A multi-platform approach to identify a blood-based host protein signature for distinguishing between bacterial and viral infections in febrile children (PERFORM): a multi-cohort machine learning study

Application of a Machine Learning-Based Classification Approach for Developing Host Protein Diagnostic Models for Infectious Disease

In recent years, infectious disease diagnosis has increasingly turned to host-centered approaches as a complement to pathogen-directed ones. The former, however, typically requires the interpretation of complex multiple biomarker datasets to arrive at an informative diagnostic outcome. This report describes a machine learning (ML)-based classification workflow that is intended as a template for researchers seeking to apply ML approaches for developing host-based infectious disease biomarker classifiers. As an example, we built a classification model that could accurately distinguish between three disease etiology classes: bacterial, viral, and normal in human sera using host protein biomarkers of known diagnostic utility. After collecting protein data from known disease samples, we trained a series of increasingly complex Auto-ML models until arriving at an optimized classifier that could differentiate viral, bacterial, and non-disease samples. Even when limited to a relatively small training set size, the model had robust diagnostic characteristics and performed well when faced with a blinded sample set. We present here a flexible approach for applying an Auto-ML-based workflow for the identification of host biomarker classifiers with diagnostic utility for infectious disease, and which can readily be adapted for multiple biomarker classes and disease states.

Cerebrospinal Fluid Neutrophil Gelatinase-Associated Lipocalin as a Novel Biomarker for Postneurosurgical Bacterial Meningitis: A Prospective Observational Cohort Study

BACKGROUND AND OBJECTIVES

Postneurosurgical bacterial meningitis (PNBM) was a significant clinical challenge, as early identification remains difficult. This study aimed to explore the potential of neutrophil gelatinase-associated lipocalin (NGAL) as a novel biomarker for the early diagnosis of PNBM in patients who have undergone neurosurgery.

METHODS

A total of 436 postneurosurgical adult patients were enrolled in this study. Clinical information, cerebrospinal fluid (CSF), and blood samples were collected. After the screening, the remaining 267 patients were divided into the PNBM and non-PNBM groups, and measured CSF and serum NGAL levels to determine the diagnostic utility of PNBM. Subsequently, patients with PNBM were categorized into gram-positive and gram-negative bacterial infection groups to assess the effectiveness of CSF NGAL in differentiating between these types of infections. We analyzed the changes in CSF NGAL expression before and after anti-infection treatment in PNBM. Finally, an additional 60 patients were included as an independent validation cohort to further validate the diagnostic performance of CSF NGAL.

RESULTS

Compared with the non-PNBM group, CSF NGAL was significantly higher in the PNBM group (305.1 [151.6-596.5] vs 58.5 [30.7-105.8] ng/mL; P < .0001). The area under the curve of CSF NGAL for diagnosing PNBM was 0.928 (95% CI: 0.897-0.960), at a threshold of 119.7 ng/mL. However, there was no significant difference in serum NGAL between the 2 groups (142.5 [105.0-248.6] vs 161.9 [126.6-246.6] ng/mL, P = .201). Furthermore, CSF NGAL levels were significantly higher in patients with gram-negative bacterial infections than those with gram-positive bacteria (P = .023). In addition, CSF NGAL levels decrease after treatment compared with the initial stage of infection (P < .0001). Finally, in this validation cohort, the threshold of 119.7 ng/mL CSF NGAL shows good diagnostic performance with a sensitivity and specificity of 90% and 80%, respectively.

CONCLUSION

CSF NGAL holds promise as a potential biomarker for the diagnosis, early drug selection, and efficacy monitoring of PNBM.

Disease-specific plasma protein profiles in patients with fever after traveling to tropical areas

Fever is common among individuals seeking healthcare after traveling to tropical regions. Despite the association with potentially severe disease, the etiology is often not determined. Plasma protein patterns can be informative to understand the host response to infection and can potentially indicate the pathogen causing the disease. In this study, we measured 49 proteins in the plasma of 124 patients with fever after travel to tropical or subtropical regions. The patients had confirmed diagnoses of either malaria, dengue fever, influenza, bacterial respiratory tract infection, or bacterial gastroenteritis, representing the most common etiologies. We used multivariate and machine learning methods to identify combinations of proteins that contributed to distinguishing infected patients from healthy controls, and each other. Malaria displayed the most unique protein signature, indicating a strong immunoregulatory response with high levels of IL10, sTNFRI and II, and sCD25 but low levels of sCD40L. In contrast, bacterial gastroenteritis had high levels of sCD40L, APRIL, and IFN-γ, while dengue was the only infection with elevated IFN-α2. These results suggest that characterization of the inflammatory profile of individuals with fever can help to identify disease-specific host responses, which in turn can be used to guide future research on diagnostic strategies and therapeutic interventions.