Evaluation of Parameters Collected From Routine Data for the Diagnosis of Sepsis and Septic Shock and Their Influence on Time to Diagnosis and Patient Outcome

Recruiting

• Conditions: Sepsis; Septic Shock

• Registration Number: NCT05383963
• Lead Sponsor: Charite University, Berlin, Germany

Brief Summary

Retrospective observational study to develop a Machine Learning Algorithm to evaluate parameters collected from routine data for the diagnosis of sepsis and septic shock and their influence on time to diagnosis and patient outcome.

Detailed Description

Retrospective routine data from the medical records of the department of anesthesiology and operative intensive care from 01. 01. 2007 to 31. 12. 2021 are analyzed in digital form.

The first step is the development of a machine learning algorithm (MLA). This MLA will be validated and analyzed for his predictive value with regard to early diagnosis of sepsis/septic shock depending on the conceptual value of detection variables (Sepsis-3 vs. SIRS). Further analysis will focus on improvement of accuracy for the MLA and the effect of these detection variables on quality of treatment processes and also on economic consequences like cost and revenue.

Timeline:

1. Conception and development of the ML Algorithm (6 months)

2. Identification and diagnostic validation of sepsis patients (6 months)

3. Secondary analyses (36 months)

Study Timeline

• Study First Submitted: 2022-05-17
• Study First Submitted QC: 2022-05-17
• Study First Posted: 2022-05-20
• Study Start: 2022-07-15
• Status Verified: 2025-02
• Last Update Submitted: 2025-02-12
• Last Update Posted: 2025-02-13
• Primary Completion: 2025-09
• Study Completion: 2027-12

Recruitment & Eligibility

• Status: RECRUITING
• Sex: All
• Target Recruitment: 10000

Inclusion Criteria

• age >= 18 years
• ICU stay of > 24 hours

Exclusion Criteria

• none

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Sepsis/septic shock	01.01.2007 -31.12.2021	Development of a machine learning algorithm (MLA) for the prediction of sepsis/septic shock from hospital routine data.

Secondary Outcome Measures

Name	Time	Method
Predictive accuracy	01.01.2007 -31.12.2021	Evaluation of the predictive accuracy (= predictive value) of the respective sepsis diagnostic algorithm (i.e. comparison of the concepts SIRS and Sepsis-3)
Diagnostic accuracy	01.01.2007 -31.12.2021	Identification of additional variables for diagnostic accuracy (laboratory values, clinical parameters and vital-sign monitor parameters and other relevant health data
Performance indicators	01.01.2007 -31.12.2021	Evaluation of performance indicators of clinical routine processes (Intensive care quality indicators)
Case costs	01.01.2007 -31.12.2021	Case costs related to hospitalization
Revenues	01.01.2007 -31.12.2021	Revenues related to hospitalization

Trial Locations

Locations (1)

Department of Anesthesiology and Operative Intensive Care Medicine CCM/CVK, Charité - Universitätsmedizin Berlin; 🇩🇪 Berlin, Germany