ACROSS

Actionable, Collaborative, Reusable, interOperable Sepsis System

Started
June 1, 2025
Status
In Progress
Share this project

Abstract

Standardizing heterogeneous healthcare data is essential for understanding complex diseases and improving treatment. In line with the national sepsis program, the SDSC is collaborating with the University Hospital of Lausanne (CHUV), the University Hospital Bern (Inselspital) and the Children Hospital in Zurich (Kispi) to develop an AI-powered data pipeline for sepsis quality-of-care monitoring. Deployed at CHUV, the tool provides caregivers and hospital managers with timely feedback on clinical practice and enables benchmarking of key measures.

This strategic project aims to create a standardized software solution that enables hospitals to organize and share sepsis-related data in a consistent way. By implementing the same approach across partner hospitals, the project will improve data quality, support expansion to additional healthcare settings – including pediatric care – and lay the foundation for a national sepsis program that is compatible with international standards and, more broadly, for OMOP-based infrastructure in Switzerland. [1]

People

Collaborators

SDSC Team:
Laure Vancauwenberghe
Stefan Milosavljevic
Almut Lütge
Isione Bonvalot
Luana Martelli
Raphaël Matusiak
Oksana Riba Grognuz
Federico Amato

PI | Partners:

University Hospital of Lausanne (CHUV):

  • Dr. Sylvain Meylan (main applicant and sepsis expert)
  • Jéremie Despraz (principal data scientist)
  • Gauthier Le Bosse (data engineer)

University Hospital Bern (Inselspital)

  • Prof. Olga Endrich (infrastructure and OMOP project lead)
  • Dr. Christine Thurnheer (medical doctor)
  • Marcel Messerli (OMOP implementation consultant at Insel)
  • Dr. Benjamin Ellenberger (lead data scientist)

University Children’s Hospital Zürich (KiSpi):

  • Dr. Luregn Schlapbach (pediatrician)
  • Dr. Nora Lüthi (pediatrician)
  • Manuel Schweighofer (data engineer)

description

Motivation & Objectives

CHUV and SDSC have co-developed an AI-powered data pipeline for sepsis quality-of-care monitoring. Currently deployed at CHUV, this tool provides caregivers and hospital managers with timely and precise feedback on the clinical practice and allows benchmarking on clinical measures. 

In this project, we aim to:

  • Standardize the data pipeline to make it interoperable by porting it to the OMOP common data model.
  • Package it into production-ready software, enabling its national and international deployment.
  • Deploy the standardized pipeline at CHUV, Insel, and KiSpi and validate its performance as a proof-of-concept for a wider dissemination.

This packaged pipeline should eventually enable the creation of a national standardized sepsis registry, with international interoperability.

SDSC Contribution

The SDSC team will have a dual role: on the one hand, our data scientists and engineers are involved in re-modelling, adapting and industrializing the existing AI data pipeline. On the other hand, the team will play a critical role in infrastructure build and deployment. 

The modelling work includes:

  • Improving the existing AI module
  • Generalizing and/or modularizing the pre-processing steps of the source data with the help of the OMOP common data model [1]
  • Adapt AI module to a pediatric context
  • Refactoring and packaging source code with industry standards and OMOP, ensuring data quality, traceability, privacy and robustness 

The infrastructure work includes:

  • Understand the IT architecture and context for each hospital
  • Coordinate with data engineers to find the most fitting deploying option
  • Ensure services are set up and/or ready for a smooth and secure deployment
  • Include upstream changes to the modelling/infrastructure code when necessary

Impact

This project extends the reach and impact of the previously validated and operational HERACLES sepsis model at CHUV by adapting it for use with Inselspital patients, laying the groundwork for harmonizing sepsis prevention and treatment protocols between Inselspital and CHUV. 

Beyond this initial application, the underlying solution is designed for broader scalability: any Swiss hospital capable of standardizing its data in OMOP format can adopt it, extending its clinical value across the national healthcare system.

Footnote: 

[1] OMOP - Observational Medical Outcomes Partnership – is known for OMOP Common Data Model (CDM), an open-source standard designed to normalize and structure complex, fragmented healthcare data (such as electronic health records and insurance claims) into a single, predictable, relational database format.

Gallery

Annexe

Additional resources

Bibliography

Publications

Related Pages

More projects

Dedgeflow

Completed
Using Data Science and Edge Computing for Debris Flow Warning
Climate & Environment
Academia

CHUV: Heracles - Sepsis Model

Completed
CHUV: Improving Sepsis detection and quality of care with AI
Health & Biomedical
Public sector

AI-Driven Political Monitoring

Completed
Legislative tracking for labor advocacy at Kaufmännischer Verband Schweiz
Digital Society
Private sector

LUCID National Data Stream

In Progress
Low Value of Care in Medical Hospitalized Patients - a National Data Stream on Quality of Care in Swiss University Hospitals
Health & Biomedical
Public sector
Academia

More projects

No results found.
There are no results with this criteria. Try changing your search.
No result

News

Latest news

Coding the Future: Energy Data Hackdays Expand to French-speaking Switzerland
May 7, 2026

Coding the Future: Energy Data Hackdays Expand to French-speaking Switzerland

Coding the Future: Energy Data Hackdays Expand to French-speaking Switzerland

Held at the SDSC headquarters at Biopôle, the Energy Data Hackdays gather 100 experts to tackle 5 energy and grid challenges.
Science des données : le SDSC et le Canton de Vaud soutiennent quatre projets appliqués
April 30, 2026

Science des données : le SDSC et le Canton de Vaud soutiennent quatre projets appliqués

Science des données : le SDSC et le Canton de Vaud soutiennent quatre projets appliqués

Le SDSC et le Canton de Vaud ont retenu quatre projets parmi les 57 soumissions reçues lors de leur deuxième appel à projets.
Le Swiss Data Science Center inaugure son siège au Biopôle de Lausanne
March 12, 2026

Le Swiss Data Science Center inaugure son siège au Biopôle de Lausanne

Le Swiss Data Science Center inaugure son siège au Biopôle de Lausanne

Le SDSC inaugure aujourd'hui son siège au campus Biopôle de Lausanne, dans le cadre d'un partenariat stratégique avec l'État de Vaud.

Contact us

Let’s talk Data Science

Do you need our services or expertise?
Contact us for your next Data Science project!