Osteoporosis is a serious health concern in patients with rheumatoid arthritis (RA). Machine learning (ML) models have been increasingly incorporated into various clinical practices, including disease classification, risk prediction, and treatment response. However, only a few studies have focused on predicting osteoporosis using ML in patients with RA. We aimed to develop an ML model to predict osteoporosis using a representative Korean RA cohort database. The KORean Observational study Network for Arthritis (KORONA) database, established by the Clinical Research Center for RA in Korea, was used in this study. Among the 5077 patients registered in KORONA, 2374 patients were included in this study. Four representative ML algorithms were used for the prediction: logistic regression (LR), random forest, XGBoost (XGB), and LightGBM. The accuracy, F1 score, and area under the curve (AUC) of each model were measured. The LR model achieved the highest AUC value at 0.750, while the XGB model achieved the highest accuracy at 0.682. Body mass index, age, menopause, waist and hip circumferences, RA surgery, and monthly income were risk factors of osteoporosis. In conclusion, ML algorithms are a useful option for screening for osteoporosis in patients with RA.

Background/Aims: Using a nationwide cohort, we investigated the cancer risk in Korean patients with gout.Methods: Data were obtained from the Korean National Health Insurance Service Database. Patients with gout were defined as those aged ≥ 20 years who were diagnosed with gout and received anti-gout medication (allopurinol, colchicine, and benzbromarone) between 2008 and 2010. Patients with nail disorders were randomly assigned to a control group (1:1 ratio) after frequency matching for age and sex. Cancer incidence was then investigated between 2012 and 2018. Cox proportional hazard regression analysis was used to investigate the association between gout and cancer after adjusting for concomitant diseases.Results: This study included 179,930 patients with gout and an equal number of matched controls. The incidence of overall cancer was higher in patients with gout than in controls (incidence rate ratio, 1.08). Cox proportional hazards regression analysis showed that gout was associated with a hazard ratio of 1.053 (95% confidence interval ,1.031 to 1.077) after adjusting for concomitant diseases.Conclusions: Gout was associated with a significantly high risk of cancer, especially esophageal, stomach, colon, liver, pancreatic, lung, ovarian, renal, and bladder cancers.

Choi HJ, et al. J Korean Med Sci. 2020 Mar;35(20):e133. https://doi.org/10.3346/jkms.2020.35.e133

We aimed to compare clinical characteristics of patients with and without tophi at the time of the diagnosis of gout and investigate the association of tophi and renal function in gout patients. The patients who were first diagnosed with gout at the Kangwon National University Hospital were retrospectively studied. Patients were divided into 2 groups according to the presence of tophi at the diagnosis. We compared clinical characteristics and the progression of renal dysfunction between the two groups. Of 276 patients, 66 (25.5%) initially presented with tophi. Tophi group was older, had a longer symptom duration, and a higher prevalence of multiple joint involvement than those without tophi. In multivariate logistic regression analysis, prolonged symptom duration and multiple joint involvement were significantly associated with increased risk of formation of tophi. The decline in the eGFR was more prominent in patients with tophi than in those without (− 4.8 ± 14.5 vs. − 0.7 ± 11.9 ml/min/1.73 m²/year, respectively; P = 0.039). The presence of tophi was significantly associated with a rapid decline in the eGFR (β = − 0.136; P = 0.042). In conclusion, the presence of tophi was associated with a rapid declining renal function. Therefore, an early diagnosis and closely monitoring of renal function might be important in gout patients with tophi.

Chung MK, et al. J Korean Med Sci. 2021 Jul;36(32):e208. https://doi.org/10.3346/jkms.2021.36.e208

The epidermal growth factor receptor (EGFR), a member of ErbB receptor tyrosine kinase (RTK) family, is activated through growth factor-induced reorganization of the actin cytoskeleton and subsequent dimerization. We herein explored the molecular mechanism underlying the suppression of ligand-induced EGFR dimerization by CD99 agonists and its relevance to tumor growth in vivo. Epidermal growth factor (EGF) activated the formation of c-Src/focal adhesion kinase (FAK)-mediated intracellular complex and subsequently induced RhoA-and Rac1-mediated actin remodeling, resulting in EGFR dimerization and endocytosis. In contrast, CD99 agonist facilitated FAK dephosphorylation through the HRAS/ERK/PTPN12 signaling pathway, leading to inhibition of actin cytoskeletal reorganization via inactivation of the RhoA and Rac1 signaling pathways. Moreover, CD99 agonist significantly suppressed tumor growth in a BALB/c mouse model injected with MDA-MB-231 human breast cancer cells. Taken together, these results indicate that CD99-derived agonist ligand inhibits epidermal growth factor (EGF)-induced EGFR dimerization through impairment of cytoskeletal reorganization by PTPN12-dependent c-Src/FAK inactivation, thereby suppressing breast cancer growth.