Research

This page provides an overview of the research being conducted at the ICUCockpit Lab. For an extensive list of research articles by individual team members, please visit the respective profile pages.

Student opportunities:

We welcome spontaneous applications from Bachelor’s and Master’s students who are interested in doing a thesis, semester project, or other research/development work with the ICU Cockpit Lab. We have a wide variety of options available—data science, machine learning, user interface design, signal processing, clinical decision support, visualization, etc.—and can adapt topic, duration, and co-supervision according to your needs. Whether you have fixed project dates or want flexibility, we’ll work with you to define a scope that fits your goals. If interested, please send your CV, transcript, research interests, and (if possible) a proposed timeline to emanuela.keller AT usz.ch.

Highlighted

Limitations of SpO2 / FiO2-ratio for classification and monitoring of acute respiratory distress syndrome—an observational cohort study

Rolf Erlebach, Una Pale, Tilman Beck, Sasa Markovic, Marko Seric, Sascha David, Emanuela Keller

Critical Care  ·  19 Feb 2025  ·  10.1186/s13054-025-05317-7

The ratio of pulse-oximetric peripheral oxygen saturation to fraction of inspired oxygen (SpO2/FiO2) has been proposed as additional hypoxemia criterion in a new global definition of acute respiratory distress syndrome (ARDS). This study aims to evaluate the clinical and theoretical limitations of the SpO2/FiO2-ratio when using it to classify patients with ARDS and to follow disease progression.

acute-respiratory-distress-syndrome algorithm classification

A Longitudinal Model for a Dynamic Risk Score to Predict Delayed Cerebral Ischemia after Subarachnoid Hemorrhage

Jan F. Willms, Corinne Inauen, Stefan Yu Bögli, Carl Muroi, Jens M. Boss, Emanuela Keller

Bioengineering  ·  30 Sep 2024  ·  10.3390/bioengineering11100988

Accurate longitudinal risk prediction for DCI (delayed cerebral ischemia) occurrence after subarachnoid hemorrhage (SAH) is essential for clinicians to administer appropriate and timely diagnostics, thereby improving treatment planning and outcome. This study aimed to develop an improved longitudinal DCI prediction model and evaluate its performance in predicting DCI between day 4 and 14 after aneurysm rupture.

model algorithm machine-learning brain-injuries

Solving the explainable AI conundrum by bridging clinicians’ needs and developers’ goals

Nadine Bienefeld, Jens Michael Boss, Rahel Lüthy, Dominique Brodbeck, Jan Azzati, Mirco Blaser, Jan Willms, Emanuela Keller

npj Digital Medicine  ·  22 May 2023  ·  doi:10.1038/s41746-023-00837-4

This paper presents the findings of a longitudinal multi-method study involving 112 developers and clinicians co-designing an XAI solution for a clinical decision support system. Our study identifies three key differences between developer and clinician mental models of XAI, including opposing goals (model interpretability vs. clinical plausibility), different sources of truth (data vs. patient), and the role of exploring new vs. exploiting old knowledge

social-sciences

ICU Cockpit: a platform for collecting multimodal waveform data, AI-based computational disease modeling and real-time decision support in the intensive care unit

Jens Michael Boss, Gagan Narula, Christian Straessle, Jan Willms, Jan Azzati, …, Carl Muroi, David Jule Mack, Marko Seric, Daniel Baumann, Emanuela Keller

Journal of the American Medical Informatics Association  ·  14 Jul 2022  ·  doi:10.1093/jamia/ocac064

The description of our ICUCockpit IT infrastructure responsible for collecting multimodal data from a neurosurgical ICU and real-time decision support

machine-learning data-dashboard high-resolution-waveform clinical-research research-database

All

2025

2024

2023

2022

2021

2020