Factors Affecting Engagement in Web-Based Health Care Patient Information: Narrative Review of the Literature

Chatbot Performance in Defining and Differentiating Palliative Care, Supportive Care, Hospice Care

CONTEXT

Artificial intelligence (AI) chatbot platforms are increasingly used by patients as sources of information. However, there is limited data on the performance of these platforms, especially regarding palliative care terms.

OBJECTIVES

We evaluated the accuracy, comprehensiveness, reliability, and readability of three AI platforms in defining and differentiating "palliative care," "supportive care," and "hospice care."

METHODS

We asked ChatGPT, Microsoft Bing Chat, Google Bard to define and differentiate "palliative care," "supportive care," and "hospice care" and provide three references. Outputs were randomized and assessed by six blinded palliative care physicians using 0-10 scales (10 = best) for accuracy, comprehensiveness, and reliability. Readability was assessed using Flesch Kincaid Grade Level and Flesch Reading Ease scores.

RESULTS

The mean (SD) accuracy scores for ChatGPT, Bard, and Bing Chat were 9.1 (1.3), 8.7 (1.5), and 8.2 (1.7), respectively; for comprehensiveness, the scores for the three platforms were 8.7 (1.5), 8.1 (1.9), and 5.6 (2.0), respectively; for reliability, the scores were 6.3 (2.5), 3.2 (3.1), and 7.1 (2.4), respectively. Despite generally high accuracy, we identified some major errors (e.g., Bard stated that supportive care had "the goal of prolonging life or even achieving a cure"). We found several major omissions, particularly with Bing Chat (e.g., no mention of interdisciplinary teams in palliative care or hospice care). References were often unreliable. Readability scores did not meet recommended levels for patient educational materials.

CONCLUSION

We identified important concerns regarding the accuracy, comprehensiveness, reliability, and readability of outputs from AI platforms. Further research is needed to improve their performance.

Predictors of participation in online self-management programs: A longitudinal observational study

PURPOSE/OBJECTIVE

Lack of patient participation and engagement remains a barrier to implementing effective online self-management and behavioral health interventions. Identifying patient characteristics associated with engagement rates may lead to interventions that improve engagement in traditional and online self-management programs. In this study, two online self-management and recovery programs were evaluated to identify factors that predict patient engagement.

RESEARCH METHOD/DESIGN

Predictors were collected in a questionnaire at baseline before 435 participants started either of the two interventions. One or two online lessons were completed per week with seven or eight total lessons to complete in each program, and each lesson took about 20-30 min to finish. Full patient engagement was defined as completing all lessons and assessments in the program and partial engagement as attempting at least one lesson or assessment.

RESULTS

Predictors of full patient engagement were self-rated confidence in completing the program or being over 60 years of age. Predictors of at least partial patient engagement were experienced ordering online or being over 50 years of age.

CONCLUSIONS/IMPLICATIONS

Identifying profiles of individuals who predict poor engagement may improve implementation and the health outcomes of intervention programs. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Parents' User Experience Accessing and Using a Web-Based Map of COVID-19 Recommendations for Health Decision-Making: Qualitative Descriptive Study

BACKGROUND

The eCOVID19 Recommendations Map & Gateway to Contextualization (RecMap) website was developed to identify all COVID-19 guidelines, assess the credibility and trustworthiness of the guidelines, and make recommendations understandable to various stakeholder groups. To date, little has been done to understand and explore parents' experiences when accessing and using the RecMap website for COVID-19 health decision-making.

OBJECTIVE

To explore (1) where parents look for COVID-19 health information and why, (2) parents' user experience when accessing and using the RecMap website to make health decisions, and (3) what knowledge mobilization activities are needed to increase parents' awareness, use, and engagement with the RecMap website.

METHODS

We conducted a qualitative descriptive study using semistructured interviews and a think-aloud activity with parents of children aged 18 years or younger living in Canada. Participants were asked to provide feedback on the RecMap website and to "think aloud" as they navigated the website to find relevant COVID-19 health recommendations. Demographic information was collected using a web-based questionnaire. A hybrid deductive and inductive thematic approach guided analysis and data synthesis.

RESULTS

A total of 21 participants (13/21, 62% mothers) were interviewed and participated in a think-aloud activity. The data were categorized into four sections, representative of key elements that deductively and inductively emerged from the data: (1) parent information seeking behaviors and preferences for COVID-19, (2) RecMap website usability, (3) perceived usefulness of the RecMap website, and (4) knowledge mobilization strategies to increase awareness, use, and engagement of the RecMap website. Parents primarily used the internet to find COVID-19 information and focused on sources that they determined to be credible, trustworthy, simple, and engaging. As the pandemic evolved, participants' information-seeking behaviors changed, specifically their topics of interest and search frequency. Most parents were not aware of the RecMap website before this study but found satisfaction with its concept and layout and expressed intentions to use and share it with others. Parents experienced some barriers to using the RecMap website and suggested key areas for improvement to facilitate its usability and perceived usefulness. Recommendations included a more user-friendly home page for lay audiences (separate public-facing user interface), improving the search and filter options, quicker navigation, clearer titles, more family-friendly graphics, and improving mobile-friendly access. Several strategies to disseminate the RecMap website were also expressed, including a mix of traditional and nontraditional methods (handouts and social media) in credible and high-traffic locations that parents frequent often.

CONCLUSIONS

Overall, parents liked the concept of the RecMap website but had some suggestions to improve its usability (language, navigation, and website interface). These findings can be used to improve the RecMap website for parents and offer insight for the development and dissemination of effective web-based health information tools and resources for the general public.

A content analysis of medication adherence material in patient educational resources about gout

Objective

This study aimed to investigate how medication adherence is addressed in online gout resources in six countries. We investigated how often adherence was referred to, the strategies suggested to improve patient adherence, and the types of nonadherence that were targeted. We also examined the readability of the adherence material.

Methods

A content analysis was conducted on 151 online gout resources from medical and health organisations in six predominantly English-speaking countries. Two reviewers coded the content of the websites into categories (kappa 0.80). The analysis involved coding the resources for reasons for nonadherence, and adherence-promoting strategies. Flesch-Kincaid Reading Ease scores and word count were also computed.

Results

Out of 151 websites examined, 77 websites discussed medication adherence (51%), with intentional nonadherence being more prevalent than unintentional nonadherence. 67 websites targeted different types of nonadherence, including drug-specific concerns (50%), misconceptions of gout curability and the necessity of medication (16%), forgetfulness (16%), and other practical challenges (5%). Strategies to promote adherence were found in one-third of the websites, with medication education being the most prevalent strategy (17%), followed by healthcare provider engagement (13%) and memory aid strategies (6%). On average, about 11% of the words (89.27, SD = 76.35) in the entire document were focused on adherence. Difficult reading comprehension was found in one-fifth of adherence-related websites.

Conclusion

Findings reveal limited medication adherence coverage and narrow strategies in online gout resources. Improved adherence portrayal is needed for effective gout management through comprehensive strategies and clear, understandable information.