Search

Background: We investigated the prevalence of and the factors associated with a high risk of osteoporotic fractures in Korean patients with ankylosing spondylitis (AS). Methods: This was a multicenter, retrospective study including 219 AS patients from five university hospitals; the control group was selected by matching age and sex with those of the AS patients. The fracture risk was evaluated based on bone mineral density (BMD) measured by dual-energy X-ray absorptiometry and the fracture risk assessment tool (FRAX) with/without BMD. Results: The mean age of the patients was 47.6 years, and 144 (65.8%) patients were men. According to the WHO criteria and FRAX with/without BMD, the candidates for pharmacological treatment were 44 (20.1%), 20 (13.2%), and 23 (15.1%) patients, respectively, significantly more than those in the healthy control group. Among them, the proportion of patients receiving osteoporosis treatment was 39.1–75%. In logistic regression analysis, menopause was an independent factor for the high risk of fracture according to the WHO criteria and FRAX with/without BMD. C-reactive protein level (odds ratio (OR) 3.8 and OR 6) and glucocorticoid use (OR 1.5 and OR 1.7) were associated with a high risk of osteoporotic fracture based on FRAX without BMD and osteoporosis diagnosed according to the WHO criteria. Conclusions: Our study suggests that both FRAX and WHO criteria may be complementary for treatment decisions to reduce osteoporotic fractures in patients with AS.

Axial spondyloarthritis (axSpA) is a chronic inflammatory disease of the sacroiliac joints. In this study, we develop a method for detecting bone marrow edema by magnetic resonance (MR) imaging of the sacroiliac joints and a deep-learning network. A total of 815 MR images of the sacroiliac joints were obtained from 60 patients diagnosed with axSpA and 19 healthy subjects. Gadolinium-enhanced fat-suppressed T1-weighted oblique coronal images were used for deep learning. Active sacroiliitis was defined as bone marrow edema, and the following processes were performed: setting the region of interest (ROI) and normalizing it to a size suitable for input to a deep-learning network, determining bone marrow edema using a convolutional-neural-network-based deep-learning network for individual MR images, and determining sacroiliac arthritis in subject examinations based on the classification results of individual MR images. About 70% of the patients and normal subjects were randomly selected for the training dataset, and the remaining 30% formed the test dataset. This process was repeated five times to calculate the average classification rate of the five-fold sets. The gradient-weighted class activation mapping method was used to validate the classification results. In the performance analysis of the ResNet18-based classification network for individual MR images, use of the ROI showed excellent detection performance of bone marrow edema with 93.55 ± 2.19% accuracy, 92.87 ± 1.27% recall, and 94.69 ± 3.03% precision. The overall performance was additionally improved using a median filter to reflect the context information. Finally, active sacroiliitis was diagnosed in individual subjects with 96.06 ± 2.83% accuracy, 100% recall, and 94.84 ± 3.73% precision. This is a pilot study to diagnose bone marrow edema by deep learning based on MR images, and the results suggest that MR analysis using deep learning can be a useful complementary means for clinicians to diagnose bone marrow edema.

Background: Although gout is accompanied by the substantial burden of kidney disease, there are limited data to assess renal function as a therapeutic target. This study evaluated the importance of implementing a &ldquo, treat-to-target&rdquo, approach in relation to renal outcomes. Methods: Patients with gout who underwent continuous urate-lowering therapy (ULT) for at least 12 months were included. The effect of ULT on renal function was investigated by means of a sequential comparison of the estimated glomerular filtration rate (eGFR). Results: Improvement in renal function was only demonstrated in subjects in whom the serum urate target of &lt, 6 mg/dL was achieved (76.40 &plusmn, 18.81 mL/min/1.73 m2 vs. 80.30 &plusmn, 20.41 mL/min/1.73 m2, p &lt, 0.001). A significant difference in the mean change in eGFR with respect to serum urate target achievement was shown in individuals with chronic kidney disease stage 3 (&minus, 0.35 &plusmn, 3.87 mL/min/1.73 m2 vs. 5.33 &plusmn, 11.64 mL/min/1.73 m2, p = 0.019). Multivariable analysis predicted that patients &ge, 65 years old had a decreased likelihood of improvement (OR 0.31, 95% CI 0.13&ndash, 0.75, p = 0.009). Conclusions: The &ldquo, approach in the long-term management of gout is associated with better renal outcomes, with a greater impact on those with impaired renal function.

In this paper, we proposed a gait type classification method based on deep learning using a smart insole with various sensor arrays. We measured gait data using a pressure sensor array, an acceleration sensor array, and a gyro sensor array built into a smart insole. Features of gait pattern were then extracted using a deep convolution neural network (DCNN). In order to accomplish this, measurement data of continuous gait cycle were divided into unit steps. Pre-processing of data were then performed to remove noise followed by data normalization. A feature map was then extracted by constructing an independent DCNN for data obtained from each sensor array. Each of the feature maps was then combined to form a fully connected network for gait type classification. Experimental results for seven types of gait (walking, fast walking, running, stair climbing, stair descending, hill climbing, and hill descending) showed that the proposed method provided a high classification rate of more than 90%.