New technology will fundamentally change the way inpatient care works over the next few years. We therefore research artificial intelligence for clinical processes actively, build our own models, which we reconstruct, measure and predict from real-time data – and validate them together with hospitals and research partners on real data.
Part of this work happens in collaboration: we provide data and infrastructure, supervise bachelor's, master's and doctoral theses, and work with international research networks. The work listed below came out of that, or places the field in its scientific context.
Grabow, S.
Practice report from LMU Klinikum Munich: a digital assistant for OR management reduces delays in the operating room – and shows that what matters most are the people in day-to-day OR work.
Giese, J., Palan, N.
How UKSH introduces digitally supported process and patient management in the OR step by step – from the starting point to routine operation.
Giese, J.
Overview of digital assistance systems in day-to-day OR work and the demands they place on organization and teams.
Hort, A. · TH Rosenheim, Informatik
Master's thesis on the data-driven analysis and optimization of the perioperative process at LMU Klinikum Großhadern.
Conducted in cooperation with sqior medical GmbH
Kloyer, M. · University of Oslo, Health Management and Health Economics
Master's thesis with a qualitative analysis of the change processes involved in introducing a digital assistant for OR management at a Munich university hospital.
Conducted in cooperation with sqior medical GmbH
Szabó, A.K., Flemming, S. · Die Chirurgie
Review article on patient safety in the operating room.
View PublicationRamamurthi, A., Neupane, B., Deshpande, P., et al. · JAMA Surgery
Retrospective study of more than 125,000 elective cases: how accurately do large language models predict surgical case length from unstructured clinical data, compared with established estimation methods?
View PublicationPark, J., Roh, G., Kim, K., Kim, H. · Journal of Medical Systems
Department-specific random forest models for predicting surgical case durations, benchmarked against methods such as XGBoost, LightGBM and CatBoost.
View PublicationYu, H., Yuan, Y., Zhang, Y., et al. · BMC Medical Informatics and Decision Making
Descriptive analysis of anesthesia and surgery durations in emergency cases as a basis for operating room performance metrics.
View PublicationRamamurthi, A., Neupane, B., Deshpande, P., et al. · Surgery
Development and validation of an AI system for predicting surgical case length.
View PublicationDo you have a project proposal, are you looking for a research consortium partner, or do you need access to our clinical process database or our AI models?