Performance of C-reactive protein and procalcitonin to distinguish viral from bacterial and malarial causes of fever in Southeast Asia

Abstract

Background: Poor targeting of antimicrobial drugs contributes to the millions of deaths each year from malaria, pneumonia, and other tropical infectious diseases. While malaria rapid diagnostic tests have improved use of antimalarial drugs, there are no similar tests to guide the use of antibiotics in undifferentiated fevers. In this study we estimate the diagnostic accuracy of two well established biomarkers of bacterial infection, procalcitonin and C-reactive protein (CRP) in discriminating between common viral and bacterial infections in malaria endemic settings of Southeast Asia.

Methods: Serum procalcitonin and CRP levels were measured in stored serum samples from febrile patients enrolled in three prospective studies conducted in Cambodia, Laos and, Thailand. Of the 1372 patients with a microbiologically confirmed diagnosis, 1105 had a single viral, bacterial or malarial infection. Procalcitonin and CRP levels were compared amongst these aetiological groups and their sensitivity and specificity in distinguishing bacterial infections and bacteraemias from viral infections were estimated using standard thresholds.

Results: Serum concentrations of both biomarkers were significantly higher in bacterial infections and malaria than in viral infections. The AUROC for CRP in discriminating between bacterial and viral infections was 0.83 (0.81-0.86) compared with 0.74 (0.71-0.77) for procalcitonin (p < 0.0001). This relative advantage was evident in all sites and when stratifying patients by age and admission status. For CRP at a threshold of 10 mg/L, the sensitivity of detecting bacterial infections was 95% with a specificity of 49%. At a threshold of 20 mg/L sensitivity was 86% with a specificity of 67%. For procalcitonin at a low threshold of 0.1 ng/mL the sensitivity was 90% with a specificity of 39%. At a higher threshold of 0.5 ng/ul sensitivity was 60% with a specificity of 76%.

Conclusion: In samples from febrile patients with mono-infections from rural settings in Southeast Asia, CRP was a highly sensitive and moderately specific biomarker for discriminating between viral and bacterial infections. Use of a CRP rapid test in peripheral health settings could potentially be a simple and affordable measure to better identify patients in need of antibacterial treatment and part of a global strategy to combat the emergence of antibiotic resistance.

Fig. 1

Boxplots for the distribution of procalcitonin and CRP readings in the three sites, and data points for procalcitonin and CRP levels in viral infections, rickettsia/leptospira, bacteraemia and malaria. Abbreviation: PCT, Procalcitonin; CRP, C reactive protein

Fig. 2

Receiver operating characteristic curves for procalcitonin and CRP in discriminating between aetiological groups. On the horizontal axis is the sensitivity of the biomarkers and on the vertical axis is the false positive rate (1-specificity). Abbreviations: PCT, Procalcitonin; CRP, C reactive protein; ROC, receiver operating characteristic curve

Fig. 3

AUROC for Procalcitonin and C-reactive protein levels by admission status and age group

Fig. 4

Procalcitonin and C-reactive protein levels in the four aetiological groups by site. Abbreviation: AUROC—area under the receiver operating curve; CRP—C-reactive protein