Nutripedia: The Fight against the Fake News in Nutrition during Pregnancy and Early Life

Evaluation framework for conversational agents with artificial intelligence in health interventions: a systematic scoping review

OBJECTIVES

Conversational agents (CAs) with emerging artificial intelligence present new opportunities to assist in health interventions but are difficult to evaluate, deterring their applications in the real world. We aimed to synthesize existing evidence and knowledge and outline an evaluation framework for CA interventions.

MATERIALS AND METHODS

We conducted a systematic scoping review to investigate designs and outcome measures used in the studies that evaluated CAs for health interventions. We then nested the results into an overarching digital health framework proposed by the World Health Organization (WHO).

RESULTS

The review included 81 studies evaluating CAs in experimental (n = 59), observational (n = 15) trials, and other research designs (n = 7). Most studies (n = 72, 89%) were published in the past 5 years. The proposed CA-evaluation framework includes 4 evaluation stages: (1) feasibility/usability, (2) efficacy, (3) effectiveness, and (4) implementation, aligning with WHO's stepwise evaluation strategy. Across these stages, this article presents the essential evidence of different study designs (n = 8), sample sizes, and main evaluation categories (n = 7) with subcategories (n = 40). The main evaluation categories included (1) functionality, (2) safety and information quality, (3) user experience, (4) clinical and health outcomes, (5) costs and cost benefits, (6) usage, adherence, and uptake, and (7) user characteristics for implementation research. Furthermore, the framework highlighted the essential evaluation areas (potential primary outcomes) and gaps across the evaluation stages.

DISCUSSION AND CONCLUSION

This review presents a new framework with practical design details to support the evaluation of CA interventions in healthcare research.

PROTOCOL REGISTRATION

The Open Science Framework (https://osf.io/9hq2v) on March 22, 2021.

Evaluating Messaging on Prenatal Health Behaviors Using Social Media Data: Systematic Review

BACKGROUND

Social media platforms are increasingly being used to disseminate messages about prenatal health. However, to date, we lack a systematic assessment of how to evaluate the impact of official prenatal health messaging and campaigns using social media data.

OBJECTIVE

This study aims to review both the published and gray literature on how official prenatal health messaging and campaigns have been evaluated to date in terms of impact, acceptability, effectiveness, and unintended consequences, using social media data.

METHODS

A total of 6 electronic databases were searched and supplemented with the hand-searching of reference lists. Both published and gray literature were eligible for review. Data were analyzed using content analysis for descriptive data and a thematic synthesis approach to summarize qualitative evidence. A quality appraisal tool, designed especially for use with social media data, was used to assess the quality of the included articles.

RESULTS

A total of 11 studies were eligible for the review. The results showed that the most common prenatal health behavior targeted was alcohol consumption, and Facebook was the most commonly used source of social media data. The majority (n=6) of articles used social media data for descriptive purposes only. The results also showed that there was a lack of evaluation of the effectiveness, acceptability, and unintended consequences of the prenatal health message or campaign.

CONCLUSIONS

Social media is a widely used and potentially valuable resource for communicating and evaluating prenatal health messaging. However, this review suggests that there is a need to develop and adopt sound methodology on how to evaluate prenatal health messaging using social media data, for the benefit of future research and to inform public health practice.

Diet-Nutrition Information Seeking, Source Trustworthiness, and Eating Behavior Changes: An International Web-Based Survey

To understand the extent to which different sources of diet and nutrition information are sought, trusted, and relied upon for making dietary changes, the present international web-based survey study gauged participants' (n = 3419) diet-nutrition information-seeking behaviors from 22 interpersonal and general sources with varying quality, trust levels in these sources, and reliance on each source for making dietary changes. Qualitative insights were also captured regarding trustworthiness formation. The results revealed a disconnect between source popularity and perceived trustworthiness. While nutrition-health websites, Google-Internet searches, and diet-health books were most commonly consulted, participants placed the highest level of trust in nutrition scientists, nutrition professionals, and scientific journals, suggesting that frequent information seeking from a subpar source may not be a reliable predictor of the level of trust assigned to it. Although the frequency of source-seeking behaviors and source trustworthiness both contributed to dietary changes, the latter appeared to have a more pronounced influence. When a source was less trusted, there was a reduced likelihood of relying on it for changing diet. Additionally, source seeking may not always translate into effective dietary change, as shown by the less strong correlation between the two. These associations significantly differed depending on the source.

The Era of Precision Nutrition in the Field of Reproductive Health and Pregnancy

When it comes to reproductive health, various lifestyle habits can act as major contributors to either an optimized or worsened scenario of female and male fertility [...].

Understanding the impact of an AI-enabled conversational agent mobile app on users' mental health and wellbeing with a self-reported maternal event: a mixed method real-world data mHealth study

Background

Maternal mental health care is variable and with limited accessibility. Artificial intelligence (AI) conversational agents (CAs) could potentially play an important role in supporting maternal mental health and wellbeing. Our study examined data from real-world users who self-reported a maternal event while engaging with a digital mental health and wellbeing AI-enabled CA app (Wysa) for emotional support. The study evaluated app effectiveness by comparing changes in self-reported depressive symptoms between a higher engaged group of users and a lower engaged group of users and derived qualitative insights into the behaviors exhibited among higher engaged maternal event users based on their conversations with the AI CA.

Methods

Real-world anonymised data from users who reported going through a maternal event during their conversation with the app was analyzed. For the first objective, users who completed two PHQ-9 self-reported assessments (n = 51) were grouped as either higher engaged users (n = 28) or lower engaged users (n = 23) based on their number of active session-days with the CA between two screenings. A non-parametric Mann-Whitney test (M-W) and non-parametric Common Language effect size was used to evaluate group differences in self-reported depressive symptoms. For the second objective, a Braun and Clarke thematic analysis was used to identify engagement behavior with the CA for the top quartile of higher engaged users (n = 10 of 51). Feedback on the app and demographic information was also explored.

Results

Results revealed a significant reduction in self-reported depressive symptoms among the higher engaged user group compared to lower engaged user group (M-W p = .004) with a high effect size (CL = 0.736). Furthermore, the top themes that emerged from the qualitative analysis revealed users expressed concerns, hopes, need for support, reframing their thoughts and expressing their victories and gratitude.

Conclusion

These findings provide preliminary evidence of the effectiveness and engagement and comfort of using this AI-based emotionally intelligent mobile app to support mental health and wellbeing across a range of maternal events and experiences.

Eating for 2: A Systematic Review of Dutch App Stores for Apps Promoting a Healthy Diet during Pregnancy

A healthy diet during pregnancy has been associated with beneficial child and maternal health outcomes but is challenging to achieve. Recent technological advances offer new opportunities to support pregnant women in their food choices-for instance, via apps. This is already reflected by a wide availability of pregnancy-related apps, but health care professionals feel unsure about their potential. Therefore, the Dutch Google Play Store and Apple App Store were reviewed to identify existing apps on diet and pregnancy. App quality was assessed using the 1) Mobile App Rating Scale (MARS; i.e., assessing functionality, aesthetics, engagement, information quality), 2) Dutch dietary guidelines for pregnant women, and 3) App Behavior Change Scale (ABACUS). Fifty-seven unique apps were identified with an average star rating of 4.2 ±  0.6 and MARS quality score of 3.2 ±  0.3, indicating a moderate quality. Most apps scored best in terms of functionality and aesthetics (4.0 ±  0.4 and 3.3 ±  0.6), but lowest in terms of engagement (2.5 ±  0.6). Regarding nutrition information provision, most apps were incomplete or deviated from the Dutch guidelines. Folic acid supplementation (91%), hygiene (81%), caffeine (79%), and alcohol (77%) were the most commonly addressed nutrition aspects, whereas licorice (11%), iodine (19%), and soy (18%) were only addressed in a few apps. Moreover, a median of 2 out of 21 ABACUS behavior change items were identified per app, which were predominantly related to the category "knowledge and information." Thus, despite the abundance of apps supporting a healthy diet during pregnancy in the Dutch app stores, there is an urgent need for apps with complete and scientifically sound dietary information that is supported by effective behavior change techniques.