Diagnosis Of Septic Arthritis Research Articles

Performance of Multiplex Joint Infection Panel in the Diagnosis of Septic Arthritis

Performance of Multiplex Joint Infection Panel in the Diagnosis of Septic Arthritis

Tryptophanyl tRNA synthetase is an alternative synovial biomarker for diagnosis of septic arthritis in knee joint

BackgroundTo evaluate the diagnostic characteristics of tryptophanyl tRNA synthetase (WRS) for the diagnosis of septic arthritis of the knee joint and to determine whether it is a reliable and sensitive synovial biomarker for discriminating septic arthritis from other types of arthritis.MethodsPatients joint effusions for which septic arthritis was suspected were prospectively recruited between January 2019 and September 2020. A total of 9 patients had septic arthritis, 6 had acute gout attack, 1 had an acute flare of chronic rheumatic arthritis, and 46 had pseudogout or reactive arthropathy. Traditional inflammatory markers were measured, and their diagnostic abilities were compared. Neutrophil count, C-reactive protein (CRP) level, WRS, and human neutrophil α-defensin levels were assessed in the synovial fluids. Demographic parameters and biomarkers with a P < 0.05 in differentiating septic from nonseptic arthritis were included in a multivariable model. A multivariable logistic regression with a stepwise selection was performed to build the final combined model. Receiver operating characteristic curves were used to establish optimal thresholds for the diagnosis of septic arthritis of the knee joint, and the area under the curve was calculated to determine the overall accuracy of these tests compared with patients with nonseptic inflammatory arthritis.ResultsPatients with septic arthritis were more likely to display higher serum WBC and CRP levels, synovial neutrophil counts, and levels of two synovial biomarkers, including WRS and α-defensin. WRS showed the highest specificity (87.5%) and sensitivity (83.3%) with α-defensin among the three synovial biomarkers.ConclusionsSynovial fluid WRS is a relevant biomarker in discriminating septic arthritis from other inflammatory arthritis and should be tested in an independent cohort.Level of evidence: prospective observational study, III.

Septic Arthritis Modeling Using Sonographic Fusion with Attention and Selective Transformation: a Preliminary Study.

Conventionally diagnosing septic arthritis relies on detecting the causal pathogens in samples of synovial fluid, synovium, or blood. However, isolating these pathogens through cultures takes several days, thus delaying both diagnosis and treatment. Establishing a quantitative classification model from ultrasound images for rapid septic arthritis diagnosis is mandatory. For the study, a database composed of 342 images of non-septic arthritis and 168 images of septic arthritis produced by grayscale (GS) and power Doppler (PD) ultrasound was constructed. In the proposed architecture of fusion with attention and selective transformation (FAST), both groups of images were combined in a vision transformer (ViT) with the convolutional block attention module, which incorporates spatial, modality, and channel features. Fivefold cross-validation was applied to evaluate the generalized ability. The FAST architecture achieved the accuracy, sensitivity, specificity, and area under the curve (AUC) of 86.33%, 80.66%, 90.25%, and 0.92, respectively. These performances were higher than using conventional ViT (82.14%) and significantly better than using one modality alone (GS 73.88%, PD 72.02%), with the p-value being less than 0.01. Through the integration of multi-modality and the extraction of multiple channel features, the established model provided promising accuracy and AUC in septic arthritis classification. The end-to-end learning of ultrasound features can provide both rapid and objective assessment suggestions for future clinic use.

Aspirations Dashed: Conventional Synovial Fluid Analysis Is Superior to Synovial Fluid and Blood Neutrophil-to-Lymphocyte Ratios in Diagnosing Pediatric Septic Arthritis of the Hip and Knee.

Recent research suggests that synovial fluid neutrophil-to-lymphocyte ratio (SF-NLR) is a superior diagnostic for pyogenic septic arthritis (SA) in adults compared with synovial fluid white blood cell count (SF-WBC) ≥50,000 cells/μL or ≥90% polymorphonuclear leukocytes (SF-%PMN). Other research also indicates that the neutrophil-to-lymphocyte ratio in the blood (B-NLR) may be of diagnostic significance. However, it is not known whether these findings extend to the pediatric population. Medical records at a large urban tertiary-care children's hospital were queried for emergency department visits between 2012 and 2023, where synovial fluid (SF) analysis was performed to evaluate for SA of the hip or knee. Patients 18 years old and above were excluded. The "conventional composite test" (CCT) for SA was considered positive if SF analysis showed any of the following: (1) SF-WBC ≥50,000 cells/μL, (2) ≥90% PMNs, or (3) organisms reported on gram stain. Patients with aspirate and/or operating room (OR) cultures (or supplemental testing, ie, nucleic acid identification) revealing an offending organism were considered to have culture-positive septic arthritis (CPSA). The remaining patients were considered culture-negative (CN). Serum and SF test data were analyzed to assess their diagnostic utility in identifying CPSA. Receiver operating characteristic (ROC) curves were examined to compare the predictive value of SF-NLR and B-NLR versus conventional indicators of SA. A total of 394 patients met the inclusion criteria. In all, 58.6% (n=231) were male, 67.5% (n=266) involved the knee, and 20.1% (n=79) had CPSA. Those with CPSA had higher ESR and CRP compared with CN patients (P<0.01). Bivariate testing did not show a difference in SF-NLR or B-NLR between those with CPSA and CN patients (P=0.93 and 0.37, respectively). The CCT showed 91% sensitivity and 35% specificity using conventional thresholds. ROC analysis showed that SF-WBC was superior to SF-NLR and B-NLR in the diagnosis of CPSA (AUC=0.71 vs. 0.50 and 0.53, respectively; both P<0.01). Among CCT (+) patients who ended up culture negative, Lyme testing was positive in 48.8% (100/205). In contrast to adults, SF-NLR and B-NLR were not found to be strong diagnostic indicators of SA of the hip or knee in pediatric patients. This may be because competing diagnoses in children come with systemic inflammatory responses similar to that seen in pyogenic SA, while noninfectious conditions that might represent the major alternate diagnoses in adults do not increase systemic inflammatory markers as significantly. Given the high incidence of Lyme disease seen among patients in this study, this topic should be further studied at pediatric centers outside Lyme-endemic areas to better understand the generalizability of these findings. Despite excitement regarding SF-NLR and B-NLR as diagnostics for adult SA, these criteria appear less useful in the diagnosis of pyogenic SA in pediatric patients in Lyme-endemic areas.

Gold-antibody-aptamer complexed electrochemical sensing surface for septic arthritis biomarker determination

Septic arthritis (SA) is more severe in patients with rheumatoid arthritis, joint surgical issues, or a weakened immune system. Timely diagnosis of SA is crucial for effective treatment. Traditional diagnostic methods such as ELISA, white blood cell counting, blood culture, qPCR, and imaging techniques are often less accurate and time-consuming. Researchers are focusing on developing highly sensitive biosensors for SA using blood-based biomarkers. Procalcitonin is a protein and a well-established biomarker for SA. This research focuses on developing a procalcitonin interdigitated electrode (IDE) biosensor using a probe made of an aptamer and antibody-modified gold nanoparticle (AuNP) complex. The probe was attached to the IDE through an amine linker and then interacted with procalcitonin. AuNPs increased the attachment of the aptamer and antibody to the IDE, enabling the detection of procalcitonin at levels as low as 10 ng/mL, with a linear regression curve ranging from 10 to 100 ng/mL [y = 4.0691x - 2.1887; R2 = 0.9937]. Furthermore, procalcitonin-spiked serum elevated the current level with increasing procalcitonin concentrations, while control performances did not enhance the current, indicating the selective and specific detection of procalcitonin. This AuNP-aptamer-antibody complexed biosensor effectively identifies procalcitonin at low levels and aids in the diagnosis of SA.

Concomitant septic and crystal arthropathy: a single-centre 10-year retrospective observational study in New Zealand.

To quantify and characterise patients with coexistent septic arthritis (SA) and crystal arthritis (CA) (SACA) in an emergency department (ED) setting. A single-centre, retrospective, 10-year observational study was conducted at a major referral centre. Patients with a positive joint aspirate for CA or SA carried out in ED, were included. The Newman criteria were utilised to define SA. Of the 567 patients included in the final analysis, 427 had CA and 140 had a final diagnosis of SA. Twenty-three point six percent of patients diagnosed with SA had concomitant CA, while 7.2% of patients diagnosed with CA had concomitant SA. The greatest predisposing factors for SACA were previous history of gout, rheumatoid arthritis, being immunocompromised or having joint metalware. Synovial fluid (SF) white cell count (WCC) showed excellent predictive capability for joint infection with the area under the receiver operating characteristic curves (AUROCs) of 0.81 and 0.87 for SA and SACA respectively. The receiver operating characteristic curves (ROCs) reported a SF WCC cutoff of 32,000/mm3 allowed for 100% sensitivity and approximately 50% specificity. SACA remains a small but important sub-group of patients at risk of misdiagnosis of CA alone. SF WCC of 32,000/mm3 may be a better cutoff than the traditionally accepted 50,000/mm3, possibly warranting inpatient admission for investigation and management of presumed SA.

Investigation and Management of Lower Limb Septic Arthritis in Children: An Update Using the Latest British Orthopaedic Association Standard for Trauma (BOAST) Guidelines.

Septic arthritis is a serious condition in children, with the hip and knee joints most typically affected. Patients typically present with pain, joint swelling, fever, and an inability to bear weight. Early recognition and treatment are crucial, as untreated septic arthritis can lead to serious complications, including sepsis, irreversible joint damage, growth problems, and early-onset arthritis. Clinical signs, inflammatory markers, and imaging are used for the diagnosis of septic arthritis. The mainstay of management includes antibiotic therapy and surgical washout. Long-term follow-up is essential to monitor for complications.

Disseminated septic arthritis caused by Ureaplasma urealyticum in an immunocompromised patient with hypogammaglobulinemia after rituximab therapy

Abstract Purpose Ureaplasma urealyticum is a rare pathogen associated with septic arthritis that predominantly affects patients with hypogammaglobulinemia. Bacterial identification of fastidious organisms is challenging because they are undetectable by routine culture testing. To the best of our knowledge, this is the first report of septic arthritis induced by U. urealyticum infection in Japan. Case description We describe the case of a 23-year-old Japanese female with secondary hypogammaglobulinemia (serum immunoglobulin level &lt; 500 mg/dL), identified 8 years after treatment with rituximab. The patient presented with persistent fever and polyarthritis that were unresponsive to ceftriaxone and prednisolone. Contrast-enhanced computed tomography and gallium-67 scintigraphy revealed effusion and inflammation in the left sternoclavicular, hip, wrist, knee, and ankle joints. Although Gram staining and bacterial culture of the drainage fluid from the left hip joint were negative, the condition exhibited characteristics of purulent bacterial infection. The patient underwent empirical treatment with doxycycline, and her symptoms promptly resolved. Subsequent 16S ribosomal RNA (rRNA) gene sequencing of the joint fluid confirmed the presence of U. urealyticum, leading to the diagnosis of septic arthritis. Combination therapy with doxycycline and azithromycin yielded a favorable recovery from the inflammatory status and severe arthritic pain. Conclusion This case highlights U. urealyticum as a potential causative agent of disseminated septic arthritis, particularly in patients with hypogammaglobulinaemia. The 16S rRNA gene analysis proved beneficial for identifying pathogens in culture-negative specimens, such as synovial fluid, in suspected bacterial infections.

Does rickets carry an increased risk of osteomyelitis and septic arthritis? An aggregated electronic health record data study.

To investigate the prevalence of osteomyelitis and septic arthritis in pediatric patients with rickets, compared to the general population. A retrospective cohort study was conducted using the TriNetX analytics network, which aggregates deidentified electronic health record data from over 105 million US patients. We queried pediatric patients with rickets, based on ICD-10-CM (International Classification of Diseases, Tenth Revision, Clinical Modification) encounter diagnoses. Patients with any ICD-10-CM encounter diagnoses of osteomyelitis or septic arthritis were reported. We established a control cohort of pediatric patients without rickets. Of 7337 pediatric patients (≤18 years old) with a rickets diagnosis, 96 [1.31%, 95% confidence interval (CI): 1.05%-1.57%] had a diagnosis of osteomyelitis and 28 (0.38%, 95% CI: 0.24%-0.52%) had a diagnosis of septic arthritis. In comparison, of the 17 240 604 pediatric patients without a rickets diagnosis, 16 995 (0.10%, 95% CI: 0.10%-0.10%) had a diagnosis of osteomyelitis and 8521 (0.05%, 95% CI: 0.05%-0.05%) had a diagnosis of septic arthritis. The relative risk for an osteomyelitis diagnosis in pediatric patients with a rickets diagnosis was 13.27 (95% CI: 10.86-16.23), while the relative risk for a septic arthritis diagnosis was 7.72 (95% CI: 5.33-11.18). Pediatric patients with a diagnosis of rickets have over 10- and 5-times higher relative risks for having a diagnosis of osteomyelitis and septic arthritis, respectively, compared to those without a diagnosis of rickets. This is the first study to explore musculoskeletal infections in rickets patients, highlighting the importance of clinicians being vigilant about these conditions.

Arthrocentesis of suspected septic sternoclavicular arthritis: microbial yield and predictors of culture positivity.

Evaluate the microbial yield and factors predicting culture positivity for image-guided arthrocentesis of suspected septic sternoclavicular (SC) arthritis. An electronic health record search identified image-guided SC joint aspirations for suspected septic arthritis. Data was extracted by retrospective chart review including patient demographics, procedure characteristics, pre-procedure lab testing, joint culture results, final SC joint diagnoses and any effect of positive synovial cultures on subsequent antibiotic therapy. Factors associated with positive joint fluid cultures were assessed using a Chi-squared test for categorical predictors and logistic regression for continuous predictors. A total of 31 SC arthrocenteses met inclusion criteria with most (81%) performed using ultrasound guidance. Synovial fluid was successfully aspirated in 19/31 (61%) of cases, and in all other cases lavage fluid was successfully obtained. Synovial cultures were positive in 9/31 (29%) of cases. A final diagnosis of septic arthritis was assigned to 20/31 cases (65%) in which 9/20 (45%) had positive synovial cultures. There was no statistically significant association between synovial culture positivity and risk factors for septic arthritis, positive blood cultures, pre-aspiration antibiotics and whether synovial fluid or lavage fluid was cultured. Serum white blood cell count (WBC) and erythrocyte sedimentation rate (ESR) demonstrated statistically significant positive correlation with positive synovial cultures. Arthrocentesis is effective for microbial speciation in SC septic arthritis, and diagnostic yield may be increased with lavage when encountering a dry tap. Normal serum WBC and ESR values indicate an extremely low likelihood of positive synovial cultures.

Investing Neonatal Septic Arthritis: A Systematic Review

Background and Objectives: Septic arthritis is an uncommon condition in neonates. It is a serious disorder, especially because of the possibility of sequelae, if not identified and treated early. In addition, due to the rarity of this condition in neonates and the paucity of signs and symptoms, the diagnosis of septic arthritis is more difficult in older children. The published literature is limited to case series, which is why the purpose of this systematic review is to provide a comprehensive summary of neonatal septic arthritis based on the existing literature. This study identifies the changing trends over time, specifically focusing on intravenous cannulation as a major risk factor that led to the undertaking of the study. Methods: The preferred reporting items for systematic reviews and meta-analyses protocol guidelines were used in this study. Three search engines were used for 239 articles. A total of 26 studies were screened in full text, of which 16 articles underwent quantitative analysis. Due to limited data and heterogeneous reporting, the data were summarized descriptively. Results: The total number of babies and joints studied was 307 and 313, respectively, of which the proportion of male babies was mentioned in 12 case series, accounting for 136(228) (60% [42%-71%]) subjects. The most common presenting symptoms were swelling at the involved joint, erythema, and decreased range of motion in variable order. The most common site of involvement was the hip joint (42%), followed by the knee joint (27%). Staphylococcus aureus (40%) was the most commonly cultured pathogen, followed by Klebsiella (18%). Antibiotics were reported in only 12% (38 babies) of the cases. Open surgery was performed on 16% of the 49 babies. The rest of the babies responded to joint aspiration and irrigation, with or without immobilization. Prompt laboratory and radiographic evaluations could help reduce delays in diagnosis and improve outcomes. Blood and tissue cultures were positive in most of the cases. Previous culture reports for the same unit guide the addition of empirical antibiotics. Conclusions: In our case series, the majority of the babies were premature. The most common joint involved is the hip joint. The most common underlying cause is sepsis and catheterization. Intravenous canulation is also a major risk factor because of the continuity of metaphysis and epiphysial vessels. The most common presenting symptom is local signs. Unexplained fever and irritability make it better to look for a local examination of joints. Follow-up is mandatory as a long-term sequel is more.

Neutrophil-Lymphocyte Ratio in Septic Arthritis Diagnosis and Treatment Follow-Up

Neutrophil-Lymphocyte Ratio in Septic Arthritis Diagnosis and Treatment Follow-Up

Perfusion Changes in Acute Septic Arthritis of the Hip Joint During Infancy Using Doppler USG.

To quantitatively assess vascularity changes of acute septic hips in infants using Doppler ultrasonography. To compare these findings with asymptomatic hips, and establish a correlation for accurate diagnosis between these findings. In this prospective case-control study, we included all children under 1year of age with a diagnosis of acute septic arthritis of the hip in the case group. For the control group, we enrolled apparently healthy, full-term neonates and infants not affected with any hip pathology. Doppler ultrasound of the medial femoral circumflex artery of the hip joint was done using a single Phillips HDI 5000 sonography machine. Following parameters were studied: peak systolic velocity (PSV), resistive index (RI), pulsatility index (PI), and systolic to diastolic ratio (SD ratio). Doppler signals and spectral waveforms were obtainable in 100% of hips in both groups. A statistically significant difference was found between the cases and controls with respect to their PSVs, RIs, PIs and SD ratios. The most striking difference was found between the PSVs of the two groups, whose mean was 6.18 in the control group and 11.8 in the case group. No significant correlation between age/gender and any of the 4 parameters was found. Doppler parameters are useful in raising suspicion of onset in the diagnosis of septic arthritis. No correlation was found between age or gender and any parameter in control group. These baseline values can be held valid for all children below the age of 7months.

1694. Joint Fluid Cell Count of Septic Arthritis Patients Diagnosed with Positive Culture in Children

Abstract Background Septic arthritis is one of serious pediatric infections that could result motor comorbidities. Historically, joint fluid cell count of 50,000 and over cells/mm3 has been used for presumptive diagnosis of septic arthritis while awaiting for culture result. Our aim of study was to evaluate joint fluid cell count for diagnosis among septic arthritis patients confirmed with positive culture in children. Methods Patients with septic arthritis were included at Tokyo Metropolitan Children's Medical Center from March 2010 to March 2023. Septic arthritis was confirmed with positive joint fluid culture for a pathogenic organism. Patients with negative joint fluid culture and patients without joint fluid cell count were excluded. Electrical charts were retrospectively reviewed for demographic data, timing of arthrocentesis, culture result and joint fluid cell count. Results A total of 95 patients with septic arthritis were identified. After excluding patients with negative culture and without joint fluid cell count, 22 patients were included for our study. Median age was 5 (IQR: 2-10) years old. Girl ratio was 45%. The median joint fluid cell count was 19,575 (IQR: 6,806-47,388) cells/mm3. Patients with 50,000 and over cells/mm3 was 23%. The median time from onset to arthrocentesis was 3 (IQR: 2-5) days. The isolated organisms were methicillin-susceptible Staphylococcus aureus (50%), methicillin-resistant S. aureus (9%) and Streptococcus pyogenes (27%), Streptococcus pneumoniae (5%), Klebsiella pneumoniae (5%) and Salmonella spp (5%). The infected joints were hip (59%), knee (23%), ankle (14%), elbow (5%) and shoulder (5%). One patient had hip and ankle arthritis. Nine patients were complicated with septic osteomyelitis. The Pearson correlation coefficient between days from onset of symptoms to puncture and the number of joint cells was 0.093 (p=0.681). (Figure 1) Conclusion Majority of patients with septic arthritis confirmed with joint fluid culture did not exceed joint fluid cell 50,000 cells/mm3. Disclosures All Authors: No reported disclosures

164 The Diagnostic Utility of Hip Ultrasound in the Diagnosis of Septic Arthritis of the Hip in Pediatric Patients

164 The Diagnostic Utility of Hip Ultrasound in the Diagnosis of Septic Arthritis of the Hip in Pediatric Patients

How reliable are the synovial cell count and blood parameters in the diagnosis of septic arthritis?

This study aims to investigate the reliability of the joint fluid cell count and blood parameters compared to the culture results in the diagnosis of septic arthritis (SA). A total of 192 patients (112 males, 80 females, mean age: 60.3±19.2 years; range, 18 to 98 years) who presented with SA between January 2018 and July 2022 were evaluated retrospectively. The recorded joint fluid cell count, complete blood count (CBC), white blood cell (WBC) count, serum erythrocyte sedimentation rate (ESR) and serum C-reactive protein (CRP) and culture results were analyzed comparatively according to SA diagnosis. The most commonly involved joint was the knee joint (82.3%), which was affected in 158 patients. Thirty-six (18.8%) of the patients who underwent joint aspiration had positive culture result. The cultures were positive in 10 (35.7%) of 28 patients with synovial WBC value greater than 50,000/mm3, while 26 (15.9%) of 164 patients with a synovial WBC value less than 50,000/mm3 had positive culture results (p=0.013). Patients with SA may present variable blood and synovial parameters. Making decision based on the commonly used synovial WBC count cut-off value of 50,000/mm3 may lead to misdiagnosis. To avoid misdiagnosis or delay in treatment, it is of utmost importance not to exclude the diagnosis acutely, and suspicion of SA should remain even with unlikely values.

Septic arthritis and transient synovitis of the hip

Differentiating between septic arthritis and transient synovitis can be challenging but is very important as alate diagnosis of septic arthritis can lead to sepsis and joint damage. For correct diagnosis and prediction of complications, the right combination of physical examination, laboratory and radiological studies is needed. Hip ultrasound is easy to learn and has ahigh sensitivity for joint effusion. Faster diagnosis and therapy are possible due to increasing use of ultrasound. Magnetic resonance imaging (MRI) is primarily used to rule out co-infections (osteomyelitis, pyomyositis) and differential diagnoses. X‑ray is typically nonremarkable in septic arthritis. Routine use of ultrasound in nontraumatic pediatric hip pain. Generous use of MRI in case of elevated inflammatory markers or inconclusive clinical findings. Using only few sequences may be appropriate to avoid sedation, primarily fluid sensitive sequences (fat-saturated T2, TIRM, STIR), in case of positive findings, accompanied by T1-weighted images.

RISK FACTORS AND CLINICAL PRESENTATION OF SEPTIC ARTHRITIS OF HIP IN INFANTS: A PROSPECTIVE STUDY

Objective: The objective of this study was to analyze the risk factors and clinical presentation of septic arthritis of hip in infants. Methods: Thirty infants with unilateral septic arthritis of hip were included in this study on the basis of a pre-defined inclusion and exclusion criteria. The study was conducted in PIOS Medilinks Pvt. Limited, Jaysingpur, Kolhapur, India. The duration of the study was 18 months from June 2021 to December 2022. The institutional ethical committee approved the study. The diagnosis of septic arthritis was made on the basis of Morrey’s criteria. Risk factors associated with septic arthritis and clinical presentation were studied. Results: Out of the total 30 infants diagnosed to be having septic arthritis of unilateral hip, 17 (57.67%) were males and 13 (43.33%) were females. In our study, an overwhelming majority of the patients belonged to neonatal age group (80%) followed by 1 month–2 months (10%). Only 3 infants were between 2 months and 1 year of age (10%). Low birth weight and prematurity or a combination of these two factors was the most common risk factor in neonates with septic hip arthritis and was seen in 7 (23.33%) patients. All infants having septic arthritis had increased local temperature (100%) and reduced joint movements (100%). Erythema (86.67%), swelling (73.33%), and irritability (60%) were other common clinical features associated with septic arthritis. The most common offending organism was Staphylococcus aureus (33.33%) followed by Klebsiella pneumoniae (13.33%). The analysis of outcome at the end of 3-month follow-up showed that out of 30 studied cases, 28 (93.33%) infants had a painless hip with normal range of motion. Conclusion: Septic arthritis of hip in infants is an emergency and requires prompt treatment. Any delay in diagnosis can have catastrophic consequences. However, in majority of appropriately managed infants, there is no residual damage to the affected joint.

Deep learning-based assessment of knee septic arthritis using transformer features in sonographic modalities

PurposeSeptic arthritis is an infectious disease. Conventionally, the diagnosis of septic arthritis can only be based on the identification of causal pathogens taken from synovial fluid, synovium or blood samples. However, the cultures require several days for the isolation of pathogens. A rapid assessment performed through computer-aided diagnosis (CAD) would bring timely treatment. MethodsA total of 214 non-septic arthritis and 64 septic arthritis images generated by gray-scale (GS) and Power Doppler (PD) ultrasound modalities were collected for the experiment. A deep learning-based vision transformer (ViT) with pre-trained parameters were used for image feature extraction. The extracted features were then combined in machine learning classifiers with ten-fold cross validation in order to evaluate the abilities of septic arthritis classification. ResultsUsing a support vector machine, GS and PD features can achieve an accuracy rate of 86% and 91%, with the area under the receiver operating characteristic curves (AUCs) being 0.90 and 0.92, respectively. The best accuracy (92%) and best AUC (0.92) was obtained by combining both feature sets. ConclusionsThis is the first CAD system based on a deep learning approach for the diagnosis of septic arthritis as seen on knee ultrasound images. Using pre-trained ViT, both the accuracy and computation costs improved more than they had through convolutional neural networks. Additionally, automatically combining GS and PD generates a higher accuracy to better assist the physician's observations, thus providing a timely evaluation of septic arthritis.

LIVER DISEASE IS A RISK FACTOR FOR ACUTE SEPTIC ARTHRITIS: RESULTS FROM A MAJOR TRAUMA CENTRE

A hot swollen joint is a commonly encountered condition in clinical practice. With a broad range of differentials, septic arthritis (SA) is perhaps one of the most concerning. Treated by culture-specific antibiotics and arthroscopic lavage, some patients require multiple washouts. We aimed to determine:(1) What are the risk factors for development of SA?(2) What are the risk factors for repeat washout in SA patients?(3) What are the important clinical differences between a periprosthetic joint infection (PJI) and SA cohort?All patients presenting to the emergency department, orthopaedic, and rheumatology clinics between January 2020 to January 2021 with a hot, swollen joint were retrospectively evaluated. Patients with previous trauma on the ipsilateral joint, with data missing from their medical records in any of the variables required for analysis, &lt;24 months follow-up were excluded.Variables of interest in the three-month period preceding the diagnosis of SA were compared between SA and non-SA patients. Factors with a p-value of p&lt;0.100 in univariate analysis were included in a stepwise multivariate logistic regression model. Similar analyses were performed to compare SA patients with multiple washouts with those needing one washout. Demographical and clinical data for PJI patients were collected to delineate important differences with SA cohort.211 patients were included (SA:28;PJI:24;pseudogout:32;gout:26;others:101). Multivariate analysis showed rheumatoid arthritis (RA), skin infection, and liver disease were risk factors for SA. Amongst patients with septic arthritis, multivariate analysis showed that WBC levels above normal limits (3.6-10.5×109 cells/L) and RA were risk factors for multiple washouts.Between the SA and PJI cohorts, BMI (p=0.002) was significantly lower in the former, whilst WBC level (p=0.023) and CRP (p&lt;0.0001) was significantly higher in the former.Early diagnosis of septic arthritis requires understanding the risk factors, namely RA, skin infection, and liver disease. Considering PJI and septic arthritis as the same entity can lead to wrong clinical judgement, and clinicians should be aware of important differences. We believe that the models in this study are of prognostic value to clinicians who are presented with the common presenting compliant of a hot swollen joint.