabolism is key to uncovering the mechanisms underlying metabolic health and disease. Our group focuses on disentangling the complex interactions between metabolic pathways, genetic regulation, and environmental influences across tissues and organs. By integrating multi-omics, fluxomics, and metabolic phenotyping data, we aim to build a comprehensive picture of metabolic regulation and its perturbations in disease states, with a particular emphasis on Type 2 Diabetes. Through these integrative approaches, we seek to advance the mapping of genetic-metabolic wiring and uncover new insights into metabolic dysfunction.

Speaker:  Dr. Dominik Lutter

Biography

Dr. Dominik Lutter is Group Leader of Computational Discovery Research at the Institute for Diabetes and Obesity, Helmholtz Munich. He earned his PhD in Biology from the University of Regensburg in 2009, focusing on computational methods to identify regulatory networks in mammalian transcriptomes. After postdoctoral postions in systems biology and computational modeling at Helmholtz Munich, he joined the Institute for Diabetes and Obesity in 2013 and established his research group in 2015. His research combines computational biology, multi-omics integration, and metabolic phenotyping to elucidate the genetic and regulatory architecture of metabolism and its dysregulation in diseases such as Type 2 Diabetes. 

Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

Speaker:

Biography

Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

Speaker: Yuki Hagiwara

Biography

Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

Speaker:  Prof. Dr. Janina Bahnemann

Biography

Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

Speaker:  PD Dr. Daniel Gräfe

Biography

Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

Speaker:  Prof. Dr. Philipp Altrock

Biography

Location: Lecture hall N2045 (Faculty of Applied Computer Science)

Abstract

Speaker:

Biography