Machine learning identification of specific changes in myeloid cell phenotype during bloodstream infections

• Published in: Scientific reports Vol. 11; no. 1; p. 20288
• Main Authors: Gosset, Christian, Foguenne, Jacques, Simul, Mickaël, Tomsin, Olivier, Ammar, Hayet, Layios, Nathalie, Massion, Paul B., Damas, Pierre, Gothot, André
• Format: Journal Article Web Resource
• Language: English
• Published: London Nature Publishing Group UK 13.10.2021; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1305; 631/114/2413; 631/1647/1407/1492; 631/250/2504/133; 631/250/2504/223; 631/250/2504/342; 631/250/254; 692/308/53/2423; 692/420/256; 692/420/256/1980; Adult; Aged; Algorithms; Area Under Curve; Bacteremia; Bacteremia - diagnosis; Biomarkers - metabolism; Blood culture; CD123 antigen; CD14 antigen; CD16 antigen; Cell culture; Critical Care; Dendritic cells; Dendritic Cells - cytology; Female; Flow Cytometry; Genotype & phenotype; GPI-Linked Proteins - metabolism; Granulocytes - cytology; Heart surgery; Hematology; Human health sciences; Humanities and Social Sciences; Humans; Hématologie; Immunophenotyping; Inflammation; Intensive Care Units; Interleukin-3 Receptor alpha Subunit - metabolism; Learning algorithms; Leukocytes (neutrophilic); Lipopolysaccharide Receptors - metabolism; Machine Learning; Macrophages - cytology; Male; Middle Aged; Monocytes; Monocytes - cytology; multidisciplinary; Myeloid cells; Myeloid Cells - metabolism; Neutrophils; Nosocomial infection; Nosocomial infections; Patients; Phenotype; Phenotypes; Receptors, IgG - metabolism; ROC Curve; Science; Science (multidisciplinary); Sciences de la santé humaine; Sepsis - physiopathology
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-021-99628-8

The early identification of bacteremia is critical for ensuring appropriate treatment of nosocomial infections in intensive care unit (ICU) patients. The aim of this study was to use flow cytometric data of myeloid cells as a biomarker of bloodstream infection (BSI). An eight-color antibody panel was used to identify seven monocyte and two dendritic cell subsets. In the learning cohort, immunophenotyping was applied to (1) control subjects, (2) postoperative heart surgery patients, as a model of noninfectious inflammatory responses, and (3) blood culture-positive patients. Of the complex changes in the myeloid cell phenotype, a decrease in myeloid and plasmacytoid dendritic cell numbers, increase in CD14 + CD16 + inflammatory monocyte numbers, and upregulation of neutrophils CD64 and CD123 expression were prominent in BSI patients. An extreme gradient boosting (XGBoost) algorithm called the “infection detection and ranging score” (iDAR), ranging from 0 to 100, was developed to identify infection-specific changes in 101 phenotypic variables related to neutrophils, monocytes and dendritic cells. The tenfold cross-validation achieved an area under the receiver operating characteristic (AUROC) of 0.988 (95% CI 0.985–1) for the detection of bacteremic patients. In an out-of-sample, in-house validation, iDAR achieved an AUROC of 0.85 (95% CI 0.71–0.98) in differentiating localized from bloodstream infection and 0.95 (95% CI 0.89–1) in discriminating infected from noninfected ICU patients. In conclusion, a machine learning approach was used to translate the changes in myeloid cell phenotype in response to infection into a score that could identify bacteremia with high specificity in ICU patients.