Dataset Information

Determination of Patient Sentiment and Emotion in Ophthalmology: Infoveillance Tutorial on Web-Based Health Forum Discussions.

ABSTRACT:

Background

Clinical data in social media are an underused source of information with great potential to allow for a deeper understanding of patient values, attitudes, and preferences.

Objective

This tutorial aims to describe a novel, robust, and modular method for the sentiment analysis and emotion detection of free text from web-based forums and the factors to consider during its application.

Methods

We mined the discussion and user information of all posts containing search terms related to a medical subspecialty (oculoplastics) from MedHelp, the largest web-based platform for patient health forums. We used data cleaning and processing tools to define the relevant subset of results and prepare them for sentiment analysis. We executed sentiment and emotion analyses by using IBM Watson Natural Language Understanding to generate sentiment and emotion scores for the posts and their associated keywords. The keywords were aggregated using natural language processing tools.

Results

Overall, 39 oculoplastic-related search terms resulted in 46,381 eligible posts within 14,329 threads. Posts were written by 18,319 users (117 doctors; 18,202 patients) and included 201,611 associated keywords. Keywords that occurred ≥500 times in the corpus were used to identify the most prominent topics, including specific symptoms, medication, and complications. The sentiment and emotion scores of these keywords and eligible posts were analyzed to provide concrete examples of the potential of this methodology to allow for a better understanding of patients' attitudes. The overall sentiment score reflects a positive, neutral, or negative sentiment, whereas the emotion scores (anger, disgust, fear, joy, and sadness) represent the likelihood of the presence of the emotion. In keyword grouping analyses, medical signs, symptoms, and diseases had the lowest overall sentiment scores (-0.598). Complications were highly associated with sadness (0.485). Forum posts mentioning body parts were related to sadness (0.416) and fear (0.321). Administration was the category with the highest anger score (0.146). The top 6 forum subgroups had an overall negative sentiment score; the most negative one was the Neurology forum, with a score of -0.438. The Undiagnosed Symptoms forum had the highest sadness score (0.448). The least likely fearful posts were those from the Eye Care forum, with a score of 0.260. The overall sentiment score was much more negative before the doctor replied. The anger, disgust, fear, and sadness emotion scores decreased in likelihood, whereas joy was slightly more likely to be expressed after doctors replied.

Conclusions

This report allows physicians and researchers to efficiently mine and perform sentiment analysis on social media to better understand patients' perspectives and promote patient-centric care. Important factors to be considered during its application include evaluating the scope of the search; selecting search terms and understanding their linguistic usages; and establishing selection, filtering, and processing criteria for posts and keywords tailored to the desired results.

SUBMITTER: Nguyen AX

PROVIDER: S-EPMC8167608 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundThe increasing use of social media and mHealth apps has generated new opportunities for health care consumers to share information about their health and well-being. Information shared through social media contains not only medical information but also valuable information about how the survivors manage disease and recovery in the context of daily life.ObjectiveThe objective of this study was to determine the feasibility of acquiring and modeling the topics of a major online breast cancer support forum. Breast cancer patient support forums were selected to discover the hidden, less obvious aspects of disease management and recovery.MethodsFirst, manual topic categorization was performed using qualitative content analysis (QCA) of each individual forum board. Second, we requested permission from the Breastcancer.org Community for a more in-depth analysis of the postings. Topic modeling was then performed using open source software Machine Learning Language Toolkit, followed by multiple linear regression (MLR) analysis to detect highly correlated topics among the different website forums.ResultsQCA of the forums resulted in 20 categories of user discussion. The final topic model organized >4 million postings into 30 manageable topics. Using qualitative analysis of the topic models and statistical analysis, we grouped these 30 topics into 4 distinct clusters with similarity scores of ?0.80; these clusters were labeled Symptoms & Diagnosis, Treatment, Financial, and Family & Friends. A clinician review confirmed the clinical significance of the topic clusters, allowing for future detection of actionable items within social media postings. To identify the most significant topics across individual forums, MLR demonstrated that 6 topics-based on the Akaike information criterion values ranging from -642.75 to -412.32-were statistically significant.ConclusionsThe developed method provides an insight into the areas of interest and concern, including those not ascertainable in the clinic. Such topics included support from lay and professional caregivers and late side effects of therapy that consumers discuss in social media and may be of interest to clinicians. The developed methods and results indicate the potential of social media to inform the clinical workflow with regards to the impact of recovery on daily life.

Project description:ImportanceSince 2014, medical industry payment data to physicians have been public via the Open Payments database. Patient opinions regarding these data help us to understand concerns and policymakers to improve reporting mechanisms for such payments.ObjectiveTo assess patient perceptions of Open Payments information.Design, setting, and participantsThis cross-sectional, questionnaire-based study was conducted in 3 ophthalmology clinic sites of an academic institution in Manhattan, New York City, New York. All patients older than 18 years who were waiting for appointments were eligible. Data were collected from January to June 2016 and analyzed from June to September 2016.ExposuresParticipants answered 27 questions about the Open Payments database in English or Spanish. Demographic information was also collected.Main outcomes and measuresKey questionnaire results included patient awareness of the Open Payments database and perceptions of physicians' financial relationships. Cronbach α validation of the survey was performed, and Poisson multivariable regression analysis was performed to evaluate the association between patient characteristics and responses.ResultsA total of 407 individuals participated. The mean (SD) age of study participants was 58.8 (17.9) years, and 220 (54.2%) were women. Of these, 30 (7.3% [95% CI, 5.1%-19.4%]) were aware of the Open Payments database, and 109 (26.8% [95% CI, 24.8%-34.0%]) planned to access it. More than half (n = 212; 53.5% [95% CI, 48.6%-58.5%]) wanted to know if their physician receives industry payments. Regarding payments of any kind valuing $100, 161 (41.9% [95% CI, 37.0%-46.9%]) disapproved. Similarly, 178 (45.8% [95% CI, 40.8%-50.7%]) disapproved of $500 payments, and 221 (57.0% [95% CI, 52.0%-61.9%]) disapproved of $25 000 payments. Poisson multivariable regression analysis demonstrated that participants who took the survey in Spanish were 38% more likely to approve of physicians receiving payments than were those who took the survey in English (incidence rate ratio [IRR], 1.38 [95% CI, 1.19-1.59]; P < .001). For every 1 year of age, the likelihood of approval for a physician receiving payments decreased by 1% (IRR, 0.995 [95% CI, 0.99-1.00]; P = .007). Participants with graduate degrees were 20% less likely to approve of physicians receiving payments, compared with those with less than a high school degree (IRR, 0.80 [95% CI, 0.66-0.97]; P = .02).Conclusions and relevanceIf the survey is validated, and if these results are generalizable outside of the 3 academic centers in ophthalmology surveyed, the findings suggest that many patients disapprove of physicians receiving payments from industry. However, few patients had accessed the Open Payments database or planned to access it. Further investigation is required to determine if these results can be generalized for other settings.

Project description:BACKGROUND:A minimum standard based upon consensus decision making recommends a core set of tinnitus-specific health complaints (outcome domains) that should be assessed and reported in all clinical trials as this enables comparisons to be made across studies as well as data pooling for meta-analysis. OBJECTIVE:This study aimed to further clarify how the outcome domain concepts should be defined for 5 of the core set: tinnitus intrusiveness, sense of control, acceptance of tinnitus, concentration, and ability to ignore. This step requires a clear and fully elaborated definition for each outcome domain, moving from an abstract or a vague concept to an operationalized and measurable health-related construct, so that a suitable measurement instrument can then be identified. METHODS:A series of 5 focus group-style semistructured discussions were conducted via a Web-based discussion forum, each open for 2 weeks and ending with a vote. The participants included 148 tinnitus experts who completed a preceding e-Delphi survey that had generated the original set of minimum standards. The participants were health care users living with tinnitus, health care professionals, clinical researchers, commercial representatives, and funders. RESULTS:The Web discussions led to a revision of all 5 original plain language definitions that had been used in the preceding e-Delphi survey. Each revised definition was voted by 8 to 53 participants and reached the prespecified threshold of 70% consensus for all except tinnitus intrusiveness. Although a single definition was not agreed upon for tinnitus intrusiveness, the majority of participants shared the view that the concept should be sufficiently broad to encapsulate a range of subdomains. The examples included tinnitus awareness, unpleasantness, and impact on different aspects of everyday life. Thematic analysis of the 5 Web-based discussion threads gave important insights into expert interpretations of each core outcome domain, generating an operationalized and measurable health construct in each case. CONCLUSIONS:The qualitative data gathered during the Web-based discussion forum provided an important in-depth understanding of the health concepts that had raised a debate during earlier face-to-face meetings. The descriptive summaries and definitions provide sufficient operationalization of those concepts to proceed to the second stage of core outcome set development that is to identify and evaluate suitable measurement instruments. This study supports the use of Web-based peer discussion forums in defining health concepts.