著者
Hikaru TAKARA Yoshiki KOHATSU Shota SUZUKI Shuhei SATOH Yoko ABE Shohei MIYAZATO Shin MINAKATA Masamichi MORIYA
出版者
Japanese Society of Physical Therapy
雑誌
Physical Therapy Research (ISSN:21898448)
巻号頁・発行日
pp.E10205, (Released:2022-11-08)
参考文献数
32
被引用文献数
2

Objective: The study aim was to investigate the association between initiating mobilization within 7 days after onset and symptomatic cerebral vasospasm (SCV) in patients with aneurysmal subarachnoid hemorrhage (aSAH). Methods: This was a retrospective multicenter case-control study in Japan. Patients with a diagnosis of aSAH who underwent physical therapy with/without occupational therapy were included and categorized into 2 groups according to the presence or absence of SCV. Initiating mobilization was defined as sitting on the bed edge (at least once, with/without assist, regardless of duration) within 7 days after aSAH onset. Cox proportional hazards regression analysis was performed to evaluate the association between initiating mobilization within 7 days after onset and SCV. Results: The analysis included 510 patients. Among all included patients, 57 (11.2%) patients had SCV. In the univariate Cox proportional hazards regression analysis, initiating of mobilization was not associated with SCV (hazard ratio [HR] = 0.78; 95% confidence interval [CI] = 0.45–1.32). In the multivariate analysis, only the modified Fisher scale was significantly associated with SCV (HR = 26.23; 95% CI = 1.21–571.0). Conclusion: Initiating mobilization within 7 days after aSAH onset was not associated with SCV in patients with aSAH.
著者
Shota SUZUKI Takayuki ITO Ahmed MOUSTAFA Rafik HADFI
出版者
一般社団法人 人工知能学会
雑誌
人工知能学会全国大会論文集 第34回全国大会(2020)
巻号頁・発行日
pp.2G5ES302, 2020 (Released:2020-06-19)

Online discussion platforms require extracting the discussion structure in order to support understanding the flow of these discussions. Towards this end, this paper proposes an approach that performs node classification which is the first step towards extracting the structure of online discussions. In this regard, the proposed approach employs a graph attention network (GAT) in order to directly learn the discussion structure. In specific, the GAT, which is a type of graph neural networks (GNNs), encodes the graph structures directly. In addition, the GAT, which is based on attention architecture, is able to deal with different graph structures. In order to evaluate the proposed approach, we have conducted a set of experiments on the persuasive essays dataset that is styled using the issue-based information system (IBIS). The experimental results show that the proposed approach is able to classify the nodes in online discussion structures accurately.
著者
Mikio Fujimoto Shota Suzuki Hirotaka Kuki Minori Masuda Keiichi Takei Mitsuru Yamamoto
出版者
The Society of Physical Therapy Science
雑誌
Journal of Physical Therapy Science (ISSN:09155287)
巻号頁・発行日
vol.31, no.7, pp.504-507, 2019 (Released:2019-07-02)
参考文献数
10
被引用文献数
2

[Purpose] The Gait Judge System measures the plantar flexion resistive torque acting on the angle of the ankle joint, as well as the ankle joint itself, of the ankle-foot orthosis using a 1,000 Hz sampling frequency. This pilot study aimed to determine the characteristics of plantar flexion resistive torque acting on the double Klenzak ankle joint of the ankle-foot orthoses worn by healthy individuals. [Participants and Methods] Participants were eight healthy young adults (3 male, 5 female; mean age, 26.8 years old; mean height, 165 cm.; mean body weight, 56.3 kg). Plantar flexion resistive torques and angles of the ankle joint in gait cycles were measured with the Gait Judge System. Speed of gait was calculated using a ruler attached on the floor and the Gait Judge System video. We classified waveforms according to the existence of second peaks in the gait cycle. The correlations between parameters related to the plantar flexion resistive torque and the speed of gait were evaluated using Pearson’s simple correlation analysis. [Results] The plantar flexion resistive torque showed two peaks: the first peak was at the loading response, measured at 17.4 Nm, and the second peak was at the pre-swing phase, measured at 10.9 Nm. However, the second peak was absent in three of the participants. The normalized second peak and the second peak/first peak ratio had a strong, positive correlation with the speed of gait. [Conclusion] The Gait Judge System revealed typical waveforms according to the parameters set in this study.