An artificial intelligence-powered learning health system to improve sepsis detection and quality of care: a before-and-after study - Summary - MDSpire

An artificial intelligence-powered learning health system to improve sepsis detection and quality of care: a before-and-after study

  • By

  • Jérémie Despraz

  • Raphaël Matusiak

  • Snežana Nektarijevic

  • Valerio Rossetti

  • François Bastardot

  • Rachid Akrour

  • Andreas Konasch

  • Emeline Gauthiez

  • Olivier Pignolet

  • Santino Pepe

  • Jean-Daniel Chiche

  • Daniel E. Kaufmann

  • Thierry Calandra

  • Jean Louis Raisaro

  • Sylvain Meylan

  • January 20, 2026

  • 0 min

Share

Objective:

To develop and validate a Sepsis Learning Health System (SLHS) to support the Lausanne University Hospital's Sepsis Quality of Care Program, focusing on enhancing early detection and treatment of sepsis.

Key Findings:
  • The SLHS included 97,559 hospital stays and 57,180 unique patients by December 2024, with a noted increase in documentation and treatment adherence by X%.
Interpretation:

The SLHS represents a novel approach to sepsis management, leveraging AI to create a continuous feedback loop that enhances clinical decision-making and patient outcomes through systematic data integration.

Limitations:
  • The study relies on retrospective data, which may introduce biases, particularly in patient selection and outcome assessment.
  • The effectiveness of the SLHS in diverse clinical settings remains to be validated, necessitating further research.
Conclusion:

The SLHS has the potential to significantly improve sepsis detection and care quality through systematic data integration and AI-driven insights.

Original Source(s)

An artificial intelligence-powered learning health system to improve sepsis detection and quality of care: a before-and-after study

  • by Jérémie Despraz, Raphaël Matusiak, Snežana Nektarijevic, Valerio Rossetti, François Bastardot, Rachid Akrour, Andreas Konasch, Emeline Gauthiez, Olivier Pignolet, Santino Pepe, Jean-Daniel Chiche, Daniel E. Kaufmann, Thierry Calandra, Jean Louis Raisaro, Sylvain Meylan

  • January 20, 2026

Related Content

Evaluation of the Agata Sepsis® Platform for Molecular Diagnosis of Sepsis in Hospitalized Patients

The 5-Hour Sepsis Test: No Cultures Required

Rapid culture-free test results are consistent with the gold standard for sepsis detection

Efficacy analysis of disitamab vedotin (RC-48) in the treatment of HER2-low metastatic breast cancer: a case report