Language selection

Government of Canada / Gouvernement du Canada

Search

A machine learning and centrifugal microfluidics platform for bedside prediction of sepsis

From National Research Council Canada

Download
DOIResolve DOI: https://doi.org/10.1038/s41467-025-59227-x
AuthorSearch for: 1ORCID identifier: https://orcid.org/0000-0001-8594-9191; Search for: ; Search for: ; Search for: 1ORCID identifier: https://orcid.org/0000-0002-1786-0803; Search for: 1; Search for: 1; Search for: ; Search for: 1ORCID identifier: https://orcid.org/0000-0003-3791-7747; Search for: 1ORCID identifier: https://orcid.org/0009-0001-8897-6555; Search for: 1ORCID identifier: https://orcid.org/0000-0001-5183-6455; Search for: 1; Search for: ORCID identifier: https://orcid.org/0009-0006-1269-7492; Search for: ; Search for: ; Search for: ; Search for: ; Search for: ORCID identifier: https://orcid.org/0000-0001-9103-2494; Search for: 1; Search for: ORCID identifier: https://orcid.org/0000-0002-7902-6291; Search for: 1ORCID identifier: https://orcid.org/0000-0002-8838-5528; Search for: ORCID identifier: https://orcid.org/0000-0001-5989-8503; Search for: 1ORCID identifier: https://orcid.org/0000-0002-9594-8042; Search for: ORCID identifier: https://orcid.org/0000-0002-6446-8791
Affiliation
  1. National Research Council of Canada. Medical Devices
FunderSearch for: CIHR Skin Research Training Centre; Search for: Canada Research Chairs
FormatText, Article
Abstract
Sepsis is a life-threatening organ dysfunction due to a dysfunctional response to infection. Delays in diagnosis have substantial impact on survival. Herein, blood samples from 586 in-house patients with suspected sepsis are used in conjunction with machine learning and cross-validation to define a six-gene expression signature of immune cell reprogramming, termed Sepset, to predict clinical deterioration within the first 24 h (h) of clinical presentation. Prediction accuracy (~90% in early intensive care unit (ICU) and 70% in emergency room patients) is validated in 3178 patients from existing independent cohorts. A RT-PCR-based Sepset detection test shows a 94% sensitivity in 248 patients to predict worsening of the sequential organ failure assessment scores within the first 24 h. A stand-alone centrifugal microfluidic instrument that automates whole-blood Sepset classifier detection is tested, showing a sensitivity of 92%, and specificity of 89% in identifying the risk of clinical deterioration in patients with suspected sepsis.
Publication date
PublisherNature
Licence
In
  • Nature Communications 16, no. 1, 4442 (27 May 2025).
LanguageEnglish
Peer reviewedYes
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifier17a81d26-cacf-4df6-ba93-8daae1f219e9
Record created2025-05-29
Record modified2025-05-29
Date modified: