Search

AbstractIn this study, we focus on visualizing trajectory data, a type of data based on a series of temporal observations. We present an adapted version of t-distributed stochastic neighborhood embedding (t-SNE) tailored for trajectory data. This method is designed to preserve the inherent curved structure of trajectory data by incorporating a robust distance measure. Furthermore, it demonstrates the ability to maintain the data structure even in the presence of missing values at different time points. The performance of the proposed method is rigorously evaluated through a simulation study and demonstrated its effectiveness in visualizing two types of trajectory data, Gait data and NBA data. [ABSTRACT FROM AUTHOR]

The current large amounts of data and advanced technologies have produced new types of complex data, such as histogram-valued data. The paper focuses on classification problems when predictors are observed as or aggregated into histograms. Because conventional classification methods take vectors as input, a natural approach converts histograms into vector-valued data using summary values, such as the mean or median. However, this approach forgoes the distributional information available in histograms. To address this issue, we propose a margin-based classifier called support histogram machine (SHM) for histogram-valued data. We adopt the support vector machine framework and the Wasserstein-Kantorovich metric to measure distances between histograms. The proposed optimization problem is solved by a dual approach. We then test the proposed SHM via simulated and real examples and demonstrate its superior performance to summary-value-based methods. [ABSTRACT FROM AUTHOR]

We aimed to investigate the progression of patella alta (PA) in patients with cerebral palsy (CP) using the Koshino-Sugimoto (KS) index and assess associated risk factors. Participants in our retrospective study met the following inclusion criteria: patients with CP who visited our institute from May 2003 to December 2019, were ≤18 years of age, were followed up for >2 years and had at least two lateral knee radiographs. KS indices of both knee radiographs were measured for each patient. A linear mixed model was implemented. Our participants included 222 CP patients. KS index values were measured via 652 knee radiographs. Reference values of the KS index for those between 4 and 18 years of age were determined according to Gross Motor Function Classification System (GMFCS) levels. In all GMFCS levels, the KS index decreased with patients' ages (P < 0.0001). In groups where the KS index increased, GMFCS levels IV (P = 0.0045) and V (P = 0.0040) were statistically significant. Change in the KS index values indicates that PA improves as patients age within all GMFCS levels. However, in patients with GMFCS levels of IV and V, progressive PA is expected., (Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.)

Purpose: This study evaluated the rates and annual trends of pediatric CT scans in South Korea using a nationwide population-based database., Materials and Methods: Data regarding pediatric CT scan usage between 2012 and 2017 were retrieved from the health insurance review and assessment service. Data on the age, sex, diagnosis, and the anatomical area of involved patients were also extracted., Results: A total of 576376 CT examinations were performed among 58527528 children aged below 18 years (9.8 scans/1000 children), and the number of CT examinations per 1000 children was noted to have increased by 23.2% from 9.0 in 2012 to 11.0 in 2017. Specifically, the number of CT examinations increased by 32.9% for the 6-12 years of age group (7.4/1000 to 9.8/1000) and by 34.0% for the 13-18 years of age group (11.4/1000 to 15.3/1000). Moreover, majority of the CT scans were limited to the head (39.1%), followed by the extremities (32.5%) and the abdomen (13.7%). Notably, the number of extremity CT scans increased by 83.6% (2.3/1000 to 4.2/1000), and its proportion as compared to other scans increased from 25.3% to 37.7%., Conclusion: CT scans in the pediatric population increased continuously from 2012 to 2017 at an annual rate of 4.4%. Therefore, physicians should balance the benefits of CT with its potential harms from associated radiation exposure in pediatric patients., Competing Interests: Conflicts of Interest: The authors have no potential conflicts of interest to disclose., (Copyrights © 2022 The Korean Society of Radiology.)