Multi-Biomarker Prediction Models for Multiple Infection Episodes Following Blunt Trauma

Tsurumi, Amy; Flaherty, Patrick J.; Que, Yok-Ai; Ryan, Colleen M.; Mendoza, April E.; Almpani, Marianna; Bandyopadhaya, Arunava; Ogura, Asako; Dhole, Yashoda V.; Goodfield, Laura F.; Tompkins, Ronald G.; Rahme, Laurence G. (2020). Multi-Biomarker Prediction Models for Multiple Infection Episodes Following Blunt Trauma. iScience, 23(11), p. 101659. Elsevier 10.1016/j.isci.2020.101659

[img]
Preview
Text
1-s2.0-S2589004220308518-main.pdf - Published Version
Available under License Creative Commons: Attribution-Noncommercial-No Derivative Works (CC-BY-NC-ND).

Download (2MB) | Preview

Severe trauma predisposes patients to multiple independent infection episodes (MIIEs), leading to augmented morbidity and mortality. We developed a method to identify increased MIIE risk before clinical signs appear, which is fundamentally different from existing approaches entailing infections' detection after their establishment. Applying machine learning algorithms to genome-wide transcriptome data from 128 adult blunt trauma patients' (42 MIIE cases and 85 non-cases) leukocytes collected ≤48 hr of injury and ≥3 days before any infection, we constructed a 15-transcript and a 26-transcript multi-biomarker panel model with the least absolute shrinkage and selection operator (LASSO) and Elastic Net, respectively, which accurately predicted MIIE (Area Under Receiver Operating Characteristics Curve [AUROC] [95% confidence intervals, CI]: 0.90 [0.84-0.96] and 0.92 [0.86-0.96]) and significantly outperformed clinical models. Gene Ontology and network analyses found various pathways to be relevant. External validation found our model to be generalizable. Our unique precision medicine approach can be applied to a wide range of patient populations and outcomes.

Item Type:

Journal Article (Original Article)

Division/Institute:

04 Faculty of Medicine > Department of Intensive Care, Emergency Medicine and Anaesthesiology (DINA) > Clinic of Intensive Care

UniBE Contributor:

Que, Yok-Ai

Subjects:

600 Technology > 610 Medicine & health

ISSN:

2589-0042

Publisher:

Elsevier

Language:

English

Submitter:

Jsabelle Arni

Date Deposited:

02 Dec 2020 12:19

Last Modified:

02 Dec 2020 12:26

Publisher DOI:

10.1016/j.isci.2020.101659

PubMed ID:

33047099

BORIS DOI:

10.7892/boris.148818

URI:

https://boris.unibe.ch/id/eprint/148818

Actions (login required)

Edit item Edit item
Provide Feedback