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%.

Ha YJ, et al. J Korean Med Sci. 2014 Sep;29(9):1199-1204. http://dx.doi.org/10.3346/jkms.2014.29.9.1199

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.

(1) Background: We evaluated the prevalence and fracture risk of osteoporosis in patients with rheumatoid arthritis (RA), and compared the fracture risk assessment tool (FRAX) criteria and bone mineral density (BMD) criteria established by the World Health Organization (WHO). (2) Methods: This retrospective cross-sectional study, which included 479 RA patients in 5 hospitals, was conducted between January 2012 and December 2016. The FRAX criteria for high-risk osteoporotic fractures were calculated including and excluding the BMD values, respectively. The definition of high risk for fracture by FRAX criteria and BMD criteria by WHO was 10-year probability of ≥ 20% for major osteoporotic fracture or ≥ 3% for hip fracture, and T score ≤ −2.5 or Z score ≤ −2.0, respectively. (3) Results: The mean age was 61.7 ± 11.9 years. The study included 426 female patients (88.9%), 353 (82.9%) of whom were postmenopausal. Osteoporotic fractures were detected in 81 (16.9%) patients. The numbers of candidates for pharmacological intervention using the FRAX criteria with and without BMD and the WHO criteria were 226 (47.2%), 292 (61%), and 160 (33.4%), respectively. Only 69.2%–77% of the patients in the high-risk group using the FRAX criteria were receiving osteoporosis treatments. The following were significant using the WHO criteria: female (OR 3.55, 95% CI 1.46–8.63), age (OR 1.1, 95% CI 1.08–1.13), and BMI (OR 0.8, 95% CI 0.75–0.87). Glucocorticoid dose (OR 1.09, 95% CI 1.01–1.17), age (OR 1.09, 95% CI 1.06–1.12), and disease duration (OR 1.01, 95% CI 1–1.01) were independent risk factors for fracture. (4) Conclusions: The proportion of RA patients with a high risk of osteoporotic fractures was 33.4%–61%. Only 69.2%–77% of candidate patients were receiving osteoporotic treatments while applying FRAX criteria. Independent risk factors for osteoporotic fractures in RA patients were age, the dose of glucocorticoid, and disease duration.

Recent studies indicate that individuals can be identified by their gait pattern. A number of sensors including vision, acceleration, and pressure have been used to capture humans’ gait patterns, and a number of methods have been developed to recognize individuals from their gait pattern data. This study proposes a novel method of identifying individuals using null-space linear discriminant analysis on humans’ gait pattern data. The gait pattern data consists of time series pressure and acceleration data measured from multi-modal sensors in a smart insole used while walking. We compare the identification accuracies from three sensing modalities, which are acceleration, pressure, and both in combination. Experimental results show that the proposed multi-modal features identify 14 participants with high accuracy over 95% from their gait pattern data of walking.