A machine learning and centrifugal microfluidics platform for bedside prediction of sepsis
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.
Authors
- Peter Zhang (ORCID: https://orcid.org/0000-0003-0557-3572)
- Manjeet Bains
- Byeong‐Ui Moon (ORCID: https://orcid.org/0000-0003-3791-7747)
- Uriel Trahtemberg (ORCID: https://orcid.org/0000-0001-9103-2494)
- Matthias Geißler (ORCID: https://orcid.org/0000-0002-8838-5528)
- Jim Tsoporis
- Lidija Malic (ORCID: https://orcid.org/0000-0001-8594-9191)
- Dillon Da Fonte
- Evan F. Haney (ORCID: https://orcid.org/0000-0003-3645-770X)
- D. Brassard (ORCID: https://orcid.org/0000-0001-5183-6455)
- Liviu Clime
- Pamela Plant (ORCID: https://orcid.org/0000-0002-3781-4337)
- Robert E. W. Hancock (ORCID: https://orcid.org/0000-0001-5989-8503)
- John C. Marshall (ORCID: https://orcid.org/0000-0002-7902-6291)
- Ljuboje Lukic
- Reza Falsafi
- Maxence Mounier
- Teodor Veres
- Christina Nassif
- Claúdia C. dos Santos (ORCID: https://orcid.org/0000-0002-6446-8791)
- Eryn Churcher (ORCID: https://orcid.org/0009-0006-1269-7492)
- Andrew Baker (ORCID: https://orcid.org/0000-0002-6312-5172)
- Victor Mun-Sing Sit (ORCID: https://orcid.org/0009-0001-8897-6555)
Institutions
- St. Michael's Hospital (CA)
- Bar-Ilan University (IL)
- University of British Columbia (CA)
- University of Toronto (CA)
- University of Victoria (CA)
- Western Galilee Hospital (IL)
- Canada Research Chairs (CA)
- National Research Council Canada (CA)
- McGill University (CA)
Publication Details
- Journal
- Nature Communications
- Published
- 2025-05-27
- DOI
- https://doi.org/10.1038/s41467-025-59227-x
- Citations
- 7
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 9.48
Funders
- California HIV/AIDS Research Program
- Public Health Agency of Canada
- Génome Québec
- Public Health Agency
- Canada Research Chairs
- University of Toronto
- Killam Trusts
- Groupe canadien de recherche en soins intensifs
- Canadian Space Agency
- Canadian Institutes of Health Research
- Natural Sciences and Engineering Research Council of Canada
- CIHR Skin Research Training Centre