Patient Questions and Physician Responses in a Chinese Health Q&A Website: Content Analysis

Information Seeking and Receiving of Older Adults with Diabetes in the Online Health Community: An Information Need Contextualization Perspective

Online health communities (OHCs) are important online health communication channels for older adults with diabetes to access health information. When seeking health information, they often disclose a variety of contextual information (e.g., socio-economic situations) in their questions. Selective contextual information disclosure is a type of communication strategy for users in OHCs to elicit replies from others. In this study, we adopted text analysis to investigate what contextual information older adults with diabetes disclose to articulate their information needs and used the fixed-effect Poisson model to examine the relationships between different types of contextual information disclosure and informational support receipt. Our analyses were based on a dataset of 4,505 questions and corresponding replies from an online diabetes community. The results showed that cognitive information is the most frequently disclosed contextual information, while older adults tend to disclose demographic information in their questions less. Providing demographic and situational details in questions can enhance informational support receiving, resulting in an increased number of informational supports. However, disclosing cognitive, affective, informational channels, or support information does not significantly affect the informational support receiving. These findings can contribute to extending our existing understanding of information seekers' communication strategies in OHCs.

Unveiling the clinical incapabilities: a benchmarking study of GPT-4V(ision) for ophthalmic multimodal image analysis

PURPOSE

To evaluate the capabilities and incapabilities of a GPT-4V(ision)-based chatbot in interpreting ocular multimodal images.

METHODS

We developed a digital ophthalmologist app using GPT-4V and evaluated its performance with a dataset (60 images, 60 ophthalmic conditions, 6 modalities) that included slit-lamp, scanning laser ophthalmoscopy, fundus photography of the posterior pole (FPP), optical coherence tomography, fundus fluorescein angiography and ocular ultrasound images. The chatbot was tested with ten open-ended questions per image, covering examination identification, lesion detection, diagnosis and decision support. The responses were manually assessed for accuracy, usability, safety and diagnosis repeatability. Auto-evaluation was performed using sentence similarity and GPT-4-based auto-evaluation.

RESULTS

Out of 600 responses, 30.6% were accurate, 21.5% were highly usable and 55.6% were deemed as no harm. GPT-4V performed best with slit-lamp images, with 42.0%, 38.5% and 68.5% of the responses being accurate, highly usable and no harm, respectively. However, its performance was weaker in FPP images, with only 13.7%, 3.7% and 38.5% in the same categories. GPT-4V correctly identified 95.6% of the imaging modalities and showed varying accuracies in lesion identification (25.6%), diagnosis (16.1%) and decision support (24.0%). The overall repeatability of GPT-4V in diagnosing ocular images was 63.3% (38/60). The overall sentence similarity between responses generated by GPT-4V and human answers is 55.5%, with Spearman correlations of 0.569 for accuracy and 0.576 for usability.

CONCLUSION

GPT-4V currently is not yet suitable for clinical decision-making in ophthalmology. Our study serves as a benchmark for enhancing ophthalmic multimodal models.

Health information needs and feedback of users in the online TCM community

To improve the information service quality of the online Traditional Chinese Medicine (TCM) community, this study investigated users' information needs, feedback and the relationship between them. Using qualitative content analysis, the basic characteristics of users' needs were obtained. Logistic regression was used to explore the impact of different need characteristics of feedback. The main findings are as follows: 1) Disease consultation, health preservation, professional discussion, knowledge sharing and experience description are the major 5 types of information needs in the online TCM community; 2) Some users provided TCM-related information, such as the tongue image and the TCM four diagnosis; 3) A total of 78.8% of the posts received effective feedback, and the main types of feedback were answering, discussing, inquiring and emotional supporting; 4) Providing enough information can significantly and positively affect whether needs receive effective feedback, suggesting that users can present information about their condition in as many different formats as possible when articulating their needs.

Multilevel Classification of Users' Needs in Chinese Online Medical and Health Communities: Model Development and Evaluation Based on Graph Convolutional Network

BACKGROUND

Online medical and health communities provide a platform for internet users to share experiences and ask questions about medical and health issues. However, there are problems in these communities, such as the low accuracy of the classification of users' questions and the uneven health literacy of users, which affect the accuracy of user retrieval and the professionalism of the medical personnel answering the question. In this context, it is essential to study more effective classification methods of users' information needs.

OBJECTIVE

Most online medical and health communities tend to provide only disease-type labels, which do not give a comprehensive summary of users' needs. The study aims to construct a multilevel classification framework based on the graph convolutional network (GCN) model for users' needs in online medical and health communities so that users can perform more targeted information retrieval.

METHODS

Using the Chinese online medical and health community "Qiuyi" as an example, we crawled questions posted by users in the "Cardiovascular Disease" section as the data source. First, the disease types involved in the problem data were segmented by manual coding to generate the first-level label. Second, the needs were identified by K-means clustering to generate the users' information needs label as the second-level label. Finally, by constructing a GCN model, users' questions were automatically classified, thus realizing the multilevel classification of users' needs.

RESULTS

Based on the empirical research of questions posted by users in the "Cardiovascular Disease" section of Qiuyi, the hierarchical classification of users' questions (data) was realized. The classification models designed in the study achieved accuracy, precision, recall, and F1-score of 0.6265, 0.6328, 0.5788, and 0.5912, respectively. Compared with the traditional machine learning method naïve Bayes and the deep learning method hierarchical text classification convolutional neural network, our classification model showed better performance. At the same time, we also performed a single-level classification experiment on users' needs, which in comparison with the multilevel classification model exhibited a great improvement.

CONCLUSIONS

A multilevel classification framework has been designed based on the GCN model. The results demonstrated that the method is effective in classifying users' information needs in online medical and health communities. At the same time, users with different diseases have different directions for information needs, which plays an important role in providing diversified and targeted services to the online medical and health community. Our method is also applicable to other similar disease classifications.

Dentistry website analysis: An overview of the content of formulated questions and answers

Aim

This study aimed to analyze the content of questions and answers posted on dentistry websites.

Subject and methods

A mixed-method study was conducted in 2020. A total of 1354 related questions were included, of which 1182 were answered by dentists. The data was analyzed quantitatively according to the classification of the questions, main complaints of the subjects and length of the questions and answers using Excel₂₀₁₃. A qualitative content analysis was carried out also for data robustness and triangulation.

Results

Of the 1354 questions, 866 of them were categorized into 11 categories according to the main sub-classes of the International Classification of Diseases to Dentistry and Stomatology. Furthermore, the inquiries were allocated to 3 communication styles to present the users' main complaints that included contextual (52.33%), emotional (6.79%) and focal (40.89%) strategies. Results of the qualitative content analysis have led to 6 main themes: seeking the related recommendations of any actions, treatment seeking, information seeking, seeking for causes and reasons, seeking for oral and dental health recommendations and seeking for the dentists' diagnosis or comments.

Conclusions

The present study can be used for designing specific customized websites of dentistry and help the website managers for better optimization of the websites. All these interventions can pave the way for developing teleconsulting in dentistry for middle-income countries.

Self-Adaptive Telemedicine Specialist Recommendation Considering Specialist Activity and Patient Feedback

Purpose: With the rapid development of medical informatization, information overload and asymmetry have become major obstacles that limit patients' ability to find appropriate telemedicine specialists. Although doctor recommendation methods have been proposed, they fail to address data sparsity and cold-start issues, and electronic medical records (EMRs), patient preferences, potential interest of service providers and the changes over time are largely under-explored. Therefore, this study develops a self-adaptive telemedicine specialist recommendation method that incorporates specialist activity and patient utility feedback from the perspective of privacy protection to fill the research gaps. Methods: First, text vectorization, view similarity and probabilistic topic model are used to construct the patient and specialist feature models based on patients' EMRs and specialists' long- and short-term knowledge backgrounds, respectively. Second, the recommended specialist candidate set and recommendation index are obtained based on the similarity between patient features. Then, the specialist long-term knowledge feature model is used to update the newly registered specialist recommendation index and the recommended specialist candidate set to overcome the data sparsity and cold-start issues, and the specialist short-term knowledge feature model is adopted to extend the recommended specialist candidate set at the semantic level. Finally, we introduce the specialists' activity and patients' perceived utility feedback mechanism to construct a closed-loop adjusted and optimized specialist recommendation method. Results: An empirical study was conducted integrating EMRs of telemedicine patients from the National Telemedicine Center of China and specialists' profiles and ratings from an online healthcare platform. The proposed method successfully recommended relevant and active telemedicine specialists to the target patient, and increased the recommended opportunities for newly registered specialists to some extent. Conclusions: The proposed method emphasizes the adaptability and acceptability of the recommended results while ensuring their accuracy and relevance. Specialists' activity and patients' perceived utility jointly contribute to the acceptability of recommended results, and the recommendation strategy achieves the organic fusion of the two. Several comparative experiments demonstrate the effectiveness and operability of the hybrid recommendation strategy under the premise of data sparsity and privacy protection, enabling effective matching of patients' demand and service providers' capabilities, and providing beneficial insights for data-driven telemedicine services.

Pregnant women's coping strategies, participation roles and social support in the online community during the COVID-19

Pregnant women are experiencing enormous physical changes and suffering pregnancy-related losses, which may lead to depression symptoms during pregnancy. Given that the onslaught of COVID-19 had exacerbated pregnant women's anxiety because of disruptions in antenatal care and concerns regarding safe delivery, it is worth exploring how they obtain social support to cope with stress during COVID-19. Although many works have explored the impact of coping resources that people have on coping strategies, few studies have been done on the relationship between people's coping strategies and their acquisition of coping resources such as social support. To fill this gap, based on the stress and coping theory (SCT) and social penetration theory (SPT), this study investigates the impacts of pregnant women's different coping strategies on the acquisition of social support and the moderating role of the adverse impacts of COVID-19 and their online participation roles (support providers vs. support seekers) using the data of 814 pregnant women's online behavior from a parenting community in China1. Our study indicates that both women's superficial level disclosure and personal level disclosure positively affect online social support received. Moreover, self-disclosure about the adverse impacts of COVID-19 negatively moderates the relationship between personal level disclosure and social support received. Participation role positively moderates the relationship between personal level disclosure and social support received, but negatively moderates the relationship between superficial level disclosure and social support received. This paper makes theoretical contributions to the literature of SCT, SPT and the literature about social support in online communities.

Lurking or active? The influence of user participation behavior in online mental health communities on the choice and evaluation of doctors

BACKGROUND

Web-based psychological counseling sites have become an important source of health information and expert assistance. Although many studies have suggested the feasibility and effectiveness of online consultation, there is an insufficient understanding of the influence of the distinction of users' participation behaviors online on health behavior decision-making.

OBJECTIVE

This study aimed to investigate whether and how the differences in the online participation behaviors of users affect their doctor selection and evaluation characteristics.

METHODS

First, we collected information from 7,781 paid consultation clients from a professional mental health service platform in China. Effective indicators and variables were formed through data cleaning and classification. Next, we used a mixed methods research approach that included qualitative text analysis (topic and sentiment) and quantitative statistical analysis (ANOVA).

RESULTS

The ANOVA results show that differences in online participation behaviors (diving, searching and socializing) have a significant impact on doctor selection based on consultation price (F_7,780=6.05; P = 0.00), online service volume (F_7,780=4.76; P = 0.00), online reputation (F_7,780=4.30; P = 0.01) and online answers (F_7,780=5.76; P = 0.00). When evaluating doctors, the frequency of reviews (F_7,780=69.62; P = 0.00) and the average length of the text (F_7,780=15.33; P = 0.00) were significantly different among users. Two of the three topics, namely, service attitude (F_7,780=28.63; P = 0.00) and self-expression (F_7,780=40.83; P = 0.00), had significant effects. In addition, our results show that differences in participating behaviors have a significant impact on both the positive (F_7,780=7.30; P = 0.00) and negative (F_7,780=9.44; P = 0.00) emotions involved in evaluating doctors.

CONCLUSIONS

Our findings provide preliminary insights for establishing the relationship between users' online information behavior and health decision-making. Further research should be conducted to verify the validity of the results and help apply them to the design of personalized customized services for the users in an online health community.

Medical Needs Extraction for Breast Cancer Patients from Question and Answer Services: Natural Language Processing-Based Approach

BACKGROUND

A large number of patient narratives are available on various web services. As for web question and answer services, patient questions often relate to medical needs, and we expect these questions to provide clues for a better understanding of patients' medical needs.

OBJECTIVE

This study aimed to extract patients' needs and classify them into thematic categories. Clarifying patient needs is the first step in solving social issues that patients with cancer encounter.

METHODS

For this study, we used patient question texts containing the key phrase "breast cancer," available at the Yahoo! Japan question and answer service, Yahoo! Chiebukuro, which contains over 60,000 questions on cancer. First, we converted the question text into a vector representation. Next, the relevance between patient needs and existing cancer needs categories was calculated based on cosine similarity.

RESULTS

The proportion of correct classifications in our proposed method was approximately 70%. Considering the results of classifying questions, we found the variation and the number of needs.

CONCLUSIONS

We created 3 corpora to classify the problems of patients with cancer. The proposed method was able to classify the problems considering the question text. Moreover, as an application example, the question text that included the side effect signaling of drugs and the unmet needs of cancer patients could be extracted. Revealing these needs is important to fulfill the medical needs of patients with cancer.

Factors Influencing the Popularity of a Health-Related Answer on a Chinese Question-and-Answer Website: Case Study

BACKGROUND

Social question-and-answer (Q&A) sites have become an important venue for individuals to obtain and share human papillomavirus (HPV) vaccine knowledge.

OBJECTIVE

This study aims to examine how different features of an HPV vaccine-related answer are associated with users' response behaviors on social Q&A websites.

METHODS

A total of 2953 answers and 270 corresponding questions regarding the HPV vaccine were collected from a leading Chinese social Q&A platform, Zhihu. Three types of key features, including content, context, and contributor, were extracted and coded. Negative binomial regression models were used to examine their impact on the vote and comment count of an HPV vaccine-related answer.

RESULTS

The findings showed that both content length and vividness were positively related to the response behaviors of HPV vaccine-related answers. In addition, compared with answers under the question theme benefits and risks, answers under the question theme vaccination experience received fewer votes and answers under the theme news opinions received more votes but fewer comments. The effects of characteristics of contributors were also supported, suggesting that answers from a male contributor with more followers and no professional identity would attract more votes and comments from community members. The significant interaction effect between content and context features further showed that long and vivid answers about HPV vaccination experience were more likely to receive votes and comments of users than those about benefits and risks.

CONCLUSIONS

The study provides a complete picture of the underlying mechanism behind response behaviors of users toward HPV vaccine-related answers on social Q&A websites. The results help health community organizers develop better strategies for building and maintaining a vibrant web-based community for communicating HPV vaccine knowledge.

An empirical study of Q&A websites for game developers

The game development industry is growing, and training new developers in game development-specific abilities is essential to satisfying its need for skilled game developers. These developers require effective learning resources to acquire the information they need and improve their game development skills. Question and Answer (Q&A) websites stand out as some of the most used online learning resources in software development. Many studies have investigated how Q&A websites help software developers become more experienced. However, no studies have explored Q&A websites aimed at game development, and there is little information about how game developers use and interact with these websites. In this paper, we study four Q&A communities by analyzing game development data we collected from their websites and the 347 responses received on a survey we ran with game developers. We observe that the communities have declined over the past few years and identify factors that correlate to these changes. Using a Latent Dirichlet Allocation (LDA) model, we characterize the topics discussed in the communities. We also analyze how topics differ across communities and identify the most discussed topics. Furthermore, we find that survey respondents have a mostly negative view of the communities and tended to stop using the websites once they became more experienced. Finally, we provide recommendations on where game developers should post their questions, which can help mitigate the websites' declines and improve their effectiveness.