Early detection of lung nodules is crucial for the prevention and treatment of lung cancer. However, current methods face challenges such as missing small nodules, variations in nodule size, and high false positive rates. To address these challenges, we propose a Global Channel Spatial Attention Mechanism (GCSAM). Building upon it, we develop a Candidate Nodule Detection Network (CNDNet) and a False Positive Reduction Network (FPRNet). CNDNet employs Res2Net as its backbone network to capture multi-scale features of lung nodules, utilizing GCSAM to fuse global contextual information, adaptively adjust feature weights, and refine processing along the spatial dimension. Additionally, we design a Hierarchical Progressive Feature Fusion (HPFF) module to effectively combine deep semantic information with shallow positional information, enabling high-sensitivity detection of nodules of varying sizes. FPRNet significantly reduces the false positive rate by accurately distinguishing true nodules from similar structures. Experimental results on the LUNA16 dataset demonstrate that our method achieves a competitive performance metric (CPM) value of 0.929 and a sensitivity of 0.977 under 2 false positives per scan. Compared to existing methods, our proposed method effectively reduces false positives while maintaining high sensitivity, achieving competitive results.

Background: With the rapid expansion of biomedical literature, biomedical information extraction has attracted increasing attention from researchers. In particular, relation extraction between 2 entities is a long-term research topic. Objective: This study aimed to perform 2 multiclass relation extraction tasks of Biomedical Natural Language Processing Workshop 2019 Open Shared Tasks: relation extraction of Bacteria-Biotope (BB-rel) task and binary relation extraction of plant seed development (SeeDev-binary) task. In essence, these 2 tasks are aimed at extracting the relation between annotated entity pairs from biomedical texts, which is a challenging problem. Methods: Traditional research methods adopted feature- or kernel-based methods and achieved good performance. For these tasks, we propose a deep learning model based on a combination of several distributed features, such as domain-specific word embedding, part-of-speech embedding, entity-type embedding, distance embedding, and position embedding. The multi-head attention mechanism is used to extract the global semantic features of an entire sentence. Meanwhile, we introduced a dependency-type feature and the shortest dependency path connecting 2 candidate entities in the syntactic dependency graph to enrich the feature representation. Results: Experiments show that our proposed model has excellent performance in biomedical relation extraction, achieving F1 scores of 65.56% and 38.04% on the test sets of the BB-rel and SeeDev-binary tasks. Especially in the SeeDev-binary task, the F1 score of our model is superior to that of other existing models and achieves state-of-the-art performance. Conclusions: We demonstrated that the multi-head attention mechanism can learn relevant syntactic and semantic features in different representation subspaces and different positions to extract comprehensive feature representation. Moreover, syntactic dependency features can improve the performance of the model by learning dependency relation between the entities in biomedical texts.

Background: Domestic violence is a global public health concern as stated by World Health Organization. We aimed to conduct a textual analysis of tweets associated with domestic violence through keyword identification, word trends and word collocations. The data was obtained from Twitter, focusing on publicly available tweets written in English. The objectives are to find out if the identified keywords, word trends and word collocations can help differentiate between domestic violence-related tweets and non-domestic violence-related tweets, as well as, to analyze the textual characteristics of domestic violence-related tweets and non-domestic violence-related tweets. Methods: Overall, 11,041 tweets were collected using a few keywords over a period of 15 days from 22 March 2021 to 5 April 2021. A text analysis approach was used to discover the most frequent keywords used, the word trends of those keywords and the word collocations of the keywords in differentiating between domestic violence-related or non-domestic violence-related tweets. Results: Domestic violence-related tweets and non-domestic violence-related tweets had differentiating characteristics, despite sharing several main keywords. In particular, keywords like “domestic”, “violence” and “suicide” featured prominently in domestic-violence related tweets but not in non-domestic violence-related tweets. Significant differences could also be seen in the frequency of keywords and the word trends in the collection of the tweets. Conclusion: These findings are significant in helping to automate the flagging of domestic-violence related tweets and alert the authorities so that they can take proactive steps such as assisting the victims in getting medical, police and legal help as needed.

Background: Adolescent sexual and reproductive health (SRH) education requires accurate knowledge, understanding of risks, and supportive access to well-being. Objectives: This review aims to assess how knowledge about sexual and reproductive health (SRH) influences adolescent behaviour, identifying barriers, effective strategies, and communication methods. It evaluates interventions like school-based programs and online resources to empower informed decision-making among adolescents regarding SRH. Method: A systematic search from January 2013 yielded 14 articles, mostly quantitative studies involving adolescents aged 14-19. A narrative analysis identified two main themes: (i) Enhancing SRH knowledge, attitudes, and skills for positive outcomes and innovative intervention strategies. The findings were organized by Endnote 20. Results: The key findings of the review highlight the effectiveness of interventions in improving adolescents’ knowledge, attitudes, and skills related to sexual and reproductive health (SRH). These interventions have shown success in enhancing adolescents’ understanding of SRH issues, fostering positive attitudes toward SRH topics, and building self-efficacy for safe sexual practices. Furthermore, the review highlights the importance of innovative and targeted intervention strategies, such as technology-driven approaches, customized interventions, and the synergistic combination of multiple strategies, to effectively address the diverse needs for SRH of adolescents and promote positive outcomes for SRH. Conclusions: This review emphasizes the impact of SRH interventions on adolescent well-being, advocating for tailored gender-specific approaches, policy integration, and long-term efficacy evaluations for sustained positive outcomes.