The Florida Scoring System for stratifying children with suspected Sjögren's disease: a cross-sectional machine learning study

BACKGROUND

Childhood Sjögren's disease is a rare, underdiagnosed, and poorly-understood condition. By integrating machine learning models on a paediatric cohort in the USA, we aimed to develop a novel system (the Florida Scoring System) for stratifying symptomatic paediatric patients with suspected Sjögren's disease.

METHODS

This cross-sectional study was done in symptomatic patients who visited the Department of Pediatric Rheumatology at the University of Florida, FL, USA. Eligible patients were younger than 18 years or had symptom onset before 18 years of age. Patients with confirmed diagnosis of another autoimmune condition or infection with a clear aetiological microorganism were excluded. Eligible patients underwent comprehensive examinations to rule out or diagnose childhood Sjögren's disease. We used latent class analysis with clinical and laboratory variables to detect heterogeneous patient classes. Machine learning models, including random forest, gradient-boosted decision tree, partial least square discriminatory analysis, least absolute shrinkage and selection operator-penalised ordinal regression, artificial neural network, and super learner were used to predict patient classes and rank the importance of variables. Causal graph learning selected key features to build the final Florida Scoring System. The predictors for all models were the clinical and laboratory variables and the outcome was the definition of patient classes.

FINDINGS

Between Jan 16, 2018, and April 28, 2022, we screened 448 patients for inclusion. After excluding 205 patients due to symptom onset later than 18 years of age, we recruited 243 patients into our cohort. 26 patients were excluded because of confirmed diagnosis of a disorder other than Sjögren's disease, and 217 patients were included in the final analysis. Median age at diagnosis was 15 years (IQR 11-17). 155 (72%) of 216 patients were female and 61 (28%) were male, 167 (79%) of 212 were White, and 20 (9%) of 213 were Hispanic, Latino, or Spanish. The latent class analysis identified three distinct patient classes: class I (dryness dominant with positive tests, n=27), class II (high symptoms with negative tests, n=98), and class III (low symptoms with negative tests, n=92). Machine learning models accurately predicted patient class and ranked variable importance consistently. The causal graphical model discovered key features for constructing the Florida Scoring System.

INTERPRETATION

The Florida Scoring System is a paediatrician-friendly tool that can be used to assist classification and long-term monitoring of suspected childhood Sjögren's disease. The resulting stratification has important implications for clinical management, trial design, and pathobiological research. We found a highly symptomatic patient group with negative serology and diagnostic profiles, which warrants clinical attention. We further revealed that salivary gland ultrasonography can be a non-invasive alternative to minor salivary gland biopsy in children. The Florida Scoring System requires validation in larger prospective paediatric cohorts.

FUNDING

National Institute of Dental and Craniofacial Research, National Institute of Arthritis, Musculoskeletal and Skin Diseases, National Heart, Lung, and Blood Institute, and Sjögren's Foundation.

A lower prevalence of malignant lymphoma in Sjögren's syndrome patients: A cross-sectional study

OBJECTIVE

This study aims to determine the prevalence and risk factors associated with lymphoma in primary Sjögren's syndrome (pSS).

METHODS

We conducted a cross-sectional study on pSS patients who were registered into the Integrated Data Repository (IDR) at the University of Florida (UF) Health Shands Hospital. The parameters, such as age, sex, race, and smoking status, were included. Lymphoma types in pSS were categorized. The clinical and laboratory features were compared between pSS patients with and those without lymphoma by utilizing the items in the EULAR Sjögren's Syndrome Disease Activity Index (ESSDAI).

RESULTS

Among 1,211,343 patients, we found 6799 patients (0.56%) with lymphomas and 2562 patients (0.21%) with pSS. Out of the 2562 pSS patients, 67 patients (2.6%) were diagnosed with lymphoma. The difference in the clinical and laboratory features listed under the ESSDAI domains between pSS patients with lymphomas and pSS without it was significant (p < 0.05 or 0.01): fever, weight loss, lymphadenopathy, splenomegaly, lacrimal gland diseases, cough, shortness of breath, hematuria, cerebrovascular accident diseases, peripheral nerve involvement due to vasculitis, neutropenia, and thrombocytopenia.

CONCLUSION

We report 2.6% of lymphoma prevalence in pSS, lower than previously reported in the literature.

Characterization of soft tissue tumours with ultrasound, shear wave elastography and MRI

OBJECTIVE

To predict accurately whether a soft tissue mass was benign or malignant and to characterize its type using ultrasound, shear wave elastography and MRI. We hypothesized that with the addition of shear wave elastography, it would be possible to determine a threshold velocity value to classify a lesion as benign or malignant.

MATERIALS AND METHODS

A total of 151 consecutive, consenting adult patients were prospectively recruited to this study in a tertiary referral musculoskeletal oncology centre. All lesions were assessed with ultrasound, including B mode, Doppler and shear wave elastography measurements. One hundred thirty-eight patients also underwent MRI of the lesion. A histological diagnosis was obtained for all lesions.

RESULTS

Malignant lesions were larger than benign lesions and had a greater Doppler activity. There was no useful threshold shear wave velocity to differentiate between benign and malignant lesions. Longitudinal and transverse shear wave velocities were strongly positively correlated with each other. An inverse correlation was shown with lesion size and depth, regardless of whether it was benign or malignant. A logistic regression model combining the ultrasound and MRI characteristics did not confidently classify a lesion as benign or malignant and was inferior to expert opinion.

CONCLUSION

The strongest predictors of malignancy are large lesion size and high vascularity. The combination of all ultrasound characteristics (including shear wave elastography) and MRI features does not confidently classify a lesion as benign or malignant, and histological diagnosis remains the gold standard.

The relationship between abuse, sexually transmitted diseases, & group B streptococcus in childbearing women

PURPOSE

To examine the relationship between abuse, sexually transmitted diseases (STDs) and group B (GBS) infection among childbearing women using Selye's (1978) stress response theory.

DESIGN AND METHODS

Retrospective chart review (n = 205) from two different clinical sites in Washington State, using the Childbearing Health Questionnaire to guide data collection. The women in the sample had an average age of 26.4 years and represented Anglo (81.4%), Hispanic (12%), Native American (3.9%), and African American (2.5%) ethnic groups. Thirty-eight percent ( = 78) reported experiencing physical and/or sexual abuse during their lifetimes and 31% had been diagnosed with an STD.

RESULTS

Abuse was significantly related to STDs, and ethnicity emerged as a significant variable for the Hispanic women participating in this study. Findings indicated that infection with group B was also related to abuse status ( r=.60, p < or =.002) and to presence of herpes simplex virus-2 (r =.468, p<or =.01). Total prevalence of STDs was positively related to abuse ( r=.78, p <or =.000). Abused Hispanic women were more likely to be positive for STDs than were their nonabused counterparts ( p <or =.03).

CLINICAL IMPLICATIONS

The findings support previously published results that abuse is widespread in the United States and that abused women are at increased risk for STDs. These results highlight the need for regular screenings for abuse during healthcare, for abuse is a critical variable to consider when screening for STDs and GBS. STD screening typically occurs during the first prenatal visit and may need to be repeated for high-risk groups.