RESUMO
BACKGROUND: An emerging paradigm suggests that positive Cutibacterium acnes shoulder cultures can result from either true infection or contamination, with true infections demonstrating a host inflammatory response and early culture growth. This clinical retrospective study examines the relationship between C. acnes antigen, C. acnes culture results, and inflammation. METHODS: From January 2021 to July 2023, 1,365 periprosthetic synovial fluid samples from 347 institutions were tested for shoulder infection at a centralized clinical laboratory. A biomarker scoring system based on the 2018 International Consensus Meeting (ICM) definition was utilized to assign each sample an inflammation score. Associations between inflammation, culture results, and C. acnes antigen results were assessed utilizing cluster and correlation analyses. RESULTS: Of 1,365 samples, 1,150 were culture-negative and 215 were culture-positive (94 C. acnes and 121 other organisms). Among the 94 C. acnes culture-positive samples, unsupervised clustering revealed 2 distinct sample clusters (silhouette coefficient, 0.83): a high-inflammation cluster (n = 67) and a low-inflammation cluster (n = 27). C. acnes antigen levels demonstrated moderate-strong positive correlation with inflammation (Spearman ρ, 0.60), with 166-fold higher levels of C. acnes antigen in high-inflammation samples (16.6 signal/cutoff [S/CO]) compared with low-inflammation samples (0.1 S/CO) (p < 0.0001). The days to C. acnes culture positivity demonstrated weak-inverse correlation with inflammation (Spearman ρ = -0.38), with 1.5-fold earlier growth among the 67 high-inflammation samples (6.7 compared with 10.4 days; p < 0.0001). Elevated C. acnes antigen was observed in only 4 (0.38%) of 1,050 low-inflammation culture-negative samples and in only 5 (4.9%) of 103 high-inflammation non-C. acnes-positive cultures. However, 19.0% of high-inflammation, culture-negative samples demonstrated elevated C. acnes antigen. CONCLUSIONS: Synovial fluid C. acnes antigen was detected among shoulder samples with high inflammation and early culture growth, supporting the emerging paradigm that these samples represent true infection. Future research should explore antigen testing to differentiate contamination from infection and to identify culture-negative C. acnes infections. LEVEL OF EVIDENCE: Diagnostic Level III. See Instructions for Authors for a complete description of levels of evidence.
RESUMO
Background and objective The current periprosthetic joint infection (PJI) diagnostic guidelines require clinicians to interpret and integrate multiple criteria into a complex scoring system. Also, PJI classifications are often inconclusive, failing to provide a clinical diagnosis. Machine learning (ML) models could be leveraged to reduce reliance on these complex systems and thereby reduce diagnostic uncertainty. This study aimed to develop an ML algorithm using synovial fluid (SF) test results to establish a PJI probability score. Methods We used a large clinical laboratory's dataset of SF samples, aspirated from patients with hip or knee arthroplasty as part of a PJI evaluation. Patient age and SF biomarkers [white blood cell count, neutrophil percentage (%PMN), red blood cell count, absorbance at 280 nm wavelength, C-reactive protein (CRP), alpha-defensin (AD), neutrophil elastase, and microbial antigen (MID) tests] were used for model development. Data preprocessing, principal component analysis, and unsupervised clustering (K-means) revealed four clusters of samples that naturally aggregated based on biomarker results. Analysis of the characteristics of each of these four clusters revealed three clusters (n=13,133) with samples having biomarker results typical of a PJI-negative classification and one cluster (n=4,032) with samples having biomarker results typical of a PJI-positive classification. A decision tree model, trained and tested independently of external diagnostic rules, was then developed to match the classification determined by the unsupervised clustering. The performance of the model was assessed versus a modified 2018 International Consensus Meeting (ICM) criteria, in both the test cohort and an independent unlabeled validation set of 5,601 samples. The SHAP (SHapley Additive exPlanations) method was used to explore feature importance. Results The ML model showed an area under the curve of 0.993, with a sensitivity of 98.8%, specificity of 97.3%, positive predictive value (PPV) of 92.9%, and negative predictive value (NPV) of 99.8% in predicting the modified 2018 ICM diagnosis among test set samples. The model maintained its diagnostic accuracy in the validation cohort, yielding 99.1% sensitivity, 97.1% specificity, 91.9% PPV, and 99.9% NPV. The model's inconclusive rate (diagnostic probability between 20-80%) in the validation cohort was only 1.3%, lower than that observed with the modified 2018 ICM PJI classification (7.4%; p<0.001). The SHAP analysis found that AD was the most important feature in the model, exhibiting dominance among >95% of "infected" and "not infected" diagnoses. Other important features were the sum of the MID test panel, %PMN, and SF-CRP. Conclusions Although defined methods and tools for diagnosis of PJI using multiple biomarker criteria are available, they are not consistently applied or widely implemented. There is a need for algorithmic interpretation of these biomarkers to enable consistent interpretation of the results to drive treatment decisions. The new model, using clinical parameters measured from a patient's SF sample, renders a preoperative probability score for PJI which performs well compared to a modified 2018 ICM definition. Taken together with other clinical signs, this model has the potential to increase the accuracy of clinical evaluations and reduce the rate of inconclusive classification, thereby enabling more appropriate and expedited downstream treatment decisions.