Digital Guidelines & Knowledge-based Decision Support

Projects

CODEX-CELIDA

In the CODEX-CELIDA project, we developed an interoperable approach that links digitally represented clinical guideline recommendations with standardized routine clinical data. The system was subsequently deployed and validated across five university hospitals. The multicenter study included more than 82,000 ICU stays and approximately 2.2 million patient-days. Compared with a physician-reviewed reference standard, the automated system achieved an accuracy of 97.0% in determining guideline applicability and adherence.

Multicenter evaluation study · Design and implementation study · FHIR Implementation Guide

Dissolve-E

Dissolve-E is transforming the quality-assured guideline registry of the Association of the Scientific Medical Societies in Germany into a digital, standards-based infrastructure. University Medicine Greifswald is a consortium partner and contributes in particular to the interoperable representation of guideline information and to interfaces for digital applications.

Project description · Study protocol

Digi-POD

Digi-POD develops a digital clinical decision support system for the prevention of postoperative delirium. Evidence-based recommendations are represented in a machine-readable format and automatically matched with routine clinical data in real time.

Project description

cpgQA-DE

cpgQA-DE is a German-language research benchmark for medical question answering based on clinical practice guidelines. The dataset contains 200 validated questions with answer keys, references, contextual excerpts, and annotations of difficulty and clinical relevance. It evaluates both direct responses from Large Language Models and Retrieval-Augmented Generation using guideline-based document corpora.

Publication · Dataset · Code

Selected Publications

  • Lichtner G, Schiefenhövel F, Gashi B, et al. Multicenter Evaluation of an Interoperable System for Automated Guideline Adherence Monitoring in ICUs. Critical Care Medicine. 2026;54(1):119–128. DOI
  • Schwietering J, Lichtner G. Benchmarking large language models for question answering on German clinical practice guidelines. BMJ Health & Care Informatics. 2026;33:e102207. DOI
  • von Dincklage F, Bublitz V, Kumpf O, et al. Computer-Interpretable Quality Indicators for Intensive Care Medicine: Development and Validation Study. Journal of Medical Internet Research. 2025;27:e77077. DOI
  • Nothacker M, et al. Digitalisation of the guideline registry of the Association of Scientific Medical Societies in Germany for an open, guideline-based, trustworthy evidence ecosystem (Dissolve-E). BMJ Open. 2025;15:e095294. DOI
  • Lichtner G, Jurth C, Alper BS, et al. Representation of evidence-based clinical practice guideline recommendations on FHIR. Journal of Biomedical Informatics. 2023;139:104305. DOI
  • Lichtner G, Spies C, Jurth C, et al. Automated Monitoring of Adherence to Evidence-Based Clinical Guideline Recommendations: Design and Implementation Study. Journal of Medical Internet Research. 2023;25:e41177. DOI

Contacts