A hospital stay can be unsettling – especially in the run-up to major operations or medical procedures.  "Patient Empowerment Through Immersive Hospital Experiences before Operations or Procedures" (PERISKOP) uses immersive 360° films to bring key wards and medical care processes to life. Stereoscopic 360° videos show the environment and processes in the intensive care unit, during preparation for surgery and in obstetrics.

This gives patients the opportunity to familiarise themselves with the environment before their stay, learn about spatial and organisational processes, and experience potentially anxiety-provoking situations in advance. The aim is to reduce uncertainty, create a feeling of familiarity and support individual preparation for the hospital stay.
The project also examines how VR-supported information services can improve patient education and be integrated into clinical routine in the long term to support hospital staff.

The studies are based on three stereoscopic 360° films on the clinical areas of anaesthesia, intensive care and childbirth, produced at original locations at Charité – Universitätsmedizin Berlin. The films are not only aimed at patients: hospital staff can also use the recordings to gain the patient's perspective and thus deepen their empathy and understanding of the clinical experience. Each sub-study follows its own research design, tailored to the respective clinical situation and target group. Among other things, the studies examine preoperative anxiety, the subjective feeling of preparation, and effects on empathy and communication in everyday clinical practice. Data collection is currently underway. The project is funded by the Charité Foundation through the Max Rubner Prize 2024.

Learn more about PERISKOP via periskop.experimental-surgery.de/

We thank Stiftung Charité for their support and making this project come alive!

The study "Overcoming the data barrier: transfer learning for 90-day mortality prediction in general surgery - a retrospective multicenter development and comparison study" was published in the January issue of the International Surgery Journal by A. Winter, B. Pfitzner, R.P. van de Water, L. Faraj, C. Riepe, W.H. Hahn, F. Krenzien, C. Schineis, T. Malinka, W. Schöning, C. Denecke, B. Arnrich, K. Beyer, J. Pratschke J, I.M. Sauer, and M.M. Maurer.

This multicenter study investigated whether transfer learning (TL) can improve AI-based prediction of 90-day postoperative mortality in general surgery, where limited datasets often hinder the development of robust models.

Data from 14,922 patients undergoing esophageal, liver, pancreatic, or colorectal surgery across three tertiary centers (2015–2023) were analyzed using 85 preoperative variables. Large source neural network models were first trained, then fine-tuned for specific surgical procedures using transfer learning. These models were compared with conventional machine learning (ML) approaches and standard clinical risk scores.
Results showed that ML models already outperformed traditional risk scores (e.g., ASA and Charlson Comorbidity Index). Transfer learning further improved performance, particularly in predicting mortality for esophageal (+38% AUPRC), liver (+14%), and pancreatic surgery (+8%). Across all models, patient age and the Charlson Comorbidity Index were the most influential predictors.
Overall, the study demonstrates that transfer learning can significantly enhance AI model performance in surgical settings with limited data, offering a promising strategy for improving preoperative risk stratification and decision-making in general surgery.

M.M. Maurer, B. Pfitzner, R.P. van de Water, L. Faraj, C. Riepe, D. Zuluaga, F. Krenzien, N. Raschzok, R. Siegel, C. Schineis, B. Arnrich, K. Beyer, J. Pratschke, I.M. Sauer, and A. Winter evaluated federated learning (FL) as a privacy-preserving approach for AI-based prediction of 90-day mortality after colorectal surgery. Limited data sharing between hospitals often restricts surgical AI development, and FL allows multicenter model training without transferring raw patient data. The study also assessed the effect of differential privacy (DP) on model performance.
Data from 2,959 patients undergoing elective colorectal surgery at three tertiary centers (2015–2021) were analyzed. Neural networks were trained locally at each center, using centralized data aggregation and distributed federated learning. Additional privacy protection was implemented using central and local differential privacy.
Results showed that federated learning performed similarly to centralized modeling, achieving comparable predictive accuracy (AUROC ~0.78 vs. 0.81). However, adding differential privacy reduced performance, with central DP causing moderate declines and local DP nearly eliminating predictive accuracy. Across models, the most influential predictors were patient age, blood parameters, and the Charlson Comorbidity Index.
Overall, the study demonstrates that federated learning can enable effective multicenter surgical AI models while preserving data privacy, though strong privacy mechanisms like differential privacy may significantly compromise model performance.

"Privacy preserving federated learning for 90-day mortality prediction in colorectal surgery: a multicenter retrospective development and comparison study" is available in International Journal of Surgery 2025;111(12):9065-9074

Virtual reality (VR) and augmented reality (AR) are among the fastest-growing technologies of the 21st century. They also open up enormous opportunities for social integration: through cultural and educational offerings, through networked digital interaction spaces, or as a means of promoting citizen participation. The contributions in this volume present a wide range of application scenarios for VR and AR in the fields of education, health and public space. They demonstrate in a practical way how society, but also companies, can benefit from expanding their technological skills and taking diversity aspects into account. After all, genuine participation is only possible through a sustainable, transdisciplinary and citizen science approach.

Our book chapter ‘Human-Centred Design of Mixed Reality Applications in Medical Education – GreifbAR’ is now available in open access. Authors are Robert Luzsa, Moritz Queisner, Christopher Remde, Igor Sauer, Nadia Robertini and Susanne Mayr.

As part of the BMBF-funded project ‘Tangible Reality – Skilful Interaction of User Hands and Fingers with Real Tools in Mixed Reality Worlds’, we investigated how XR technology can be integrated into medical education. The chapter presents an interdisciplinary, XR-based training system for surgical knot tying. It describes key design principles and experiences from development and evaluation. In addition, it proposes a model for the human-centred design of comparable training applications that can also support other projects.

We warmly invite you to the opening of »Vessels. Infrastructures of Life« at the Berlin Museum of Medical History at the Charité (bmm), a group exhibition curated by Igor M. Sauer and Navena Widulin with contributions by Assal Daneshgar, Emile de Visscher, Frédéric Eyl, Karl Hillebrandt, Eriselda Keshi, Dietrich Polenz, Moritz Queisner, Iva Rešetar and Igor M. Sauer.

Vernissage
Wed, 4 June 2025, 7:00 - 10:00 pm

Exhibition
5 June – 12 October 2025 Tue, Thu, Fri, Sun, 10:00 am - 5:00 pm Wed, Sat, 10:00 am - 7:00 pm Closed on Mondays

Venue
Berliner Medizinhistorisches Museum der Charité (bmm) Virchowweg 17 10117 Berlin

What do plants, animals, humans and cities have in common? They all have vascular systems and, therefore, an infrastructure without which they would not be able to survive.

In the human body, arteries and veins move the blood together with the heart. Plants have a finely branched vascular system for the transport of water and nutrients. And cities utilize an underground network of pipelines that supply clean water and remove wastewater. The temporary exhibition, co-curated by Igor Sauer and Navena Widulin, shows how these vessels function and how they can be visualized, used and reproduced.

What can medicine learn from these natural and technical supply systems? What role does the interdisciplinary view – between biology, design, materials research and medical technology – play for regenerative medicine? And what innovative approaches can be derived from this for the development of artificial and bioartificial donor organs?

»Vessels. Infrastructures of Life« provides insights into the work of designers, material scientists and surgical researchers who are working together on solutions for the future – inspired by nature, technology and the logic of living systems. From exhibits on transplantation and regenerative medicine to examples of architecture and design, the exhibition offers exciting insights into these often-hidden structures. The objects on display correspond with those in Rudolf Virchow’s historical collection of specimens. A particular focus lies on the connections between natural vessels and human-made networks, such as the regulation of temperature in buildings or the water and wastewater supply in cities.

The temporary exhibition »Vessels. Infrastructures of Life« is a collaboration between the Berlin Museum of Medical History and the Experimental Surgery at the Charité and the Cluster of Excellence »Matters of Activity« of Humboldt-Universität zu Berlin as part of the → ＿matter Festival 2025.

Our paper, "90-Day Mortality Prediction in Elective Visceral Surgery Using Machine Learning: A Retrospective Multicenter Development, Validation, and Comparison Study" has been published online ahead of print in the International Journal of Surgery.
Authors are C. Riepe, R. van de Water, A. Winter, B. Pfitzner, L. Faraj, R. Ahlborn, M. Schulze, D. Zuluaga, C. Schineis, K. Beyer, J. Pratschke, B. Arnrich, I.M. Sauer, and M.M. Maurer

Machine Learning (ML) is increasingly being adopted in biomedical research, however, its potential for outcome prediction in visceral surgery remains uncertain. This study compares the potential of ML methods for preoperative 90-day mortality (90DM) prediction of an aggregated multi-organ approach to conventional scoring systems and individual organ models.

This retrospective cohort study enrolled patients undergoing major elective visceral surgery between 2014 and 2022 across two tertiary centers. Multiple ML models for preoperative 90DM prediction were trained, externally validated and benchmarked against the American Society of Anesthesiologists (ASA) score and revised Charlson Comorbidity Index (rCCI). Areas under the receiver operating characteristic (AUROC) and precision recall curves (AUPRC) including standard deviations were calculated. Additionally, individual models for esophageal, gastric, intestinal, liver, and pancreatic surgery were developed and compared to an aggregated approach. A total of 7,711 cases encompassing 78 features were included. Overall 90DM was 4% (n = 309). An XBoost classifier demonstrated the best performance and high robustness following external validation (AUROC: 0.86 [0.01]; AUPRC: 0.2 [0.04]). All models outperformed the ASA score (AUROC: 0.72; AUPRC: 0.08) and rCCI (AUROC: 0.81; AUPRC: 0.11). rCCI, patient age and C-reactive protein emerged as most decisive model weights. Models for gastric (AUROC: 0.88 [0.13]; AUPRC: 0.24 [0.26]) and intestinal surgery (AUROC: 0.87 [0.05]; AUPRC: 0.17 [0.09]) revealed the highest organ-specific performances, while pancreatic surgery yielded the lowest results (AUROC: 0.66 [0.08]; AUPRC: 0.22 [0.12]). A combined multi-organ approach (AUROC: 0.84 [0.04]; AUPRC: 0.21 [0.06]) demonstrated superiority over the weighted average across all organ-specific models (AUROC: 0.82 [0.07]; AUPRC: 0.2 [0.13]).

ML offers robust preoperative risk stratification for 90DM in elective visceral surgery. Leveraging training across multi-organ cohorts may improve accuracy and robustness compared to organ-specific models. Prospective studies are needed to confirm the potential of ML in surgical outcome prediction.

We are delighted to welcome Dr. Zeynep Akbal as a new member of the team!
Before she started as a post-doctoral researcher at the Digital Surgery Lab she studied communication sciences, media sciences, philosophy, and worked on developing her interdisciplinary method around virtual reality (VR) technology. She did her doctorate in philosophy at Universität Potsdam. Her dissertation is recently published as a monograph, titled "Lived-Body Experiences in Virtual Reality. A Phenomenology of the Virtual Body.”
Her research focuses on the intersection of philosophy of perception, cognitive sciences and VR. In her recent research project “Tactile Stimulation in VR” at Max Planck Institute for Human Cognitive and Brain Sciences, she focused on the behavioral consequences of haptic feedback in a VR task.

Wellcome to the team!