Physical activity and eating behaviors patterns associated with high blood pressure among Chinese children and adolescents.

BACKGROUND: Physical activity and eating behavior are associated with hypertension in children and adolescents. Revealing the associations between physical activity patterns, eating behavior patterns and high blood pressure (HBP) could help improve the problem of hypertension from the actual children's physical activities and eating behaviors. METHODS: A total of 687 students aged 8-15 years were selected from two nine-year primary and secondary schools using stratified cluster random sampling method. The students' body height, weight, systolic blood pressure (SBP) and diastolic blood pressure (DBP) were measured, and their physical activity time and eating behaviors were surveyed by using CLASS questionnaire and self-made eating behavior questionnaire, respectively. Exploratory factor analysis (EFA) was used to extract moderate to vigorous physical activity factor (MVPAF), sedentary activity factor (SAF), healthy eating behavior factor (HEBF), unhealthy eating behavior factor (UHEBF). MVPAF ≥ SAF was defined as moderate to vigorous physical activity pattern (MVPAP), MVPAF < SAF was defined as sedentary activity pattern (SAP). HEBF ≥ UHEBF was defined as healthy eating behavior pattern (HEBP), while the opposite was defined as unhealthy eating behavior pattern (UHEBP). Lifestyles includes physical activity patterns and eating behavior patterns. RESULTS: The overall prevalence of hypertension was 5.8% (40/687), and was 5.69% (21/369) in boys and 5.97% (19/318) in girls, respectively. The MVPAF and UHEBF in boys were significantly higher than those in girls (P < 0.01), while the SAF in girls was significantly higher than that in boys (P < 0.05). The SAF was positively correlated with SBP in girls (ß(SE) = 0.14 (0.50), P = 0.016), and was positively correlated with SBP (ß(SE) = 0.21 (1.22), P = 0.000 and DBP (ß(SE) = 0.14 (0.49), P = 0.006) in boys. The MVPAF was negatively correlated with DBP (ß(SE)=-0.11 (0.40), P = 0.022) in boys. In boys, the SAP increased the risks of HBP (OR (95% CI):3.34 (1.30-8.63)) and high DBP (OR (95% CI):3.08 (1.02-9.34)) compared with MVPAP. CONCLUSION: Compared with the boys with MVPAP, boys with SAP may increase the risks of HBP and high DBP. The SAF may be positively associated with SBP in boys and girls, while the MVPAF may be negatively associated with DBP in boys.

Ontology-driven and weakly supervised rare disease identification from clinical notes.

BACKGROUND: Computational text phenotyping is the practice of identifying patients with certain disorders and traits from clinical notes. Rare diseases are challenging to be identified due to few cases available for machine learning and the need for data annotation from domain experts. METHODS: We propose a method using ontologies and weak supervision, with recent pre-trained contextual representations from Bi-directional Transformers (e.g. BERT). The ontology-driven framework includes two steps: (i) Text-to-UMLS, extracting phenotypes by contextually linking mentions to concepts in Unified Medical Language System (UMLS), with a Named Entity Recognition and Linking (NER+L) tool, SemEHR, and weak supervision with customised rules and contextual mention representation; (ii) UMLS-to-ORDO, matching UMLS concepts to rare diseases in Orphanet Rare Disease Ontology (ORDO). The weakly supervised approach is proposed to learn a phenotype confirmation model to improve Text-to-UMLS linking, without annotated data from domain experts. We evaluated the approach on three clinical datasets, MIMIC-III discharge summaries, MIMIC-III radiology reports, and NHS Tayside brain imaging reports from two institutions in the US and the UK, with annotations. RESULTS: The improvements in the precision were pronounced (by over 30% to 50% absolute score for Text-to-UMLS linking), with almost no loss of recall compared to the existing NER+L tool, SemEHR. Results on radiology reports from MIMIC-III and NHS Tayside were consistent with the discharge summaries. The overall pipeline processing clinical notes can extract rare disease cases, mostly uncaptured in structured data (manually assigned ICD codes). CONCLUSION: The study provides empirical evidence for the task by applying a weakly supervised NLP pipeline on clinical notes. The proposed weak supervised deep learning approach requires no human annotation except for validation and testing, by leveraging ontologies, NER+L tools, and contextual representations. The study also demonstrates that Natural Language Processing (NLP) can complement traditional ICD-based approaches to better estimate rare diseases in clinical notes. We discuss the usefulness and limitations of the weak supervision approach and propose directions for future studies.

Maximizing Coverage Quality with Budget Constrained in Mobile Crowd-Sensing Network for Environmental Monitoring Applications.

The Mobile Crowd-sensing Network is a novel cyber-physical-social network which has received great attention recently and can be used as a powerful tool to monitor the phenomenon of the field of interest. Due to the limited budget, how to choose appropriate participants to maximize the coverage quality is one of the most important issues when the mobile crowd-sensing network applies to practical application, such as air quality monitoring. In this paper, given the number of available participants, the traverse path and the reward of each participant, we investigate the problem of how to choose suitable participants to monitor an environment of a critical region by a crowd-sensing network, while the total rewards for all selected participants is not larger than the limited budget. In our solution, we first divide a big critical region such as a city into smaller regions of different size, and select some sampling points in the smaller region; the collected data of those sampling points represents the collected data of the whole smaller region. Then, we design a greedy algorithm to select participants to cover the maximum sampling points while the total rewards of selected participants does not exceed the limited budget. Finally, we evaluate the validity and efficiency of the proposed algorithm by conducting extensive simulations. The simulation results show that the greedy algorithm outperforms an existing scheme.

Forecasting smog-related health hazard based on social media and physical sensor.

Smog disasters are becoming more and more frequent and may cause severe consequences on the environment and public health, especially in urban areas. Social media as a real-time urban data source has become an increasingly effective channel to observe people׳s reactions on smog-related health hazard. It can be used to capture possible smog-related public health disasters in its early stage. We then propose a predictive analytic approach that utilizes both social media and physical sensor data to forecast the next day smog-related health hazard. First, we model smog-related health hazards and smog severity through mining raw microblogging text and network information diffusion data. Second, we developed an artificial neural network (ANN)-based model to forecast smog-related health hazard with the current health hazard and smog severity observations. We evaluate the performance of the approach with other alternative machine learning methods. To the best of our knowledge, we are the first to integrate social media and physical sensor data for smog-related health hazard forecasting. The empirical findings can help researchers to better understand the non-linear relationships between the current smog observations and the next day health hazard. In addition, this forecasting approach can provide decision support for smog-related health hazard management through functions like early warning.

Semantic Framework of Internet of Things for Smart Cities: Case Studies.

In recent years, the advancement of sensor technology has led to the generation of heterogeneous Internet-of-Things (IoT) data by smart cities. Thus, the development and deployment of various aspects of IoT-based applications are necessary to mine the potential value of data to the benefit of people and their lives. However, the variety, volume, heterogeneity, and real-time nature of data obtained from smart cities pose considerable challenges. In this paper, we propose a semantic framework that integrates the IoT with machine learning for smart cities. The proposed framework retrieves and models urban data for certain kinds of IoT applications based on semantic and machine-learning technologies. Moreover, we propose two case studies: pollution detection from vehicles and traffic pattern detection. The experimental results show that our system is scalable and capable of accommodating a large number of urban regions with different types of IoT applications.

Parental Stress on Children's Appearance, Body Dissatisfaction, and Eating Behaviours in Chinese Children: A Pathway Analysis.

Purpose: This study aimed to analyze the association pathways of parental stress on children's appearance, body dissatisfaction, and eating behaviours in Chinese children and adolescents. Patients and Methods: The children aged 8-15 years were selected from 2 nine-year schools using stratified cluster random sampling. The appearance-related social stress questionnaire and the body dissatisfaction subscale of EDI-1 were used to investigate parental stress on children's appearance and body dissatisfaction, respectively. The self-administered eating frequency questionnaire was used to investigate children's eating behaviours. Results: Body dissatisfaction in girls mediated associations between BMI, parental teasing, parental injustice and ignorance, parental encouragement and healthy eating behaviour: BMI → body dissatisfaction → healthy eating behaviour, parental teasing → body dissatisfaction → healthy eating behaviour, parental injustice and ignorance → body dissatisfaction → healthy eating behaviour, parental encouragement → body dissatisfaction → healthy eating behaviour. Parental injustice and ignorance directly and negatively predicted healthy eating behaviour in girls. In boys and girls, parental teasing was a direct predictor factor of unhealthy eating behaviour. Conclusion: Parental teasing, parental injustice and ignorance, parental encouragement, and BMI through body dissatisfaction positively predicted healthy eating behaviour in girls, parental injustice and ignorance directly negatively predicted healthy eating behaviour in girls, and parental teasing directly positively predicted unhealthy eating behaviour in girls and boys. Therefore, parental pressure on children's appearance may pay important role in children's eating behaviours.

Parental Pressure on Child Body Image, BMI, Body Image Dissatisfaction Associated with Eating Disorders in School-Age Children in China: A Path Analysis.

Background: Children's eating behaviors, body shape and body image cognition may be more susceptible to the influence of their parents, but these influences may be weakened with age. There may be different association pathways between parental pressure on children's body image (PPCBI), body mass index (BMI), body image dissatisfaction (BID) and eating disorders (EDs) among children and adolescents at different developmental stages. Methods: The stratified cluster sampling method (Stratified by grade, and took the classes as clusters) was used to select 486 students aged 8-15 years in two 9-year schools. Children's body height, weight, testicular volume and breast development were measured. PPCBI, BID, and EDs were investigated using the Appearance-related Social Stress Questionnaire, Body Size Questionnaire (BID-14), and EDI-1 scale, respectively. Results: The boys before puberty initiation had significantly higher EDs score (182.3±50.8) than girls before puberty initiation (164.1±58.1) (P<0.05). There were significant association pathways of PPCBI→BMI→BID→EDs and PPCBI→BID→EDs in boys before puberty initiation (ß=0.035, P<0.01; ß=0.059, P<0.01), in boys after puberty initiation (ß=0.032, P<0.01; ß=0.175, P<0.001), and in girls after puberty initiation (ß=0.026, P<0.01; ß=0.172, P<0.001). There was a positive association pathway of PPCBI→EDs in boys before puberty initiation (ß=0.30, P<0.001) and PPCBI→BID→EDs in girls before puberty initiation (ß=0.176, P<0.01). Conclusion: Parental pressure on children's body image may positively associate with children's eating disorders through BMI and body image dissatisfaction in boys and girls after puberty initiation and directly associate with eating disorders in boys before puberty initiation; however, it may indirectly associate with eating disorders only through BID in girls before puberty initiation.

Automated clinical coding: what, why, and where we are?

Clinical coding is the task of transforming medical information in a patient's health records into structured codes so that they can be used for statistical analysis. This is a cognitive and time-consuming task that follows a standard process in order to achieve a high level of consistency. Clinical coding could potentially be supported by an automated system to improve the efficiency and accuracy of the process. We introduce the idea of automated clinical coding and summarise its challenges from the perspective of Artificial Intelligence (AI) and Natural Language Processing (NLP), based on the literature, our project experience over the past two and half years (late 2019-early 2022), and discussions with clinical coding experts in Scotland and the UK. Our research reveals the gaps between the current deep learning-based approach applied to clinical coding and the need for explainability and consistency in real-world practice. Knowledge-based methods that represent and reason the standard, explainable process of a task may need to be incorporated into deep learning-based methods for clinical coding. Automated clinical coding is a promising task for AI, despite the technical and organisational challenges. Coders are needed to be involved in the development process. There is much to achieve to develop and deploy an AI-based automated system to support coding in the next five years and beyond.

Associations between negative gender attitudes and eating behaviors in Chinese children and adolescents.

Background: Negative gender cognitive attitudes (disliking one's own gender or wanting to be the opposite gender) and unhealthy eating behaviors have become common in Chinese children and adolescents. The aim of this study was to analyze the associations between negative gender attitudes and eating behaviors among Chinese children and adolescents. Methods: Primary and secondary school students aged 8-15 years were selected as participants using a stratified cluster random sampling method. The self-designed questionnaire was used to investigate the participants' negative gender cognitive attitudes. Eating frequency questionnaire was used to investigate participants' eating behaviors. Under the leading reading of standardized training investigators, the questionnaire for children aged 8-15 years was completed by themselves in the form of centralized filling. Results: A total of 6.5% [43/657, boys: 6.1% (21/347), girls: 7.1% (22/310)] of children disliked their own gender, 8.8% [58/657, boys: 5.5% (19/347), girls: 12.6% (39/310)] of children wanted to be of the opposite gender, and the proportion of girls with negative gender attitudes was higher than that of boys (P < 0.05). Boys who disliked their own gender or wanted to be the opposite gender had higher frequencies of unhealthy eating behaviors and lower frequencies of healthy eating behaviors than boys who liked their own gender or did not want to be the opposite gender (P < 0.05). Girls who disliked their own gender or wanted to be the opposite gender had higher frequencies of protein eating behaviors than girls who liked their own gender or did not want to be the opposite gender (P < 0.05). There was a significant interaction between disliking one's own gender and wanting to be the opposite gender in midnight snack eating among boys (P < 0.05) and in carbonated drink and high protein eating behaviors among girls (P < 0.05). Conclusion: Boys with negative gender cognitive attitudes express more unhealthy eating behaviors and fewer healthy eating behaviors; girls with negative gender cognitive attitudes exhibit more protein eating behaviors.

Social Media Meets Big Urban Data: A Case Study of Urban Waterlogging Analysis.

With the design and development of smart cities, opportunities as well as challenges arise at the moment. For this purpose, lots of data need to be obtained. Nevertheless, circumstances vary in different cities due to the variant infrastructures and populations, which leads to the data sparsity. In this paper, we propose a transfer learning method for urban waterlogging disaster analysis, which provides the basis for traffic management agencies to generate proactive traffic operation strategies in order to alleviate congestion. Existing work on urban waterlogging mostly relies on past and current conditions, as well as sensors and cameras, while there may not be a sufficient number of sensors to cover the relevant areas of a city. To this end, it would be helpful if we could transfer waterlogging. We examine whether it is possible to use the copious amounts of information from social media and satellite data to improve urban waterlogging analysis. Moreover, we analyze the correlation between severity, road networks, terrain, and precipitation. Moreover, we use a multiview discriminant transfer learning method to transfer knowledge to small cities. Experimental results involving cities in China and India show that our proposed framework is effective.

ELM Meets Urban Big Data Analysis: Case Studies.

In the latest years, the rapid progress of urban computing has engendered big issues, which creates both opportunities and challenges. The heterogeneous and big volume of data and the big difference between physical and virtual worlds have resulted in lots of problems in quickly solving practical problems in urban computing. In this paper, we propose a general application framework of ELM for urban computing. We present several real case studies of the framework like smog-related health hazard prediction and optimal retain store placement. Experiments involving urban data in China show the efficiency, accuracy, and flexibility of our proposed framework.

BioTCM-SE: a semantic search engine for the information retrieval of modern biology and traditional Chinese medicine.

Understanding the functional mechanisms of the complex biological system as a whole is drawing more and more attention in global health care management. Traditional Chinese Medicine (TCM), essentially different from Western Medicine (WM), is gaining increasing attention due to its emphasis on individual wellness and natural herbal medicine, which satisfies the goal of integrative medicine. However, with the explosive growth of biomedical data on the Web, biomedical researchers are now confronted with the problem of large-scale data analysis and data query. Besides that, biomedical data also has a wide coverage which usually comes from multiple heterogeneous data sources and has different taxonomies, making it hard to integrate and query the big biomedical data. Embedded with domain knowledge from different disciplines all regarding human biological systems, the heterogeneous data repositories are implicitly connected by human expert knowledge. Traditional search engines cannot provide accurate and comprehensive search results for the semantically associated knowledge since they only support keywords-based searches. In this paper, we present BioTCM-SE, a semantic search engine for the information retrieval of modern biology and TCM, which provides biologists with a comprehensive and accurate associated knowledge query platform to greatly facilitate the implicit knowledge discovery between WM and TCM.