Using machine learning and centrifugal microfluidics at the point-of-need to predict clinical deterioration of patients with suspected sepsis within the first 24 h.

From National Research Council Canada

Download	View author's version: Using machine learning and centrifugal microfluidics at the point-of-need to predict clinical deterioration of patients with suspected sepsis within the first 24 h. (PDF, 6.2 MiB)
DOI	Resolve DOI: https://doi.org/10.1101/2024.10.08.24314844
Author	Search for: Malic, Lidija¹ORCID identifier: https://orcid.org/0000-0001-8594-9191; Search for: Zhang, Peter G. Y.ORCID identifier: https://orcid.org/0000-0003-0557-3572; Search for: Plant, Pamela ORCID identifier: https://orcid.org/0000-0002-3781-4337; Search for: Clime, Liviu¹ORCID identifier: https://orcid.org/0000-0002-1786-0803; Search for: Nassif, Christina¹; Search for: Da Fonte, Dillon¹; Search for: Haney, Evan E.; Search for: Moon, Byeong-Ui¹ORCID identifier: https://orcid.org/0000-0003-3791-7747; Search for: Sit, Victor¹; Search for: Brassard, Daniel¹ORCID identifier: https://orcid.org/0000-0001-5183-6455; Search for: Mournier, Maxence; Search for: Chircher, Eryn; Search for: Tsoporis, James T.; Search for: Falsafi, Reza; Search for: Bains, Manjeet; Search for: Baker, Andrew; Search for: Trahtemberg, Uriel ORCID identifier: https://orcid.org/0000-0001-9103-2494; Search for: Lukic, Ljuboje¹; Search for: Marshall, John C.; Search for: Geissler, Matthias¹ORCID identifier: https://orcid.org/0000-0002-8838-5528; Search for: Hancock, Robert E. W.ORCID identifier: https://orcid.org/0000-0001-5989-8503; Search for: Veres, Teodor¹ORCID identifier: https://orcid.org/0000-0002-9594-8042; Search for: dos Santos, Claudia C.ORCID identifier: https://orcid.org/0000-0002-6446-8791
Affiliation	National Research Council Canada. Medical Devices
Format	Text, Preprint
Abstract	Sepsis is the bodys dysfunctional response to infection associated with organ failure. Delays in diagnosis have a substantial impact on survival. Herein, samples from 586 in-house patients were used in conjunction with machine learning and cross-validation to narrow a gene expression signature of immune cell reprogramming to predict clinical deterioration in patients with suspected sepsis within the first 24 hours (h) of clinical presentation using just six genes (Sepset). The accuracy of the test (~90% in early intensive care unit (ICU) and 70% in emergency room patients) was validated in 3,178 patients from existing independent cohorts. A real-time reverse transcriptase polymerase chain reaction (RT-PCR)-based test was shown to have a 98% sensitivity in >230 patients to predict worsening of the sequential organ failure scores or admission to the ICU within the first 24 h following Sepset detection. A stand-alone centrifugal microfluidic instrument that integrates the entire automated workflow for detection of the Sepset classifier in whole blood using digital droplet PCR was developed and tested. This PREcision meDIcine for CriTical care (PREDICT) system had a high sensitivity of 92%, specificity of 89%, and an overall accuracy of 88% in identifying the risk of imminent clinical deterioration in patients with suspected sepsis.
Publication date	2024-10-28
Publisher	medRxiv
Licence	Creative Commons, Attribution-NoDerivatives 4.0 International (CC BY-ND 4.0) http://creativecommons.org/licenses/by-nd/4.0/
Language	English
Peer reviewed	No
Export citation	Export as RIS
Report a correction	Report a correction (opens in a new tab)
Record identifier	cab9add5-0484-4ad2-a24d-534a111ce021
Record created	2025-04-03
Record modified	2025-04-10

Date modified:: 2026-01-22