Machine-learning algorithms define pathogen-specific local immune fingerprints in peritoneal dialysis patients with bacterial infections

• Published in: Kidney international Vol. 92; no. 1; pp. 179 - 191
• Main Authors: Zhang, Jingjing, Friberg, Ida M., Kift-Morgan, Ann, Parekh, Gita, Morgan, Matt P., Liuzzi, Anna Rita, Lin, Chan-Yu, Donovan, Kieron L., Colmont, Chantal S., Morgan, Peter H., Davis, Paul, Weeks, Ian, Fraser, Donald J., Topley, Nicholas, Eberl, Matthias
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.07.2017; Elsevier
• Subjects: Acute Disease; Adolescent; Adult; Aged; Aged, 80 and over; Area Under Curve; Bacteria - classification; Bacteria - immunology; Bacteria - pathogenicity; biomarkers; Biomarkers - metabolism; Case-Control Studies; Clinical Investigation; Female; Gram-Negative Bacterial Infections - diagnosis; Gram-Negative Bacterial Infections - immunology; Gram-Negative Bacterial Infections - metabolism; Gram-Negative Bacterial Infections - microbiology; Gram-Positive Bacterial Infections - diagnosis; Gram-Positive Bacterial Infections - immunology; Gram-Positive Bacterial Infections - metabolism; Gram-Positive Bacterial Infections - microbiology; Host-Pathogen Interactions; Humans; inflammation; Machine Learning; machine learning methods; Male; microbial infection; Middle Aged; Nonlinear Dynamics; Pattern Recognition, Automated; Peptide Mapping - methods; peritoneal dialysis; Peritoneal Dialysis - adverse effects; Peritonitis - diagnosis; Peritonitis - immunology; Peritonitis - metabolism; Peritonitis - microbiology; Point-of-Care Systems; Point-of-Care Testing; Predictive Value of Tests; Reproducibility of Results; ROC Curve; Time Factors; Young Adult; machine learning methods; peritoneal dialysis; microbial infection; inflammation; biomarkers
• ISSN: 0085-2538; 1523-1755; 1523-1755
• DOI: 10.1016/j.kint.2017.01.017

The immune system has evolved to sense invading pathogens, control infection, and restore tissue integrity. Despite symptomatic variability in patients, unequivocal evidence that an individual's immune system distinguishes between different organisms and mounts an appropriate response is lacking. We here used a systematic approach to characterize responses to microbiologically well-defined infection in a total of 83 peritoneal dialysis patients on the day of presentation with acute peritonitis. A broad range of cellular and soluble parameters was determined in peritoneal effluents, covering the majority of local immune cells, inflammatory and regulatory cytokines and chemokines as well as tissue damage–related factors. Our analyses, utilizing machine-learning algorithms, demonstrate that different groups of bacteria induce qualitatively distinct local immune fingerprints, with specific biomarker signatures associated with Gram-negative and Gram-positive organisms, and with culture-negative episodes of unclear etiology. Even more, within the Gram-positive group, unique immune biomarker combinations identified streptococcal and non-streptococcal species including coagulase-negative Staphylococcus spp. These findings have diagnostic and prognostic implications by informing patient management and treatment choice at the point of care. Thus, our data establish the power of non-linear mathematical models to analyze complex biomedical datasets and highlight key pathways involved in pathogen-specific immune responses.