Personalized Swiss Sepsis Study

Personalized Swiss Sepsis Study: With Machine Learning and Computational Modelling Towards Personalized Sepsis Management - Discovery of Digital Biomarkers

Status

Recruiting

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT04130789

Acronym

PSSS_digital

Enrollment

17500

Registered

2019-10-17

Start date

2019-11-15

Completion date

2025-12-31

Last updated

2025-03-05

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Sepsis

Keywords

clinical data warehouse (CDWH), machine learning, data-driven algorithms, multi-dimensional modelling

Brief summary

This multi-center study is to focus on patients with sepsis in Intensive Care Units (ICUs) in order to better understand the complex host-pathogen interaction and clinical heterogeneity associated with sepsis. Understanding this heterogeneity may allow the development of novel diagnostic approaches. Data from patients will be analyzed using state-of-the art analytical algorithms for biomarker discovery including machine learning and multidimensional mathematical modelling to explore the large datasets generated. In order to discover digital biomarkers for the study endpoints a case-control study design will be used to compare data patterns from patients with sepsis (cases) and those without sepsis (controls).

Interventions

OTHERcompare data patterns by data-driven algorithms to determine sepsis

compare data patterns by data-driven algorithms including machine learning and multi-dimensional modelling to reliably determine sepsis

OTHERcompare data patterns by data-driven algorithms to predict sepsis-related mortality

compare data patterns by data-driven algorithms including machine learning and multi-dimensional modelling to to predict sepsis-related mortality

Study design

Observational model

CASE_CONTROL

Time perspective

PROSPECTIVE

Eligibility

Sex/Gender

ALL

Age

18 Years to No maximum

Healthy volunteers

Inclusion criteria

* Patients admitted to an ICU on a Swiss University Hospital. * Patients expected to stay at least 24h on the ICU Inclusion Criteria (cases) * Present at admission to ICU or subsequent development of sepsis 3.0 criteria Inclusion Criteria (controls) * Patients not fulfilling sepsis definition during the ICU stay

Exclusion criteria

* Decline of general consent or any other negative statement against using data for research. * Patients with a clear elective stay on the ICUs.

Design outcomes

Primary

Measure	Time frame	Description
sepsis-related mortality (sensitivity)	time- series data collected from hospital entry until maximum 12 months after hospital exit (no exact time point specified)	Algorithm to predict sepsis-related mortality (sensitivity)
sepsis-related mortality (specificity)	time- series data collected from hospital entry until maximum 12 months after hospital exit (no exact time point specified)	Algorithm to predict sepsis-related mortality (specificity)
Determination of sepsis	time- series data collected from hospital entry until hospital exit; an average of 1 month (no exact time point specified)	Algorithm to determine sepsis at an early stage (at least 12 hours before classical definitions)

Countries

Switzerland

Contacts

Primary ContactAdrian Egli, PD Dr.

adrian.egli@usb.ch+41 61 556 5749

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026