Clinical Research and Real-World Evidence

At CARE, our mission is to improve patient outcomes through the rigorous analysis of electronic health record (EHR) data. Our multidisciplinary team—comprising informaticians, statisticians, and clinicians—works collaboratively to transform routinely collected patient data into actionable insights that address pressing clinical research questions.

We are committed to:

Leveraging cutting-edge technologies to drive innovation in patient care, including the application of machine learning (ML), artificial intelligence (AI), and other advanced computational methods.
Bridging the implementation gap by facilitating the translation of novel digital tools and research findings into real-world clinical practice—ensuring that innovations do not remain siloed in academic publications but reach the bedside where they can benefit patients.
Upholding the principles of reproducibility, transparency, and open science, by making our code openly available, and where feasible, sharing datasets in accordance with ethical and regulatory guidelines.
Promoting fairness and accessibility, both in the design of algorithms and in the dissemination of research outputs, to ensure equitable healthcare improvements across diverse patient populations.

By integrating data-driven insights with clinical expertise, CARE seeks to drive forward a learning health system that continuously evolves to better serve patients and clinicians alike.

Who We Are

CARE is a collaboration between the Department of Hematology & Stem Cell Transplantation and the Institute for Artificial Intelligence in Medicine (IKIM). The lab is currently comprised of three fulltime researchers and several affiliated researchers and students. It is led by Dr. med. Christopher M. Sauer, M.D., M.P.H., Ph.D.

Our Data Platform

CARE uses the Smart Hospital Information Platform (SHIP) to access all electronic health records from Essen University Hospital. Available in the standardized FHIR HL7 format, SHIP provides a rich and granular real-world data set, covering all inpatient and outpatient encounters.

What We Do

Our analytical approaches span a wide range of statistical, machine learning models, and AI models including:

Stratification & Prediction Models
Survival Analysis (e.g., Cox Proportional Hazards)
Gradient Boosting & Neural Networks
Foundation models for forecasting, prediction and text generation
Agentic AI frameworks

Another key focus is the use of causal inference methods to disentangle mere statistical associations from true causal effects that can inform clinical decision making.

CARE supports clinicians and patients by providing them with the best available evidence and decision support tools. To this end CARE is fully committed to open science, meaning that we publish our code to encourage reproducibility by colleagues.

Besides hospital EHR data, the lab has a track record of analyzing intensive care data, primarily using publicly available datasets such as:

MIMIC-IV, eICU-CRD (U.S)
AmsterdamUMCdb (Europe).

We collaborate closely with research teams at institutions including Harvard T.H. Chan School, Massachusetts Institute of Technology, Charité Berlin, and TU Dresden.

Join Us

Curious to learn more about CARE or thinking about a Bachelor, Master, MD or PhD thesis in a dynamic and fun research environment? Interested in collaborating with us? We’d love to hear from you

–Reach out anytime!

Team

Head of Junior Research Group

Dr. Dr. Christopher Sauer

christopher.sauer@uk-essen.de

Clinician-scientist focusing on advanced analytics and real-world evidence to improve outcomes of cancer patients and the critically ill.

Research Staff

Ph.D. Aman Deep
Postdoctoral Fellow

aman.deep@uk-essen.de

Clinical data scientist interested in EHR data harmonization, LLMs and Agentic AI.

MSc Gernot Pucher
Ph.D. Candidate

gernot.pucher@uk-essen.de

Data scientist interested in time series analytics and machine learning.

MSc Kevin Kopp
Ph.D. Candidate

kevin.kopp@uk-essen.de

Data Scientist interested in Statistics, Causal Inference, and Machine Learning.

Affiliated researchers

Melissa Haut
Dentist

melissa.haut@uk-essen.de

Investigating CMV reactivation after allogeneic transplantation via data integration and statistical modeling.

MSc Diab Elmehdi

diab.elmehd@gmail.com

Data Scientist interested in developing predictive models to forecast Cytokine Release Syndrome (CRS) risk in patient receiving CAR-T cell therapy.

Selected Publications

Pucher G, Rostalski T, Nensa F, Kleesiek J, Reinhardt HC, Sauer CM. Why implementing machine learning algorithms in the clinic is not a plug-and-play solution: a simulation study of a machine learning algorithm for acute leukaemia subtype diagnosis. EBioMedicine. 2025 Jan;111:105526. doi: 10.1016/j.ebiom.2024.105526. Epub 2024 Dec 24. PubMed PMID: 39721215; PubMed Central PMCID: PMC11732467.

Sauer CM, Pucher G, Celi LA. Why federated learning will do little to overcome the deeply embedded biases in clinical medicine. Intensive Care Med. 2024 Aug;50(8):1390-1392. doi: 10.1007/s00134-024-07491-8. Epub 2024 Jun 3. PubMed PMID: 38829532; PubMed Central PMCID: PMC11306542.

Leveraging Electronic Health Records for Data Science: Common pitfalls and how to avoid them. Sauer CM, Chen LC, Hyland S, Girbes A, Elbers P, Celi LA. Lancet Digit Health. 2022 Dec;4(12):e893-e898.

Systematic review and comparison of publicly available ICU data sets – A decision guide for clinicians and data scientists. Sauer CM, Dam TA, Celi LA, Faltys M, de la Hoz MAA, Adhikari L, Ziesemer KA, Girbes A, Thoral PJ, Elbers P. Crit Care Med. 2022 Mar 2. - Volume - Issue -DOI: 10.1097/CCM.0000000000005517

Funding