CMCN: Chinese medical concept normalization using continual learning and knowledge-enhanced

Medical Concept Normalization (MCN) is a crucial process for deep information extraction and natural language processing tasks, which plays a vital role in biomedical research. Although MCN in English has achieved significant research achievements, Chinese medical concept normalization (CMCN) remains insufficiently explored due to its complex syntactic structure and the paucity of Chinese medical semantic and ontology resources. In recent years, deep learning has been extensively applied across numerous natural language processing tasks, owing to its robust learning capabilities, adaptability, and transferability. It has proven to be well suited for intricate and specialized knowledge discovery research in the biomedical field. In this study, we conduct research on CMCN through the lens of deep learning. Specifically, our research introduces a model that leverages polymorphic semantic information and knowledge enhanced through multi-task learning and retain more important medical features through continual learning. As the cornerstone of CMCN, disease names are the main focus of this research. We evaluated various methodologies on Chinese disease dataset built by ourselves, finally achieving 76.12 % on Accuracy@1, 87.20 % on Accuracy@5 and 90.02 % on Accuracy@10 with our best-performing model GCBM-BSCL. This research not only advances the fields of knowledge mining and medical concept normalization but also enhances the integration and application of artificial intelligence in the medical and health field. We have published the source code and results on https://github.com/BearLiX/CMCN.

Lessons to be learned when designing comprehensible patient-oriented online information about temporomandibular disorders

BACKGROUND

Temporomandibular disorders (TMD) are a prevalent ailment with a global impact, affecting a substantial number of individuals. While some individuals are receiving treatment from orthodontists for TMD, a significant proportion of individuals obtain knowledge through websites.

OBJECTIVES

Our purpose had been to evaluate, from a patient-oriented perspective, the readability of home pages of websites scored in the 10 most prominent devoted to TMD. We also determined what level of education would have been needed to get an overview of the information on the websites under scrutiny. This approach ensures that our findings are centred on the patient experience, providing insights into how accessible and understandable websites about TMD.

METHODS

We determined the top 10 patient-focused English language websites by searching for 'temporomandibular disorders' in the 'no country redirect' plugin of the Google Chrome browser (www.google.com/ncr). The readability of the texts was assessed using the Gunning fog index (GFI), Coleman Liau index (CLI), Automated readability index (ARI) Simple Measure of Gobbledygook (SMOG), Flesch Kincald grade level (FKGL), Flesh reasing ease (FRE) (https://readabilityformulas.com).

RESULTS

The mean Flesch reading ease index score was determined to be 48.67, accompanied by a standard deviation of 15.04 and these websites require an average of 13.49 years of formal education (GFI), with a standard deviation of 2.62, for ease of understanding.

CONCLUSION

Our research indicates that a significant proportion of websites related to TMD can be defined as a level of complexity that exceeds the ability to read comprehension of the general population.

Search Engine Use for Health-Related Purposes: Behavioral Data on Online Health Information-Seeking in Germany

Internet searches for health-related purposes are common, with search engines like Google being the most popular starting point. However, results on the popularity of health information-seeking behaviors are based on self-report data, often criticized for suffering from incomplete recall, overreporting, and low reliability. Therefore, the current study builds on user-centric tracking of Internet use to reveal how individuals actually behave online. We conducted a secondary analysis of passively recorded Internet use logs to examine the prevalence of health-related search engine use, the types of health information searched for, and the sources visited after the searches. The analysis revealed two key findings. 1) We largely support earlier survey-based findings on the prevalence of online health information seeking with search engines and the relatively minor differences in information-seeking behaviors between socio-demographic groups. 2) We provide a more granular picture of the process of HISB using search engines by identifying different selection patterns depending on the scope of the searches.

Participatory Design and Evaluation of the "Stem Cells Australia" Website for Delivering Complex Health Knowledge: Mixed Methods Study

BACKGROUND

The internet has become a commonly used information source for people seeking to understand their health care options. However, inconsistent representation about what stem cell treatments are available and from whom, coupled with the lack of transparency about what has been shown to work or is even safe, can distract and mislead users. Given these challenges, there is a need to develop effective evidence-based tools for delivering information about health care options involving stem cells.

OBJECTIVE

A need to redesign an existing website in Australia was identified to provide trustworthy information about stem cell research and to counter misinformation. Using a participatory design approach to generate an understanding of what information users need for stem cell treatments, the Stem Cells Australia website serves as a case study for the development and evaluation of websites delivering complex messages about science and health.

METHODS

This study comprised 3 steps. First, a focus group and several one-on-one interviews with a purposive sample of users (n=12) were conducted to identify their needs and requirements. Second, we designed a new version of the website based on findings from the focus group and interviews. Finally, for evaluating the participatory design process, we collected 180 days of Google Analytics data for both the original and redesigned versions (90 days for each) and compared their differences using 2-sample z tests.

RESULTS

The feedback from participants was grouped into 3 themes-needed and unwanted information, how and where to obtain information, and their information preferences. These were translated into requirements for rebuilding the website. The redesigned version reached users in other continents, despite the daily numbers of users (-61.2%; P<.001) and sessions (-61.7%; P<.001) decreasing. The redesigned version also showed substantial decrease in daily bounce rate (-97.2%; P<.001), significant increase in the daily average of page reads per session (+110.8%; P<.001), and long daily average for session duration (+22.9%; P=.045). Navigation flow analysis showed more traffic toward web pages related to health conditions in the redesigned version.

CONCLUSIONS

Websites about stem cell research need to provide content for vulnerable global audiences. Participatory design that addresses knowledge gaps and information needs can produce better performance and engagement, which can be evaluated using Google Analytics, a common web analytics tool used by many websites. Learnings for improving the metrics regarding website identity, research updates, and clinical trials are concluded, which can inform the future design of websites seeking to engage users and provide reliable and accessible science and health information including but not limited to stem cell research and therapies.

Reflection on future directions: a systematic review of reported limitations and solutions in interactive information retrieval user studies

Purpose

The purpose of this paper is to understand how users behave and evaluate how systems with users are essential for interactive information retrieval (IIR) research. User study methodology serves as a primary approach to answering IIR research questions. In addition to designing user study procedures, understanding the limitations of varying study designs and discussing solutions to the limitations is also critical for improving the methods and advancing the knowledge in IIR.

Design/methodology/approach

Given this unresolved gap, we apply the faceted framework developed by Liu and Shah (2019) in systematically reviewing 131 IIR user studies recently published (2016–2021) on multiple IR and information science venues.

Findings

Our study achieve three goals: (1) extracting and synthesizing the reported limitations on multiple aspects of user study (e.g. recruitment, tasks, study procedures, system interfaces, data analysis methods) under associated facets; (2) summarizing the reported solutions to the limitations; (3) clarifying the connections between types of limitations and types of solutions.

Practical implications

The bibliography of user studies can be used by students and junior researchers who are new to user-centered IR studies as references for study design. Our results can facilitate the reflection and improvement on IR research methodology and serve as a checklist for evaluating customized IIR user studies in varying problem spaces.

Originality/value

To our knowledge, this work is the first study that systematically reviews the study limitations and solutions reported by IIR researchers in articles and empirically examines their connections to different study components.

Readability of online health information pertaining to migraine and headache in the UK

An estimated 46% of the worldwide adult population live with an active headache disorder, and it is thought that there is a proportion of headache and migraine sufferers who do not attend for medical care, instead choosing to manage their symptoms at home. The internet continues to act as a source of online health information for self-management, however, it is important that this information can be understood by the user. Research indicates that most health information online is written at a level too difficult for much of the UK population to understand. The aim of this study was to investigate the readability of online health information pertaining to headache and migraine for a UK-based internet user accessing the top four search engines. Searches for ‘headache’ and ‘migraine’ were performed on each search engine and results from the first page were selected for analysis. Five validated readability tests were used to analyse readability; Flesch-Kincaid Grade Level, Flesch Reading Ease, Gunning Fog Index, Coleman-Liau Index and Simple Measure of Gobbledygook Index. We found that the majority of online health information about migraine and headache is too difficult for the UK adult population to read. Findings highlight work is required to ensure that information from a wider variety of sources is easier to comprehend for much of the population in order for individuals to make informed decisions about health seeking and self-management of headache and migraine. Health information providers should weave readability analysis into their content design process, incorporating shorter sentences and simpler words in their description of conditions and treatment.

Trust in COVID-19 public health information

Understanding the factors that influence trust in public health information is critical for designing successful public health campaigns during pandemics such as COVID-19. We present findings from a cross-sectional survey of 454 US adults-243 older (65+) and 211 younger (18-64) adults-who responded to questionnaires on human values, trust in COVID-19 information sources, attention to information quality, self-efficacy, and factual knowledge about COVID-19. Path analysis showed that trust in direct personal contacts (B = 0.071, p = .04) and attention to information quality (B = 0.251, p < .001) were positively related to self-efficacy for coping with COVID-19. The human value of self-transcendence, which emphasizes valuing others as equals and being concerned with their welfare, had significant positive indirect effects on self-efficacy in coping with COVID-19 (mediated by attention to information quality; effect = 0.049, 95% CI 0.001-0.104) and factual knowledge about COVID-19 (also mediated by attention to information quality; effect = 0.037, 95% CI 0.003-0.089). Our path model offers guidance for fine-tuning strategies for effective public health messaging and serves as a basis for further research to better understand the societal impact of COVID-19 and other public health crises.

Exploring Resource-Sharing Behaviors for Finding Relevant Health Resources: Analysis of an Online Ovarian Cancer Community

BACKGROUND

Online health communities (OHCs) provide patients and survivors of ovarian cancer (OvCa) and their caregivers with help beyond traditional support channels, such as health care providers and clinicians. OvCa OHCs promote connections and exchanges of information among users with similar experiences. Users often exchange information, which leads to the sharing of resources in the form of web links. Although OHCs are important platforms for health management, concerns exist regarding the quality and relevance of shared resources. Previous studies have examined different aspects of resource-sharing behaviors, such as the purpose of sharing, the type of shared resources, and peer user reactions to shared resources in OHCs to evaluate resource exchange scenarios. However, there is a paucity of research examining whether resource-sharing behaviors can ultimately determine the relevance of shared resources.

OBJECTIVE

This study aimed to examine the association between OHC resource-sharing behaviors and the relevance of shared resources. We analyzed three aspects of resource-sharing behaviors: types of shared resources, purposes of sharing resources, and OHC users' reactions to shared resources.

METHODS

Using a retrospective design, data were extracted from the National Ovarian Cancer Coalition discussion forum. The relevance of a resource was classified into three levels: relevant, partially relevant, and not relevant. Resource-sharing behaviors were identified through manual content analysis. A significance test was performed to determine the association between resource relevance and resource-sharing behaviors.

RESULTS

Approximately 48.3% (85/176) of the shared resources were identified as relevant, 29.5% (52/176) as partially relevant, and 22.2% (39/176) as irrelevant. The study established a significant association between the types of shared resources (χ²₁₈=33.2; P<.001) and resource relevance (through chi-square tests of independence). Among the types of shared resources, health consumer materials such as health news (P<.001) and health organizations (P=.02) exhibited significantly more relevant resources. Patient educational materials (P<.001) and patient-generated resources (P=.01) were more significantly associated with partially relevant and irrelevant resources, respectively. Expert health materials, including academic literature, were only shared a few times but had significantly (P<.001) more relevant resources. A significant association (χ²₁₀=22.9; P<.001) was also established between the purpose of resource sharing and overall resource relevance. Resources shared with the purpose of providing additional readings (P=.01) and pointing to resources (P=.03) had significantly more relevant resources, whereas subjects for discussion and staying connected did not include any relevant shared resources.

CONCLUSIONS

The associations found between resource-sharing behaviors and the relevance of these resources can help in collecting relevant resources, along with the corresponding information needs from OvCa OHCs, on a large scale through automation. The results from this study can be leveraged to prioritize the resources required by survivors of OvCa and their caregivers, as well as to automate the search for relevant shared resources in OvCa OHCs.

Online Health Information Seeking Behaviors Among Older Adults: Systematic Scoping Review

Background

With the world’s population aging, more health-conscious older adults are seeking health information to make better-informed health decisions. The rapid growth of the internet has empowered older adults to access web-based health information sources. However, research explicitly exploring older adults’ online health information seeking (OHIS) behavior is still underway.

Objective

This systematic scoping review aims to understand older adults’ OHIS and answer four research questions: (1) What types of health information do older adults seek and where do they seek health information on the internet? (2) What are the factors that influence older adults’ OHIS? (3) What are the barriers to older adults’ OHIS? (4) How can we intervene and support older adults’ OHIS?

Methods

A comprehensive literature search was performed in November 2020, involving the following academic databases: Web of Science; Cochrane Library database; PubMed; MEDLINE; CINAHL Plus; APA PsycINFO; Library and Information Science Source; Library, Information Science and Technology Abstracts; Psychology and Behavioral Sciences Collection; Communication & Mass Media Complete; ABI/INFORM; and ACM Digital Library. The initial search identified 8047 publications through database search strategies. After the removal of duplicates, a data set consisting of 5949 publications was obtained for screening. Among these, 75 articles met the inclusion criteria. Qualitative content analysis was performed to identify themes related to the research questions.

Results

The results suggest that older adults seek 10 types of health information from 6 types of internet-based information sources and that 2 main categories of influencing factors, individual-related and source-related, impact older adults’ OHIS. Moreover, the results reveal that in their OHIS, older adults confront 3 types of barriers, namely individual, social, and those related to information and communication technologies. Some intervention programs based on educational training workshops have been created to intervene and support older adults’ OHIS.

Conclusions

Although OHIS has become increasingly common among older adults, the review reveals that older adults’ OHIS behavior is not adequately investigated. The findings suggest that more studies are needed to understand older adults’ OHIS behaviors and better support their medical and health decisions in OHIS. Based on the results, the review proposes multiple objectives for future studies, including (1) more investigations on the OHIS behavior of older adults above 85 years; (2) conducting more longitudinal, action research, and mixed methods studies; (3) elaboration of the mobile context and cross-platform scenario of older adults’ OHIS; (4) facilitating older adults’ OHIS by explicating technology affordance; and (5) promoting and measuring the performance of OHIS interventions for older adults.

Selective exposure to COVID-19 vaccination information: the influence of prior attitude, perceived threat level and information limit

Purpose

The massive amount of available information and functionality of the Internet makes selective information seeking effortless. This paper aims to understand the selective exposure to information during a health decision-making task.

Design/methodology/approach

This study conducted an experiment with a sample of 36 students to examine the influence of prior attitude, perceived threat level and information limit on users’ selective exposure to and recall of coronavirus disease 2019 (COVID-19) vaccination information. Participants were assigned to two conditions with or without an upper limit of the number of articles to be examined, and this study collected the number of articles read, the number of articles included in the report and recall score of the articles after one day of the experiment.

Findings

This study found that (1) participants with a negative attitude were more inclined to view attitude-consistent information and recalled attitude-consistent information more accurately, while participants with a positive attitude viewed more balanced information; (2) participants perceiving higher health threat level recalled attitude-consistent information more accurately; and (3) an upper limit on the number of articles to be viewed does not have any impact on selective exposure.

Research limitations/implications

The findings of this paper pinpoint the disparity of influence of positive and negative attitudes on selective exposure to and selective recall of health information, which was not previously recognized.

Practical implications

Vaccination campaigns should focus on reaching people with negative attitudes who are more prone to selective exposure to encourage them to seek more balanced information.

Originality/value

This is the first paper to explore selective exposure to COVID-19 vaccination information. This study found that people with a negative attitude and a higher level of perceived health threat are more prone to selective exposure, which was not found in previous research.

Characteristics of the health information seeking behavior of LGBTQ+ individuals: a systematic review on information types, information sources and influencing factors

Purpose

Lesbian, gay, bisexual, transgender and queer/questioning (LGBTQ+) individuals' health information seeking is an important topic across multiple disciplines and areas. The aim of this systematic review is to create a holistic view of sexual and gender minority individuals' health information seeking reported in multidisciplinary studies, with regard to the types of health information LGBTQ+ individuals sought and information sources they used, as well as the factors influencing their health information seeking behavior.

Design/methodology/approach

The review is based on the literature search in 10 major academic databases. A set of inclusion and exclusion criteria was applied to identify studies that provide evidence on LGBTQ+ individuals' health information seeking behavior. The studies were first screened by title and abstract to determine whether they met the inclusion criteria. The full texts of each relevant study were obtained to confirm whether the exclusion criteria were met. The reference lists of the included studies were manually scanned. The relevant information was then extracted from selected articles and analyzed using thematic content analysis.

Findings

A seed set of 3,122 articles published between 1997 and 2020 was evaluated, and 46 total articles were considered for further analysis. The review results show that two major categories of health information sought by LGBTQ+ individuals were sexual and nonsexual, which were further classified into 17 specific types. In terms of health information sources, researchers have reported that online resources, interpersonal sources and traditional media were frequently used. Moreover, 25 factors affecting LGBTQ+ individuals' health information seeking were identified from the literature.

Originality/value

Through evidence-based understanding, this review preliminarily bridged the knowledge gap in understanding the status quo of studies on LGBTQ+ individuals' health information seeking and proposed the potential research directions that information science researchers could contribute to this important area.

Exploring the factors in information seeking behavior: a perspective from multinational COPD online forums

This research establishes a theoretical framework for evaluating antecedents of the information seeking behaviors of online forum participants with chronic obstructive pulmonary disease (COPD). We evaluated the proposed framework using partial least squares structural equation modeling (PLS-SEM) after gathering data using a cross-sectional survey. We subsequently assessed the framework using importance-performance map analysis (IPMA). Findings suggest that perceived ease of use does not singularly influence COPD forum users' information seeking behavior. IPMA analysis reveals that the opportunity to interact with other forum members creates the greatest impact on COPD forum users' mindsets, among all the indicators. For healthcare professionals, the results of this study provide a blueprint in terms of utilizing COPD online forums to foster recurrent associations among forum administrators and users and by creating a strong social and informational resource for COPD information seekers.

Translation and Expansion: Enabling Laypeople Access to the COVID-19 Academic Collection

Academic collections, such as COVID-19 Open Research Dataset (CORD-19), contain a large number of scholarly articles regarding COVID-19 and other related viruses. These articles represent the latest development in combating COVID-19 pandemic in various disciplines. However, it is difficult for laypeople to access these articles due to the term mismatch problem caused by their limited medical knowledge. In this article, we present an effort of helping laypeople to access the CORD-19 collection by translating and expanding laypeople's keywords to their corresponding medical terminology using the National Library of Medicine's Consumer Health Vocabulary. We then developed a retrieval system called Search engine for Laypeople to access the COVID-19 literature (SLAC) using open-source software. Utilizing Centers for Disease Control and Prevention's FAQ questions as the basis for developing common questions that laypeople could be interested in, we performed a set of experiments for testing the SLAC system and the translation and expansion (T&E) process. Our experiment results demonstrate that the T&E process indeed helped to overcome the term mismatch problem and mapped laypeople terms to the medical terms in the academic articles. But we also found that not all laypeople's search topics are meaningful to search on the CORD-19 collection. This indicates the scope and the limitation of enabling laypeople to search on academic article collection for obtaining high-quality information.