A generalizable 29-mRNA neural-network classifier for acute bacterial and viral infections.

Autor: Mayhew MB; Inflammatix, Inc., 863 Mitten Rd, Suite 104, Burlingame, CA, 94010, USA., Buturovic L; Inflammatix, Inc., 863 Mitten Rd, Suite 104, Burlingame, CA, 94010, USA., Luethy R; Inflammatix, Inc., 863 Mitten Rd, Suite 104, Burlingame, CA, 94010, USA., Midic U; Inflammatix, Inc., 863 Mitten Rd, Suite 104, Burlingame, CA, 94010, USA., Moore AR; Department of Medicine, Stanford University, Palo Alto, CA, 94305, USA., Roque JA; Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, Stanford University, Palo Alto, CA, 94305, USA., Shaller BD; Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, Stanford University, Palo Alto, CA, 94305, USA., Asuni T; Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, Stanford University, Palo Alto, CA, 94305, USA., Rawling D; Inflammatix, Inc., 863 Mitten Rd, Suite 104, Burlingame, CA, 94010, USA., Remmel M; Inflammatix, Inc., 863 Mitten Rd, Suite 104, Burlingame, CA, 94010, USA., Choi K; Inflammatix, Inc., 863 Mitten Rd, Suite 104, Burlingame, CA, 94010, USA., Wacker J; Inflammatix, Inc., 863 Mitten Rd, Suite 104, Burlingame, CA, 94010, USA., Khatri P; Institute for Immunity, Transplantation and Infections, Stanford University, Palo Alto, CA, 94305, USA.; Center for Biomedical Informatics Research, Department of Medicine, Stanford University, Palo Alto, CA, 94305, USA., Rogers AJ; Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, Stanford University, Palo Alto, CA, 94305, USA., Sweeney TE; Inflammatix, Inc., 863 Mitten Rd, Suite 104, Burlingame, CA, 94010, USA. tsweeney@inflammatix.com.
Jazyk: angličtina
Zdroj: Nature communications [Nat Commun] 2020 Mar 04; Vol. 11 (1), pp. 1177. Date of Electronic Publication: 2020 Mar 04.
DOI: 10.1038/s41467-020-14975-w
Abstrakt: Improved identification of bacterial and viral infections would reduce morbidity from sepsis, reduce antibiotic overuse, and lower healthcare costs. Here, we develop a generalizable host-gene-expression-based classifier for acute bacterial and viral infections. We use training data (N = 1069) from 18 retrospective transcriptomic studies. Using only 29 preselected host mRNAs, we train a neural-network classifier with a bacterial-vs-other area under the receiver-operating characteristic curve (AUROC) 0.92 (95% CI 0.90-0.93) and a viral-vs-other AUROC 0.92 (95% CI 0.90-0.93). We then apply this classifier, inflammatix-bacterial-viral-noninfected-version 1 (IMX-BVN-1), without retraining, to an independent cohort (N = 163). In this cohort, IMX-BVN-1 AUROCs are: bacterial-vs.-other 0.86 (95% CI 0.77-0.93), and viral-vs.-other 0.85 (95% CI 0.76-0.93). In patients enrolled within 36 h of hospital admission (N = 70), IMX-BVN-1 AUROCs are: bacterial-vs.-other 0.92 (95% CI 0.83-0.99), and viral-vs.-other 0.91 (95% CI 0.82-0.98). With further study, IMX-BVN-1 could provide a tool for assessing patients with suspected infection and sepsis at hospital admission.
Databáze: MEDLINE
Externí odkaz: