Search

Prediction of fine particulate matter with particle size less than 2.5 µm (PM2.5) is an important component of atmospheric pollution warning and control management. In this study, we propose a deep learning model, namely, a spatiotemporal weighted neural network (STWNN), to address the challenge of poor long-term PM2.5 prediction in areas with sparse and uneven stations. The model, which is based on convolutional neural network–bidirectional long short-term memory (CNN–Bi-LSTM) and attention mechanisms and uses a geospatial data-driven approach, considers the spatiotemporal heterogeneity effec It is correct.ts of PM2.5. This approach effectively overcomes instability caused by sparse station data in forecasting daily average PM2.5 concentrations over the next week. The effectiveness of the STWNN model was evaluated using the Xinjiang Uygur Autonomous Region as the study area. Experimental results demonstrate that the STWNN exhibits higher performance (RMSE = 10.29, MAE = 6.4, R2 = 0.96, and IA = 0.81) than other models in overall prediction and seasonal clustering. Furthermore, the SHapley Additive exPlanations (SHAP) method was introduced to calculate the contribution and spatiotemporal variation of feature variables after the STWNN prediction model. The SHAP results indicate that the STWNN has significant potential in improving the performance of long-term PM2.5 prediction at the regional station level. Analyzing spatiotemporal differences in key feature variables that influence PM2.5 provides a scientific foundation for long-term pollution control and supports emergency response planning for heavy pollution events. [ABSTRACT FROM AUTHOR]

Background: Lumbosacral transitional vertebra (LSTV) is a common spinal variant, with the reported prevalence varying from 8.1% to 36%. LSTV has been shown to alter the lumbo-pelvic parameters and reduce the benefits of total hip arthroplasty, but the specific effects of LSTV on hip development remain unclear. The aim of this study was thus to investigate the impact of LSTV on developmental alterations of the hip., Methods: A total of 310 individuals were categorized into three groups according to whole-body computed tomography (CT) imaging: a group with sacralization of 23 presacral vertebrae (PSV) (n=102), a group with lumbarization of 25 PSV (n=108), and a normal control group with 24 PSV (n=100). Quantitative parameters of the lumbo-pelvic-hip complex (LPHC) including lumbar lordosis (LL), pelvic incidence (PI), pelvic tilt (PT), sacral slope (SS), axial and sagittal acetabular anteversion angle (AAA), center-edge (CE) angle, Sharp angle, and femoral neck-shaft angle (FNSA) were measured and analyzed. Statistical analyses were used to compare the differences of these quantitative parameters among the three groups and to assess the relationship between hip and lumbar-pelvic parameters., Results: Significant differences between each pair of three groups and the LSTV subgroups were only found in the sagittal AAA (left side: P=0.008; right side: P<0.001), with no differences found for the other parameters. Compared to the normal group (24 PSV), both the 23 PSV and 25 PSV groups exhibited increased values in the sagittal AAA, especially in the right side of the 23 PSV group. Only the sagittal AAA showed low-to-moderate positive correlations with pelvic parameters of PI (r=0.195-0.429; P=0.001-0.08) and PT (r=0.239-0.605; P=0.001-0.03)., Conclusions: Variations of LSTV are correlated with the hip anatomical development via LPHC transmission and may potentially reduce the sagittal acetabular coverage, particularly in the 23 PSV subtype on the right side., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://qims.amegroups.com/article/view/10.21037/qims-23-1816/coif). The authors have no conflicts of interest to declare., (2024 Quantitative Imaging in Medicine and Surgery. All rights reserved.)