Media Literacy and Its Potential Influence on Mpox-Related Perceptions and Prevention Intentions in China During the 2022 Multi-Country Outbreak of Mpox.

Media literacy plays an increasingly important role in health communication during public health emergencies. The present study aimed to investigate the level of media literacy and its association with disease perceptions and behavioral intentions of receiving vaccination services among young men who have sex with men (YMSM) in China during the 2022 multi-country mpox outbreak. The data were from a large-scale cross-sectional survey conducted among 2,493 YMSM aged 18-29 years in six provincial regions in China in September 2022. A total of 2,079 YMSM who had obtained mpox information from social media platforms were included in this study. Correlation analysis and path analysis were conducted. The mean age of the sample was 24.7. After controlling for background variables, significant positive correlations were found in several pairs between media literacy, mpox-related perceptions (including perceived susceptibility to mpox, perceived severity of mpox, perceived benefits of mpox vaccination, and self-efficacy of receiving mpox vaccination), and the behavioral intention of receiving mpox vaccination. The mpox-related perceptions played a significant mediation role in the association between media literacy and intention of receiving mpox vaccination (indirect effect = 0.165, p < .001, effect size = 82.1%). Media literacy is crucial for developing disease perceptions during public health emergencies and may further influence the adoption of preventive measures. As social media platforms have become the main battle field of health communication during disease outbreaks, improvement of media literacy is urgently warranted.

KNOWNET: Guided Health Information Seeking from LLMs via Knowledge Graph Integration.

The increasing reliance on Large Language Models (LLMs) for health information seeking can pose severe risks due to the potential for misinformation and the complexity of these topics. This paper introduces KNOWNET a visualization system that integrates LLMs with Knowledge Graphs (KG) to provide enhanced accuracy and structured exploration. Specifically, for enhanced accuracy, KNOWNET extracts triples (e.g., entities and their relations) from LLM outputs and maps them into the validated information and supported evidence in external KGs. For structured exploration, KNOWNET provides next-step recommendations based on the neighborhood of the currently explored entities in KGs, aiming to guide a comprehensive understanding without overlooking critical aspects. To enable reasoning with both the structured data in KGs and the unstructured outputs from LLMs, KNOWNET conceptualizes the understanding of a subject as the gradual construction of graph visualization. A progressive graph visualization is introduced to monitor past inquiries, and bridge the current query with the exploration history and next-step recommendations. We demonstrate the effectiveness of our system via use cases and expert interviews.

Depressive symptoms and its multifaceted associated factors among young men who have sex with men facing the dual threats of COVID-19 and mpox in China.

INTRODUCTION: The COVID-19 pandemic has significantly impacted the mental health of human beings since 2020, especially the young people and the pre-existing marginalized groups such as men who have sex with men (MSM). During the COVID-19 pandemic, the multi-country outbreak of mpox in 2022 additionally posed a significant stress on the most-affected communities (i.e., MSM). This study investigated the level of depressive symptoms and its multifaceted associated factors among Chinese young men who have sex with men (YMSM) in this unique period. METHODS: In September 2022, a large-scale cross-sectional survey was conducted among YMSM aged 18-29 years across six representative provinces in China. Hierarchical regression analysis was performed to test the various types of associated factors of depressive symptoms. RESULTS: Among the 2493 participants, 65.6 % (n = 1638) reported mild to severe depressive symptoms. The hierarchical regression analysis identified that depressive symptoms was significantly positively associated with unemployment, having substance use in the past 6 months, a higher level of MSM self-stigma, incompletion of COVID-19 vaccination, greater mpox risk perception, and presence of mpox related-like symptoms. LIMITATIONS: This study used the facility-based sampling method to recruit the participants, which may lead to selection bias. CONCLUSIONS: Chinese YMSM faced significant mental health challenges during the concurrent epidemics of COVID-19 and mpox, which was associated with their socio-economic status, risk behaviors, stigma, and multiple diseases-related variables. Proactive measures may hold promise as effective strategies for mitigating mental distress among marginalized groups during public health crises.

LEAP: LLM instruction-example adaptive prompting framework for biomedical relation extraction.

OBJECTIVE: To investigate the demonstration in large language models (LLMs) for biomedical relation extraction. This study introduces a framework comprising three types of adaptive tuning methods to assess their impacts and effectiveness. MATERIALS AND METHODS: Our study was conducted in two phases. Initially, we analyzed a range of demonstration components vital for LLMs' biomedical data capabilities, including task descriptions and examples, experimenting with various combinations. Subsequently, we introduced the LLM instruction-example adaptive prompting (LEAP) framework, including instruction adaptive tuning, example adaptive tuning, and instruction-example adaptive tuning methods. This framework aims to systematically investigate both adaptive task descriptions and adaptive examples within the demonstration. We assessed the performance of the LEAP framework on the DDI, ChemProt, and BioRED datasets, employing LLMs such as Llama2-7b, Llama2-13b, and MedLLaMA_13B. RESULTS: Our findings indicated that Instruction + Options + Example and its expanded form substantially improved F1 scores over the standard Instruction + Options mode for zero-shot LLMs. The LEAP framework, particularly through its example adaptive prompting, demonstrated superior performance over conventional instruction tuning across all models. Notably, the MedLLAMA_13B model achieved an exceptional F1 score of 95.13 on the ChemProt dataset using this method. Significant improvements were also observed in the DDI 2013 and BioRED datasets, confirming the method's robustness in sophisticated data extraction scenarios. CONCLUSION: The LEAP framework offers a compelling strategy for enhancing LLM training strategies, steering away from extensive fine-tuning towards more dynamic and contextually enriched prompting methodologies, showcasing in biomedical relation extraction.

Repurposing non-pharmacological interventions for Alzheimer's disease through link prediction on biomedical literature.

Non-pharmaceutical interventions (NPI) have great potential to improve cognitive function but limited investigation to discover NPI repurposing for Alzheimer's Disease (AD). This is the first study to develop an innovative framework to extract and represent NPI information from biomedical literature in a knowledge graph (KG), and train link prediction models to repurpose novel NPIs for AD prevention. We constructed a comprehensive KG, called ADInt, by extracting NPI information from biomedical literature. We used the previously-created SuppKG and NPI lexicon to identify NPI entities. Four KG embedding models (i.e., TransE, RotatE, DistMult and ComplEX) and two novel graph convolutional network models (i.e., R-GCN and CompGCN) were trained and compared to learn the representation of ADInt. Models were evaluated and compared on two test sets (time slice and clinical trial ground truth) and the best performing model was used to predict novel NPIs for AD. Discovery patterns were applied to generate mechanistic pathways for high scoring candidates. The ADInt has 162,212 nodes and 1,017,284 edges. R-GCN performed best in time slice (MR = 5.2054, Hits@10 = 0.8496) and clinical trial ground truth (MR = 3.4996, Hits@10 = 0.9192) test sets. After evaluation by domain experts, 10 novel dietary supplements and 10 complementary and integrative health were proposed from the score table calculated by R-GCN. Among proposed novel NPIs, we found plausible mechanistic pathways for photodynamic therapy and Choerospondias axillaris to prevent AD, and validated psychotherapy and manual therapy techniques using real-world data analysis. The proposed framework shows potential for discovering new NPIs for AD prevention and understanding their mechanistic pathways.

Behavioral Intention of Receiving Monkeypox Vaccination and Undergoing Monkeypox Testing and the Associated Factors Among Young Men Who Have Sex With Men in China: Large Cross-Sectional Study.

BACKGROUND: The worldwide human monkeypox (mpox) outbreak in 2022 mainly affected men who have sex with men (MSM). In China, young men who have sex with men (YMSM) were at a potential high risk of mpox infection due to their sexual activeness and the eased COVID-19 restrictions at the end of 2022. OBJECTIVE: This study aimed to investigate the behavioral intention of receiving mpox vaccination and undergoing mpox testing in 4 different scenarios and explore their associations with background and behavioral theory-related factors among Chinese YMSM. METHODS: An online cross-sectional survey was conducted among YMSM aged 18-29 years from 6 representative provinces of China in September 2022. Participants recruited (recruitment rate=2918/4342, 67.2%) were asked to self-administer an anonymous questionnaire designed based on prior knowledge about mpox and classic health behavior theories. Data on the participants' background, mpox knowledge and cognition, mpox vaccination and testing cognition, and the behavioral intention of receiving mpox vaccination and undergoing mpox testing were collected. Descriptive analysis and univariate and multivariate linear regressions were performed. Geodetector was used to measure the stratified heterogeneity of behavioral intention. RESULTS: A total of 2493 YMSM with a mean age of 24.6 (SD 2.9) years were included. The prevalence of having a behavioral intention of receiving mpox vaccination ranged from 66.2% to 88.4% by scenario, varying in epidemic status and cost. The prevalence of having an mpox testing intention was above 90% in all scenarios regardless of the presence of symptoms and the cost. The positive factors related to vaccination intention included mpox knowledge (ba=0.060, 95% CI 0.016-0.103), perceived susceptibility of mpox (ba=0.091, 95% CI 0.035-0.146), perceived severity of mpox (ba=0.230, 95% CI 0.164-0.296), emotional distress caused by mpox (ba=0.270, 95% CI 0.160-0.380), perceived benefits of mpox vaccination (ba=0.455, 95% CI 0.411-0.498), self-efficacy of mpox vaccination (ba=0.586, 95% CI 0.504-0.668), and having 1 male sex partner (ba=0.452, 95% CI 0.098-0.806), while the negative factor was perceived barriers to vaccination (ba=-0.056, 95% CI -0.090 to -0.022). The positive factors related to testing intention were perceived severity of mpox (ba=0.283, 95% CI 0.241-0.325), perceived benefits of mpox testing (ba=0.679, 95% CI 0.636-0.721), self-efficacy of mpox testing (ba=0.195, 95% CI 0.146-0.245), having 1 male sex partner (ba=0.290, 95% CI 0.070-0.510), and having in-person gatherings with MSM (ba=0.219, 95% CI 0.072-0.366), while the negative factor was emotional distress caused by mpox (ba=-0.069, 95% CI -0.137 to -0.001). CONCLUSIONS: Among Chinese YMSM, the intention of undergoing mpox testing is optimal, while the mpox vaccination intention has room for improvement. A future national response should raise YMSM's mpox knowledge, disseminate updated information about mpox and preventive measures, improve preventive service accessibility and privacy, and provide advice on positively coping with the associated emotional distress.

Behavioral intentions of self-isolation and informing close contacts after developing mpox-related symptoms among young men who have sex with men in China.

The 2022 multi-country mpox outbreak raised public concern globally. Self-isolation and informing close contacts after developing mpox-related symptoms are critical measures in controlling the outbreak. This study investigated behavioral intentions of self-isolation and informing close contacts after developing mpox-related symptoms and associated factors among young men who have sex with men (YMSM) aged 18-29 years in China. The cross-sectional study was conducted among 2493 YMSM in six provincial regions in China from September 10th to 30th, 2022. Descriptive and logistic analyses were applied, using the intentions of self-isolation and informing close contacts after developing mpox-related symptoms as binary outcomes. The mean age of the participants was 24.6 (SD = 2.9) years. The prevalence of having intentions of self-isolation and informing close contacts after developing mpox-related symptoms was 88.6% (95% CI: 87.3%-89.9%) and 84.9% (95% CI: 83.5%-86.3%). Participants who were employed (adjusted odds ratio (AOR) = 1.474, 95% CI: 1.035-2.097; AOR = 1.371, 95% CI:1.002, 1.876), had higher mpox knowledge scores (AOR = 1.474, 95% CI: 1.035-2.097; AOR = 1.371, 95% CI: 1.002-1.876), and had higher perceived threats of mpox (AOR = 1.079, 95% CI: 1.030-1.130; AOR = 1.045, 95% CI: 1.002-1.090) were more likely to intend to self-isolate and inform close contacts. Participants who had MSM in-person gatherings in the past 6 months were more likely to intend to self-isolate (AOR = 1.392, 95% CI: 1.066-1.208). Participants with higher depression scores (AOR = 0.968, 95% CI: 0.948-0.989) and self-stigma (AOR = 0.975, 95% CI: 0.954-0.997) were less likely to intend to self-isolate and inform close contacts, respectively. Self-isolation and informing close contacts when developing disease-related symptoms are acceptable measures in response to mpox in China. Strengthening targeted risk communication and self-efficacy, raising disease knowledge, providing mental support, and reducing stigma toward the affected community are warranted.

Mpox risk perception and associated factors among Chinese young men who have sex with men: Results from a large cross-sectional survey.

The mpox outbreak since 2022 had attacked the community of men who have sex with men (MSM) heavily. This large cross-sectional study investigated the levels and associated factors of mpox risk perception among young MSM (YMSM) aged 18-29 years in six provincial regions of China in September 2022. The participants were recruited via facility-based sampling. Mpox risk perception was measured by perceived susceptibility and perceived severity of mpox. Geodetector was used to measure stratified heterogeneity of mpox risk perception. Univariate and multivariable linear regressions were used to examine the factors associated with mpox risk perception. A total of 2493 participants were included with a mean age of 24.6 years. The proportion of perceiving a susceptibility of mpox under different scenarios ranged 3.7%-17.0% and that of perceiving a severity of mpox ranged 81.6%-83.2%. Stratified heterogeneity of perceived susceptibility, perceived severity, and overall perceived risk of mpox were observed in several characteristics such as study sites, monthly income, risk behaviors, and psychosocial factors. Multivariable regression showed the level of mpox risk perception was positively associated with having in-person gathering activities (ba = 0.457, 95% CI: 0.208, 0.705), history of HIV infection (ba = 0.431, 95% CI: 0.028, 0.834), depressive symptoms (ba = 0.069, 95% CI: 0.049, 0.090), and self-stigma to MSM identity (ba = 0.047, 95% CI: 0.024, 0.071). The Chinese YMSM showed a high level of perceived severity of mpox but a low level of perceived susceptibility. It is warranted to strengthen targeted risk communication of mpox, develop comprehensive and unstigmatized health messages, and provide mental health support for YMSM.

Repurposing Non-pharmacological Interventions for Alzheimer's Diseases through Link Prediction on Biomedical Literature.

Recently, computational drug repurposing has emerged as a promising method for identifying new pharmaceutical interventions (PI) for Alzheimer's Disease (AD). Non-pharmaceutical interventions (NPI), such as Vitamin E and Music therapy, have great potential to improve cognitive function and slow the progression of AD, but have largely been unexplored. This study predicts novel NPIs for AD through link prediction on our developed biomedical knowledge graph. We constructed a comprehensive knowledge graph containing AD concepts and various potential interventions, called ADInt, by integrating a dietary supplement domain knowledge graph, SuppKG, with semantic relations from SemMedDB database. Four knowledge graph embedding models (TransE, RotatE, DistMult and ComplEX) and two graph convolutional network models (R-GCN and CompGCN) were compared to learn the representation of ADInt. R-GCN outperformed other models by evaluating on the time slice test set and the clinical trial test set and was used to generate the score tables of the link prediction task. Discovery patterns were applied to generate mechanism pathways for high scoring triples. Our ADInt had 162,213 nodes and 1,017,319 edges. The graph convolutional network model, R-GCN, performed best in both the Time Slicing test set (MR = 7.099, MRR = 0.5007, Hits@1 = 0.4112, Hits@3 = 0.5058, Hits@10 = 0.6804) and the Clinical Trials test set (MR = 1.731, MRR = 0.8582, Hits@1 = 0.7906, Hits@3 = 0.9033, Hits@10 = 0.9848). Among high scoring triples in the link prediction results, we found the plausible mechanism pathways of (Photodynamic therapy, PREVENTS, Alzheimer's Disease) and (Choerospondias axillaris, PREVENTS, Alzheimer's Disease) by discovery patterns and discussed them further. In conclusion, we presented a novel methodology to extend an existing knowledge graph and discover NPIs (dietary supplements (DS) and complementary and integrative health (CIH)) for AD. We used discovery patterns to find mechanisms for predicted triples to solve the poor interpretability of artificial neural networks. Our method can potentially be applied to other clinical problems, such as discovering drug adverse reactions and drug-drug interactions.

One LLM is not Enough: Harnessing the Power of Ensemble Learning for Medical Question Answering.

Objective: To enhance the accuracy and reliability of diverse medical question-answering (QA) tasks and investigate efficient approaches deploying the Large Language Models (LLM) technologies, We developed a novel ensemble learning pipeline by utilizing state-of-the-art LLMs, focusing on improving performance on diverse medical QA datasets. Materials and Methods: Our study employs three medical QA datasets: PubMedQA, MedQA-USMLE, and MedMCQA, each presenting unique challenges in biomedical question-answering. The proposed LLM-Synergy framework, focusing exclusively on zero-shot cases using LLMs, incorporates two primary ensemble methods. The first is a Boosting-based weighted majority vote ensemble, where decision-making is expedited and refined by assigning variable weights to different LLMs through a boosting algorithm. The second method is Cluster-based Dynamic Model Selection, which dynamically selects the most suitable LLM votes for each query, based on the characteristics of question contexts, using a clustering approach. Results: The Majority Weighted Vote and Dynamic Model Selection methods demonstrate superior performance compared to individual LLMs across three medical QA datasets. Specifically, the accuracies are 35.84%, 96.21%, and 37.26% for MedMCQA, PubMedQA, and MedQA-USMLE, respectively, with the Majority Weighted Vote. Correspondingly, the Dynamic Model Selection yields slightly higher accuracies of 38.01%, 96.36%, and 38.13%. Conclusion: The LLM-Synergy framework with two ensemble methods, represents a significant advancement in leveraging LLMs for medical QA tasks and provides an innovative way of efficiently utilizing the development with LLM Technologies, customing for both existing and potentially future challenge tasks in biomedical and health informatics research.

LLM Instruction-Example Adaptive Prompting (LEAP) Framework for Clinical Relation Extraction.

Objective: To investigate the demonstration in Large Language Models (LLMs) for clinical relation extraction. We focus on examining two types of adaptive demonstration: instruction adaptive prompting, and example adaptive prompting to understand their impacts and effectiveness. Materials and Methods: The study unfolds in two stages. Initially, we explored a range of demonstration components vital to LLMs' clinical data extraction, such as task descriptions and examples, and tested their combinations. Subsequently, we introduced the Instruction-Example Adaptive Prompting (LEAP) Framework, a system that integrates two types of adaptive prompts: one preceding instruction and another before examples. This framework is designed to systematically explore both adaptive task description and adaptive examples within the demonstration. We evaluated LEAP framework's performance on the DDI and BC5CDR chemical interaction datasets, applying it across LLMs such as Llama2-7b, Llama2-13b, and MedLLaMA_13B. Results: The study revealed that Instruction + Options + Examples and its expanded form substantially raised F1-scores over the standard Instruction + Options mode. LEAP framework excelled, especially with example adaptive prompting that outdid traditional instruction tuning across models. Notably, the MedLLAMA-13b model scored an impressive 95.13 F1 on the BC5CDR dataset with this method. Significant improvements were also seen in the DDI 2013 dataset, confirming the method's robustness in sophisticated data extraction. Conclusion: The LEAP framework presents a promising avenue for refining LLM training strategies, steering away from extensive finetuning towards more contextually rich and dynamic prompting methodologies.

Effects of Different Degrees of Xanthium spinosum Invasion on the Invasibility of Plant Communities in the Yili Grassland of Northwest China.

Studying the effects of different degrees of exotic plant invasion on native plants' community structure and plant diversity is essential for evaluating the harm caused to ecosystems by plant invasion. In this study, we investigated the effects of Xanthium spinosum, a widespread invasive species, on plant community species diversity and community stability in the Ili River Valley area of Xinjiang, China, under three invasion levels (no invasion and low, moderate, and heavy invasion), and the competitive advantage index, invasion intensity, and contribution of plant community species diversity to community stability and invasibility were determined for the prickly fungus under different degrees of invasion. The results show that there were significant differences (p < 0.05) in the species diversity and community stability of plant communities caused by different degrees of invasion of X. spinosum. The species diversity and stability of plant communities were negatively correlated with the community invasibility, competitive advantage, and invasion intensity of X. spinosum (p < 0.05); therefore, the competitive advantage and invasion intensity of X. spinosum increase with the increase of its invasion degree. On the contrary, community species diversity and stability decreased with the increase of its invasion degree, ultimately leading to differences in community invasibility under different invasion degrees. The Shannon-Wiener and Simpson's indices were the greatest contributors to community stability and invasibility, respectively. Moderate and heavy levels of invasion by X. spinosum reduced the diversity and stability of local plant communities, increased the invasibility of communities, and substantially affected the structures of plant communities. Therefore, the continued invasion by X. spinosum will have an immeasurable impact on the fragile ecosystems and diversity of indigenous species in Xinjiang. We recommend that this invasive species be controlled and eradicated at the early stages of invasion to prevent further harm.

Effect of Parasitic Native Plant Cuscuta australis on Growth and Competitive Ability of Two Invasive Xanthium Plants.

The competitive ability of invasive plants is a key factor in their successful invasion, and research on this ability of invasive plants can provide a theoretical basis for the prevention and control of invasive plants. This study used Cuscuta australis, Xanthium spinosum, and Xanthium italicum as research materials and conducted outdoor controlled pot experiments to compare and study the changes in the biomass, competitiveness, and growth cycle of X. spinosum and X. italicum parasitized by C. australis at different growth stages. The results showed that (1) parasitism by C. australis increased the biomass of X. spinosum and decreased that of X. italicum, but under parasitism, the root cap ratio of X. spinosum and X. italicum increased, and the fruit biomass ratio decreased, indicating that X. spinosum and X. italicum reduced the energy input for reproduction and increased the energy input for nutrient growth to resist the impact of C. australis parasitism; (2) the relative competitive intensity calculated based on the total biomass of a single plant showed a negative value for X. spinosum during parasitism at the flowering and fruit stages, indicating an increase in competitive ability, and X. italicum showed a positive value during parasitism at the seedling and flowering stages, indicating a decrease in competitive ability; and (3) the parasitism of C. australis significantly shortened the fruit stage of X. spinosum and X. italicum, leading to a significant advance in their flowering, fruiting, and fruit ripening times. Simultaneously, it significantly reduced the morphological indicators of biomass, plant height, and crown width. Thus, C. australis parasitism has a certain inhibitory effect on the competitive ability of some invasive plants and can shorten their growth cycle, the latter of which has an important impact on their reproduction and diffusion.

Mutation of Protoporphyrinogen IX Oxidase Gene Causes Spotted and Rolled Leaf and Its Overexpression Generates Herbicide Resistance in Rice.

Protoporphyrinogen IX (Protogen IX) oxidase (PPO) catalyzes the oxidation of Protogen IX to Proto IX. PPO is also the target site for diphenyl ether-type herbicides. In plants, there are two PPO encoding genes, PPO1 and PPO2. To date, no PPO gene or mutant has been characterized in monocotyledonous plants. In this study, we isolated a spotted and rolled leaf (sprl1) mutant in rice (Oryza sativa). The spotted leaf phenotype was sensitive to high light intensity and low temperature, but the rolled leaf phenotype was insensitive. We confirmed that the sprl1 phenotypes were caused by a single nucleotide substitution in the OsPPO1 (LOC_Os01g18320) gene. This gene is constitutively expressed, and its encoded product is localized to the chloroplast. The sprl1 mutant accumulated excess Proto(gen) IX and reactive oxygen species (ROS), resulting in necrotic lesions. The expressions of 26 genes associated with tetrapyrrole biosynthesis, photosynthesis, ROS accumulation, and rolled leaf were significantly altered in sprl1, demonstrating that these expression changes were coincident with the mutant phenotypes. Importantly, OsPPO1-overexpression transgenic plants were resistant to the herbicides oxyfluorfen and acifluorfen under field conditions, while having no distinct influence on plant growth and grain yield. These finding indicate that the OsPPO1 gene has the potential to engineer herbicide resistance in rice.

Discovering Cancer Subtypes via an Accurate Fusion Strategy on Multiple Profile Data.

Discovering cancer subtypes is useful for guiding clinical treatment of multiple cancers. Progressive profile technologies for tissue have accumulated diverse types of data. Based on these types of expression data, various computational methods have been proposed to predict cancer subtypes. It is crucial to study how to better integrate these multiple profiles of data. In this paper, we collect multiple profiles of data for five cancers on The Cancer Genome Atlas (TCGA). Then, we construct three similarity kernels for all patients of the same cancer by gene expression, miRNA expression and isoform expression data. We also propose a novel unsupervised multiple kernel fusion method, Similarity Kernel Fusion (SKF), in order to integrate three similarity kernels into one combined kernel. Finally, we make use of spectral clustering on the integrated kernel to predict cancer subtypes. In the experimental results, the P-values from the Cox regression model and survival curve analysis can be used to evaluate the performance of predicted subtypes on three datasets. Our kernel fusion method, SKF, has outstanding performance compared with single kernel and other multiple kernel fusion strategies. It demonstrates that our method can accurately identify more accurate subtypes on various kinds of cancers. Our cancer subtype prediction method can identify essential genes and biomarkers for disease diagnosis and prognosis, and we also discuss the possible side effects of therapies and treatment.

Individual and family level factors associated with physical and mental health-related quality of life among people living with HIV in rural China.

BACKGROUND: One of the major challenges faced by people living with HIV (PLH) is the compromised quality of life due to the negative impact of HIV on their health. HIV/AIDS control effort should go beyond laboratory and lay more emphasis on improving the health-related quality of life (HRQoL) for PLH. The objective of this study is to evaluate the physical and mental HRQoL of PLH in rural China, and explore the relationship between HRQoL and individual- and family-level factors. METHODS: A cross-sectional study was conducted among 522 PLH in Anhui, China. Participant's sociodemographic characteristics, family status, and HIV-related factors were collected. Physical health summary score (PHS) and mental health summary score (MHS) of quality of life were measured. Multiple linear regressions were conducted to estimate the association of the individual- and family-level factors with MHS and PHS. RESULTS: Male were more likely to report a higher level of PHS and MHS than female (ß = 0.123, P = 0.009; ß = 0.150, P = 0.002). Age was significantly negatively associated with the PHS (ß = - 0.232, P<0.001) when other variables were controlled. Family size remained negatively correlated with PHS (ß = - 0.105, P = 0.021). Family annual income was significantly positively associated with PHS and MHS (ß = 0.126, P = 0.003; ß = 0.135, P = 0.002). CONCLUSIONS: Future intervention should be carefully tailored to the specific needs of sub-populations (such as female and older PLH) considering their physical and mental HRQoL conditions. More attention and care should be provided to PLH with left-behind children in the family.

An automatic diagnostic network using skew-robust adversarial discriminative domain adaptation to evaluate the severity of depression.

BACKGROUND AND OBJECTIVE: Deep learning provides an automatic and robust solution to depression severity evaluation. However, despite it is powerful, there is a trade-off between robust performance and the cost of manual annotation. METHODS: Motivated by knowledge evolution and domain adaptation, we propose a deep evaluation network using skew-robust adversarial discriminative domain adaptation (SRADDA), which adaptively shifts its domain from a large-scale Twitter dataset to a small-scale depression interview dataset for evaluating the severity of depression. RESULTS: Without top-down selection, SRADDA-based severity evaluation network achieves regression errors of 6.38 (Root Mean Square Error,RMSE) and 4.93 (Mean Absolute Error,MAE), which outperforms baselines provided by the Audio/Visual Emotion Challenge and Workshop(AVEC 2017). However, with top-down selection, the network achieves comparable results (RMSE = 5.13, MAE = 4.08). CONCLUSIONS: Results show that SRADDA not only represents features robustly, but also performs comparably to state-of-the-art results on small-scale dataset, DAIC-WOZ.

Changes in behavioral outcomes among children affected by HIV: Results of a randomized controlled trial in China.

This study assessed the effects of a multilevel intervention on HIV-affected children's negative behaviors. A total of 536 children aged 6-18 years from 475 HIV-affected families in Anhui, China, participated in the randomized controlled trial. A significant overall intervention effect on reducing negative behaviors was observed at 18-month follow-up, and the effect remained at 24-month follow-up. The intervention showed greater effects for children aged 13-18 years than those aged 6-12 years. Study findings suggest that a multilevel intervention approach could be beneficial for reducing negative behavior in HIV-affected children. Age-specific programs should be considered to maximize the intervention effects.

Behavioral Problems Reported by Adolescents and Parents from HIV Affected Families in China.

This study examined the influence of various factors on the behavioral problems of adolescents affected by HIV while considering the agreement between adolescent and parent reports on problem behaviors. A total of 136 families each with one parent living with HIV (PLH) and one child aged 13-18 were included. Structural equation modeling was used to explore relationships between selected family measures and adolescent's problem behaviors. The correlation between the PLH and adolescent-reported behavioral problem measures was low (ß = 0.11). PLH-reported adolescent problem behaviors were negatively related to PLH-reported parental bonding (ß = -0.39), family routines (ß = -0.26), and positively associated with family conflict (ß = 0.21). Adolescent-reported family participation was associated with self-reported problem behaviors (ß = -0.35). Our study reported discrete perceptions of adolescent problem behaviors from parents' and adolescents' points of view. Future intervention efforts should emphasize family contextual factors to improve behavioral outcomes in adolescents affected by HIV.

FKL-Spa-LapRLS: an accurate method for identifying human microRNA-disease association.

BACKGROUND: In the process of post-transcription, microRNAs (miRNAs) are closely related to various complex human diseases. Traditional verification methods for miRNA-disease associations take a lot of time and expense, so it is especially important to design computational methods for detecting potential associations. Considering the restrictions of previous computational methods for predicting potential miRNAs-disease associations, we develop the model of FKL-Spa-LapRLS (Fast Kernel Learning Sparse kernel Laplacian Regularized Least Squares) to break through the limitations. RESULT: First, we extract three miRNA similarity kernels and three disease similarity kernels. Then, we combine these kernels into a single kernel through the Fast Kernel Learning (FKL) model, and use sparse kernel (Spa) to eliminate noise in the integrated similarity kernel. Finally, we find the associations via Laplacian Regularized Least Squares (LapRLS). Based on three evaluation methods, global and local leave-one-out cross validation (LOOCV), and 5-fold cross validation, the AUCs of our method achieve 0.9563, 0.8398 and 0.9535, thus it can be seen that our method is reliable. Then, we use case studies of eight neoplasms to further analyze the performance of our method. We find that most of the predicted miRNA-disease associations are confirmed by previous traditional experiments, and some important miRNAs should be paid more attention, which uncover more associations of various neoplasms than other miRNAs. CONCLUSIONS: Our proposed model can reveal miRNA-disease associations and improve the accuracy of correlation prediction for various diseases. Our method can be also easily extended with more similarity kernels.