Parental Migration Trajectories From Childhood Through Adolescence: Longitudinal Impact on Emotional and Behavioral Problems Among Chinese Adolescents.

It is estimated that there are about 23% of all children in China experiencing parental migration and being left behind at hometown. Existing research indicated a significant association between parental migration and children development but overlooked the dynamic changes in family structure caused by parental migration. In this study, data was derived from a nationally representative longitudinal survey-the China Family Panel Studies. The main analyses employed four waves of data (2012, 2014, 2016, and 2018) and included 1401 adolescents aged 10-15 years (Mean:12.35, SD:1.67; 54.2% female). Six typical trajectories of parental migration capturing both migration status at each timepoint and changes in the status across six years were created. Children's depression and internalizing problems and externalizing problems were concerned outcomes. The mediating roles of the caregiver-child interaction and caregiver's depression were examined. Adolescents in the trajectory group described as experiencing transitions between being left behind by both parents and non had a higher risk of depression and internalizing and externalizing problems. Caregivers' depression was a significant mediator between parental migration and adolescent depression.

Classification of lung cancer subtypes on CT images with synthetic pathological priors.

The accurate diagnosis on pathological subtypes for lung cancer is of significant importance for the follow-up treatments and prognosis managements. In this paper, we propose self-generating hybrid feature network (SGHF-Net) for accurately classifying lung cancer subtypes on computed tomography (CT) images. Inspired by studies stating that cross-scale associations exist in the image patterns between the same case's CT images and its pathological images, we innovatively developed a pathological feature synthetic module (PFSM), which quantitatively maps cross-modality associations through deep neural networks, to derive the "gold standard" information contained in the corresponding pathological images from CT images. Additionally, we designed a radiological feature extraction module (RFEM) to directly acquire CT image information and integrated it with the pathological priors under an effective feature fusion framework, enabling the entire classification model to generate more indicative and specific pathologically related features and eventually output more accurate predictions. The superiority of the proposed model lies in its ability to self-generate hybrid features that contain multi-modality image information based on a single-modality input. To evaluate the effectiveness, adaptability, and generalization ability of our model, we performed extensive experiments on a large-scale multi-center dataset (i.e., 829 cases from three hospitals) to compare our model and a series of state-of-the-art (SOTA) classification models. The experimental results demonstrated the superiority of our model for lung cancer subtypes classification with significant accuracy improvements in terms of accuracy (ACC), area under the curve (AUC), positive predictive value (PPV) and F1-score.