ORAHS 2019

Martin Schuster, MD, MA, is a Professor of Anesthesiology at the Ruprecht-Karls-University Heidelberg and head of the Department of Anesthesiology, Intensive Care, Emergency Medicine and Pain Therapy at the Fürst-Stirum-Hospital Bruchsal and Rechbergklinik Bretten, both academic teaching hospitals of the Ruprecht-Karls-University Heidelberg.

He studied medicine, philosophy and history in Hannover, Germany and Baltimore and New York City, USA and graduated in 1997. Afterwards he spend a year in lung immunology research on a stipend of the Studienstiftung des Deutschen Volkes and started his residency in anesthesiology at the Medical School Hannover in 1998. From 2000 to 2002 he interrupted his clinical education and worked at McKinsey & Co. in business consulting as senior associate in the healthcare sector. From 2002 to 2005 he finished his residency in anesthesiology at the university hospital Hamburg-Eppendorf and was appointed as consultant. From 2007 to 2011 he worked at the Charité University Medicine in Berlin as consultant in anesthesiology and intensive care until he obtained his current position.

His main academic interest is in Health Economics, Operations Management and Quality Improvement in hospitals. He especially focused on Process Optimization in clinical medicine, steering of clinical departments and operating room management. He leads the working group on process-, cost- and operating room management in the German Society of Anesthesiology and Intensive Care and authored over 50 peer reviewed articles and book chapters. He is section editor for quality management and economics at Der Anästhesist, the leading German journal in anesthesiology and serves as reviewer for Anesthesia and Analgesia, British Journal of Anesthesia, Anesthesiology and Anästhesie und Intensivmedizin. He is also member in the scientific advisory board of the largest German operating room benchmark program.

Title: Operations Research in Operating Room Management
Operating rooms (OR) are accountable for a large share of hospital costs and OR efficiency is a major issue in hospital management. Efficient processes in the OR are not only important because of the high fix costs of operating rooms, inefficient processes also increases costs in other areas of hospital care like ward costs or costs of intensive care. Furthermore inefficient processes leads to demotivation of the staff. However the extreme variability of surgical and anesthesia processes, the high number of different departments, persons and professions involved in operating room processes, the high rate of emergency processes and processes running out of control and the many interfaces with almost all other departments and structures in the hospital makes it complex to ensure a smooth running of the operating rooms. Based on the drastically increased cost considerations in the DRG era a formal OR management structure has been established in most hospitals in Germany during the last 20 years. Along with this professionalization of practical OR management academic operations research in operating room management was established to provide a sound basis for management decisions: a common nomenclature of process description was established and key performance indicators to measure OR efficiency were identified and studied in detail, including turnover time and OR utilization. Detailed anesthesia and surgery process analysis was established and incentive structures have been studied to improve performance of the organization. Special focus has been placed on OR capacity planning and block allocation and improvement of OR list planning. A professional OR process benchmarking platform was introduced in Germany 10 years ago, which enables hospitals to compare the own processes with processes of other comparable hospitals to identify options and levers for improvement. Furthermore process redesign approaches have been used to study further improvement opportunities, including simulation based modelling.

Dolores Romero Morales is a Professor in Operations Research at Copenhagen Business School. Her areas of expertise include Supply Chain Optimization, Data Mining and Revenue Management. In Supply Chain Optimization she works on environmental issues and robustness. In Data Mining she investigates interpretability and visualization. In Revenue Management she works on large-scale network models. Her work has appeared in a variety of leading scholarly journals, including European Journal of Operational Research, Management Science, Mathematical Programming and Operations Research, and has received various distinctions. Currently, she is an Associate Editor of Omega and TOP.

She has worked with and advised various companies on these topics, including IBM, SAS, KLM and Radisson Edwardian Hotels, as a result of which these companies managed to improve some of their practices. SAS named her an Honorary SAS Fellow and member of the SAS Academic Advisory Board. She currently leads the EU H2020-MSCA-RISE NeEDS project, which has a total of 14 participants and a budget of more than €1.000.000 for intersectoral and international mobility, with the aim to improve the state of the art in Data Driven Decision Making.

Dolores joined Copenhagen Business School in 2014. Prior to coming to Copenhagen Business School she was a Full Professor at University of Oxford (2003-2014) and an Assistant Professor at Maastricht University (2000-2003). She has a BSc and an MSc in Mathematics from Universidad de Sevilla and a PhD in Operations Research from Erasmus University Rotterdam.

Titel: Learning and Interpreting with Mathematical Optimization
Data Science aims to develop models that extract knowledge from complex data and represent it to aid Data Driven Decision Making. Mathematical Optimization has played a crucial role across the three main pillars of Data Science, namely Supervised Learning, Unsupervised Learning and Information Visualization. Data Science models should strike a balance between accuracy and interpretability. Interpretability is desirable for by non-experts; it is required by regulators for models aiding, for instance, credit scoring; and since 2018 the EU extends this requirement by imposing the so-called right-to-explanation. In this lecture, we show the important role that Mathematical Optimization plays to model the trade-off between learning accuracy and interpretability.

Matthias Reumann studied Electronics at the University of Southampton, UK, and received the Master of Engineering First Class with Honours in 2003. He continued his studies in Biomedical Engineering at the Universität Karlsruhe (TH), Karlsruhe, Germany, and was awarded his PhD for his thesis on modelling atrial fibrillation, congestive heart failure and their non-pharmacological treatment.

In 2007, he joined the IBM T. J. Watson Research Center, NY, USA, as Post Doctoral Fellow to implement multi-scalar whole heart models on the worlds fastest and largest supercomputers. This expertise brought him to join the IBM Research Collaboratory for Lifesciences in Melbourne, Australia, in 2010 where he further established a research group in healthcare at the IBM Research – Australia laboratory from 2011 – 2013. During this period, he expanded his research interests into sustainable, resilient health systems research including a project in Africa. Since December 2013, he has been working at the IBM Research – Zurich Laboratory on numerous client projects aiming to get patients to the right health service provider at the right time. He was awarded a second PhD from the University of Maastricht, Maastricht, The Netherlands, in Oct. 2017 for his work on Big Data in Public Health: from Genes to Society. He holds several national and international awards and has published over 100 articles, book chapters and conference proceedings.

Title: Bridging Vision and Reality: Big Data and AI in Healthcare
The rise of Big Data and the resurgence of artificial intelligence in healthcare and lifescience holds promises that claim to lead to a creative disruption of medicine. Several publications have demonstrated the power of AI with respect to improving diagnosis and treatment. However, most of these publications were carried out under experimental conditions. AI in healthcare has gone from a forming to a storming phase. It is essential that the next step to the norming phase will be achieved so that the power of AI and Big Data can be harnessed and perform to its expectations. To realize the potential of new technology and the fast-paced innovation in digital health, a solid foundation of quality data and methods has to be built. This talk will illustrate the vision of how big data and AI could transform healthcare giving real world examples that show the status quo of digital health bridging reality and vision from genes to society.