The role of serum C-reactive protein in the diagnosis of periprosthetic shoulder infection

Abstract

Introduction: There is a paucity of literature regarding serum C-reactive protein (CRP) in the evaluation of a shoulder periprosthetic joint infection (PJI). The purpose of the current study was to establish cutoff values for diagnosing shoulder PJI and evaluate the influence of the type of infecting microorganism and the classification subgroups according to last proposed International Consensus Meeting (ICM) criteria on the CRP level.

Materials and methods: A retrospective analysis of all 136 patients, who underwent septic or aseptic revision shoulder arthroplasty in our institution between January 2010 and December 2019, was performed. Shoulder PJI was defined according to the last proposed definition criteria of the ICM. Serum CRP levels were compared between infected and non-infected cases, between infection subgroups, as well as between different species of infecting microorganisms. A receiver-operating characteristic (ROC) analysis was performed to display sensitivity and specificity of serum CRP level for shoulder PJI.

Results: A total of 52 patients (38%) were classified as infected, 18 meeting the criteria for definitive infection, 26 for probable infection and 8 for possible infection. According to the ROC curve, an optimized serum CRP threshold of 7.2 mg/l had a sensitivity of 69% and specificity of 74% (area under curve = 0.72). Patients with definitive infection group demonstrated significantly higher median serum CRP levels (24.3 mg/l), when compared to probable, possible infection groups and PJI unlikely group (8 mg/l, 8.3 mg/l, 3.6 mg/l, respectively, p < 0.05). The most common isolated microorganism was Cutibacterium acnes in 25 patients (48%) followed by coagulase-negative staphylococci (CNS) in 20 patients (39%). Patients with a PJI caused by high-virulent microorganisms had a significantly higher median serum CRP level compared to patients with PJI caused by low-virulent microorganisms (48 mg/l vs. 11.3 mg/l, p = 0.04).

Conclusions: Serum CRP showed a low sensitivity and specificity for the diagnosis of shoulder PJI, even applying cutoffs optimized by receiver-operating curve analysis. Low-virulent microorganisms and patients with probable and possible infections are associated with lower CRP levels compared to patients with definitive infection and infections caused by high-virulent microorganisms.

Level of evidence: Diagnostic Level III.

Keywords: C-reactive protein; Definition; Low-virulence; Periprosthetic shoulder infection.

Fig. 1

Receiver-operating characteristics curve for serum C-reactive protein. Sensitivity is plotted against 100% specificity. The red and blue lines mark the sensitivity and 1-specificity for the optimized threshold (Youden’s index) of 7.2 mg/l and ICM definition cutoff of 10 mg/l, respectively

Fig. 2

Box-and-whisker plot showing dependency of serum C-reactive protein (CRP) level on the different periprosthetic joint infection (PJI) classification subgroups. The horizontal black line marks the median CRP level; the box, the interquartile range; and the whiskers, the minimum and maximum. Asterisks indicate groups with significantly higher median CRP levels compared to groups without asterisks

Fig. 3

Box-and-whisker plot showing dependency of serum C-reactive protein (CRP) level on the infecting microorganism and patients with unlikely periprosthetic joint infection (PJI). The horizontal black line marks the median CRP level; the box, the interquartile range; and the whiskers, the minimum and maximum. Asterisks indicate groups with significantly higher median CRP levels compared to groups without asterisks. Staphylococcus aureus, n = 5; coagulase-negative staphylococci (CNS), n = 10; Cutibacterium acnes, n = 14; infection unlikely, n = 84

Fig. 4

Box-and-whisker plot showing dependency of serum C-reactive protein (CRP) level on the virulence of periprosthetic joint infection (PJI). The horizontal black line marks the median CRP level; the box, the interquartile range; and the whiskers, the minimum and maximum. Asterisks indicate groups with significantly higher median CRP levels compared to groups without asterisks. High-virulent PJI, n = 10; low-virulent PJI, n = 36