Skip to content

SEPSI Score ©

PREVIA MEDICAL has developed a digital biomarker, SEPSI Score ©, which provides an early warning of sepsis up to 48 hours before the first symptoms appear.

Illustrations Previa 14
Biomarqueurs Sans Fond 4

The sepsis

Sepsis is a generalised inflammatory response associated with infection. If it occurs after an invasive procedure, it is known as a nosocomial infection. Sepsis can be caused by bacteria or certain viruses (SARS-Cov2, H1N1 influenza, etc.).

Sepsis is currently responsible for 60,000 deaths a year in France and 1 in 5 deaths worldwide. Each hour's delay in diagnosis reduces the patient's chances of survival by 7%.

With a 30-day mortality rate of 20-30%*, sepsis is one of the leading causes of death in hospitals worldwide.
A precise algorithm and real-time alerts can significantly reduce the length of stay and mortality rate.

Construction of Digital Biomarkers

Digital biomarkers make it possible to collect precise, real-time information about an individual’s state of health. This data is then transmitted and processed electronically, enabling continuous health monitoring, early detection of changes and prediction of health problems.

Objective of the digital biomarker
First of all, we clearly define the objective of the digital biomarker. What disease or medical condition do we want to diagnose, predict or monitor.
Data collection
We gather data relevant to our project. This may include clinical data: laboratory, medication, history.
Data pre-processing
Before analysing the data, it often needs to be cleaned, normalised and pre-processed to eliminate errors and outliers.
Selecting features
We identify the relevant characteristics or variables in the data that can be used to construct the biomarker.
Model drive
We use a training dataset to validate our model.
Biomarker performance
We evaluate the performance of our numerical biomarker using independent validation datasets. We measure its sensitivity, specificity and positive predictive value.
Clinical validation
Before implementing our digital biomarker in a real clinical setting, we validated it using rigorous clinical studies to prove its effectiveness and reliability.

SEPSI Score © retrospective study

Illustrations Previa 15

The score was validated in collaboration with a partner hospital centre over the course of a 22-month study.

We analysed more than 1,000 beds on all wards, with more than 150 input parameters:

Vital signs, history, medication and laboratory results.

2 Mds
45 127
1 308
5 270

Data analysed





Detected in training


Score validation


Validated by an infectiologist

SEPSI Score © performance

84% of patients with sepsis are detected on average 48 hours before the first symptoms appear

0 %
0 %
Positive predictive value
0 %

SEPSI Score ©

Integrated into the hospital’s business software, SEPSI Score © speeds up medical treatment and alerts healthcare professionals, who can then start treatment earlier, thereby increasing patients’ chances of survival.

Previa Pictos 01

Detects up to 48 hours before the first symptoms appear

Previa Pictos 03

Alerting healthcare professionals

Previa Pictos 04

Risk score calculated every hour

Previa Pictos 05

Dashboard populated with all analysis results

The PREVIA © platform

Discover the features of our solution