Dataset Information

Conversational Agent for Healthy Lifestyle Behavior Change: Web-Based Feasibility Study.

ABSTRACT:

Background

The rising incidence of chronic diseases is a growing concern, especially in Singapore, which is one of the high-income countries with the highest prevalence of diabetes. Interventions that promote healthy lifestyle behavior changes have been proven to be effective in reducing the progression of prediabetes to diabetes, but their in-person delivery may not be feasible on a large scale. Novel technologies such as conversational agents are a potential alternative for delivering behavioral interventions that promote healthy lifestyle behavior changes to the public.

Objective

The aim of this study is to assess the feasibility and acceptability of using a conversational agent promoting healthy lifestyle behavior changes in the general population in Singapore.

Methods

We performed a web-based, single-arm feasibility study. The participants were recruited through Facebook over 4 weeks. The Facebook Messenger conversational agent was used to deliver the intervention. The conversations focused on diet, exercise, sleep, and stress and aimed to promote healthy lifestyle behavior changes and improve the participants' knowledge of diabetes. Messages were sent to the participants four times a week (once for each of the 4 topics of focus) for 4 weeks. We assessed the feasibility of recruitment, defined as at least 75% (150/200) of our target sample of 200 participants in 4 weeks, as well as retention, defined as 33% (66/200) of the recruited sample completing the study. We also assessed the participants' satisfaction with, and usability of, the conversational agent. In addition, we performed baseline and follow-up assessments of quality of life, diabetes knowledge and risk perception, diet, exercise, sleep, and stress.

Results

We recruited 37.5% (75/200) of the target sample size in 1 month. Of the 75 eligible participants, 60 (80%) provided digital informed consent and completed baseline assessments. Of these 60 participants, 56 (93%) followed the study through till completion. Retention was high at 93% (56/60), along with engagement, denoted by 50% (30/60) of the participants communicating with the conversational agent at each interaction. Acceptability, usability, and satisfaction were generally high. Preliminary efficacy of the intervention showed no definitive improvements in health-related behavior.

Conclusions

The delivery of a conversational agent for healthy lifestyle behavior change through Facebook Messenger was feasible and acceptable. We were unable to recruit our planned sample solely using the free options in Facebook. However, participant retention and conversational agent engagement rates were high. Our findings provide important insights to inform the design of a future randomized controlled trial.

SUBMITTER: Dhinagaran DA

PROVIDER: S-EPMC8686401 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundVarenicline is a pharmacological intervention for tobacco dependence that is safe and effective in facilitating smoking cessation. Enhanced adherence to varenicline augments the probability of prolonged smoking abstinence. However, research has shown that one-third of people who use varenicline are nonadherent by the second week. There is evidence showing that behavioral support helps with medication adherence. We have designed an artificial intelligence (AI) conversational agent or health bot, called "ChatV," based on evidence of what works as well as what varenicline is, that can provide these supports. ChatV is an evidence-based, patient- and health care provider-informed health bot to improve adherence to varenicline. ChatV has been programmed to provide medication reminders, answer questions about varenicline and smoking cessation, and track medication intake and the number of cigarettes.ObjectiveThis study aims to explore the feasibility of the ChatV health bot, to examine if it is used as intended, and to determine the appropriateness of proceeding with a randomized controlled trial.MethodsWe will conduct a mixed methods feasibility study where we will pilot-test ChatV with 40 participants. Participants will be provided with a standard 12-week varenicline regimen and access to ChatV. Passive data collection will include adoption measures (how often participants use the chatbot, what features they used, when did they use it, etc). In addition, participants will complete questionnaires (at 1, 4, 8, and 12 weeks) assessing self-reported smoking status and varenicline adherence, as well as questions regarding the acceptability, appropriateness, and usability of the chatbot, and participate in an interview assessing acceptability, appropriateness, fidelity, and adoption. We will use "stop, amend, and go" progression criteria for pilot studies to decide if a randomized controlled trial is a reasonable next step and what modifications are required. A health equity lens will be adopted during participant recruitment and data analysis to understand and address the differences in uptake and use of this digital health solution among diverse sociodemographic groups. The taxonomy of implementation outcomes will be used to assess feasibility, that is, acceptability, appropriateness, fidelity, adoption, and usability. In addition, medication adherence and smoking cessation will be measured to assess the preliminary treatment effect. Interview data will be analyzed using the framework analysis method.ResultsParticipant enrollment for the study will begin in January 2024.ConclusionsBy using predetermined progression criteria, the results of this preliminary study will inform the determination of whether to advance toward a larger randomized controlled trial to test the effectiveness of the health bot. Additionally, this study will explore the acceptability, appropriateness, fidelity, adoption, and usability of the health bot. These insights will be instrumental in refining the intervention and the health bot.Trial registrationClinicalTrials.gov NCT05997901; https://classic.clinicaltrials.gov/ct2/show/NCT05997901.International registered report identifier (irrid)PRR1-10.2196/53556.

Project description:BACKGROUND:As the process of producing official health statistics for lifestyle diseases is slow, researchers have explored using Web search data as a proxy for lifestyle disease surveillance. Existing studies, however, are prone to at least one of the following issues: ad-hoc keyword selection, overfitting, insufficient predictive evaluation, lack of generalization, and failure to compare against trivial baselines. OBJECTIVE:The aims of this study were to (1) employ a corrective approach improving previous methods; (2) study the key limitations in using Google Trends for lifestyle disease surveillance; and (3) test the generalizability of our methodology to other countries beyond the United States. METHODS:For each of the target variables (diabetes, obesity, and exercise), prevalence rates were collected. After a rigorous keyword selection process, data from Google Trends were collected. These data were denormalized to form spatio-temporal indices. L1-regularized regression models were trained to predict prevalence rates from denormalized Google Trends indices. Models were tested on a held-out set and compared against baselines from the literature as well as a trivial last year equals this year baseline. A similar analysis was done using a multivariate spatio-temporal model where the previous year's prevalence was included as a covariate. This model was modified to create a time-lagged regression analysis framework. Finally, a hierarchical time-lagged multivariate spatio-temporal model was created to account for subnational trends in the data. The model trained on US data was, then, applied in a transfer learning framework to Canada. RESULTS:In the US context, our proposed models beat the performances of the prior work, as well as the trivial baselines. In terms of the mean absolute error (MAE), the best of our proposed models yields 24% improvement (0.72-0.55; P<.001) for diabetes; 18% improvement (1.20-0.99; P=.001) for obesity, and 34% improvement (2.89-1.95; P<.001) for exercise. Our proposed across-country transfer learning framework also shows promising results with an average Spearman and Pearson correlation of 0.70 for diabetes and 0.90 and 0.91 for obesity, respectively. CONCLUSIONS:Although our proposed models beat the baselines, we find the modeling of lifestyle diseases to be a challenging problem, one that requires an abundance of data as well as creative modeling strategies. In doing so, this study shows a low-to-moderate validity of Google Trends in the context of lifestyle disease surveillance, even when applying novel corrective approaches, including a proposed denormalization scheme. We envision qualitative analyses to be a more practical use of Google Trends in the context of lifestyle disease surveillance. For the quantitative analyses, the highest utility of using Google Trends is in the context of transfer learning where low-resource countries could benefit from high-resource countries by using proxy models.

Project description:BACKGROUND:Evidence-based practice for healthy lifestyle promotion in primary health care is supported internationally by national policies and guidelines but implementation in routine primary health care has been slow. Referral to digital interventions could lead to a larger proportion of patients accessing structured interventions for healthy lifestyle promotion, but such referral might have unknown implications for clinicians with patients accessing such interventions. This qualitative study aimed to explore the perceptions of clinicians in primary care on healthy lifestyle promotion with or without digital screening and intervention. METHODS:Focus group interviews were conducted at 10 primary care clinics in Sweden with clinicians from different health professions. Transcribed interviews were analyzed using content analysis, with inspiration from a phenomenological-hermeneutic method involving naïve understanding, structural analysis and comprehensive understanding. RESULTS:Two major themes captured clinicians' perceptions on healthy lifestyle promotion: 1) the need for structured professional practice and 2) deficient professional practice as a hinder for implementation. Sub-themes in theme 1 were striving towards professionalism, which for participants meant working in a standardized fashion, with replicable routines regardless of clinic, as well as being able to monitor statistics on individual patient and group levels; and embracing the future with critical optimism, meaning expecting to develop professionally but also being concerned about the consequences of integrating digital tools into primary care, particularly regarding the importance of personal interaction between patient and provider. For theme 2, sub-themes were being in an unmanageable situation, meaning not being able to do what is perceived as best for the patient due to lack of time and resources; and following one's perception, meaning working from a gut feeling, which for our participants also meant deviating from clinical routines. CONCLUSIONS:In efforts to increase evidence-based practice and lighten the burden of clinicians in primary care, decision- and policy-makers planning the introduction of digital tools for healthy lifestyle promotion will need to explicitly define their role as complements to face-to-face encounters. Our overriding hope is that this study will contribute to maintaining meaningfulness in the patient-clinician encounter, when digital tools are added to facilitate patient behavior change of unhealthy lifestyle behaviors.

Project description:BackgroundExercise and a healthy diet can improve the quality of life and prognosis of prostate cancer survivors, but there have been limited studies on the feasibility of web-based lifestyle interventions in this population.ObjectiveThis study aims to develop a data-driven grounded theory of web-based engagement by prostate cancer survivors based on their experience in the Community of Wellness, a 12-week randomized clinical trial designed to support healthy diet and exercise habits.MethodsTrueNTH's Community of Wellness was a four-arm pilot study of men with prostate cancer (N=202) who received progressive levels of behavioral support (level 1: website; level 2: website with individualized diet and exercise recommendations; level 3: website with individualized diet and exercise recommendations, Fitbit, and text messages; and level 4: website with individualized diet and exercise recommendations, Fitbit and text messages, and separate phone calls with an exercise trainer and a registered dietitian). The primary aim of the study is to determine the feasibility and estimate the effects on behaviors (results reported in a separate paper). Following the 12-week intervention, we invited participants to participate in 4 focus groups, one for each intervention level. In this report, we used grounded theory analyses including open, axial, and selective coding to generate codes and themes from the focus group transcripts. Categories were refined across levels using embodied categorization and constant comparative methods.ResultsIn total, 20 men with prostate cancer participated in the focus groups: 5, 4, 5, and 6 men in levels 1, 2, 3, and 4, respectively. Participants converged on 5 common factors influencing engagement with the intervention: environment (home environment, competing priorities, and other lifestyle programs), motivation (accountability and discordance experienced within the health care system), preparedness (technology literacy, health literacy, trust, and readiness to change), program design (communication, materials, and customization), and program support (education, ally, and community). Each of these factors influenced the survivors' long-term impressions and habits. We proposed a grounded theory associating these constructs to describe the components contributing to the intuitiveness of a web-based lifestyle intervention.ConclusionsThese analyses suggest that web-based lifestyle interventions are more intuitive when we optimize participants' technology and health literacy; tailor interface design, content, and feedback; and leverage key motivators (ie, health care providers, family members, web-based coach) and environmental factors (ie, familiarity with other lifestyle programs). Together, these grounded theory-based efforts may improve engagement with web-based interventions designed to support prostate cancer survivorship.

Project description:BackgroundHIV testing rates in sub-Saharan Africa remain below the targeted threshold, and primary care facilities struggle to provide adequate services. Innovative approaches that leverage digital technologies could improve HIV testing and access to treatment.ObjectiveThis study aimed to examine the feasibility and acceptability of Nolwazi_bot. It is an isiZulu-speaking conversational agent designed to support HIV self-testing (HIVST) in KwaZulu-Natal, South Africa.MethodsNolwazi_bot was designed with 4 different personalities that users could choose when selecting a counselor for their HIVST session. We recruited a convenience sample of 120 consenting adults and invited them to undertake an HIV self-test facilitated by the Nolwazi_bot. After testing, participants completed an interviewer-led posttest structured survey to assess their experience with the chatbot-supported HIVST.ResultsParticipants (N=120) ranged in age from 18 to 47 years, with half of them being men (61/120, 50.8%). Of the 120 participants, 111 (92.5%) had tested with a human counselor more than once. Of the 120 participants, 45 (37.5%) chose to be counseled by the female Nolwazi_bot personality aged between 18 and 25 years. Approximately one-fifth (21/120, 17.5%) of the participants who underwent an HIV self-test guided by the chatbot tested positive. Most participants (95/120, 79.2%) indicated that their HIV testing experience with a chatbot was much better than that with a human counselor. Many participants (93/120, 77.5%) reported that they felt as if they were talking to a real person, stating that the response tone and word choice of Nolwazi_bot reminded them of how they speak in daily conversations.ConclusionsThe study provides insights into the potential of digital technology interventions to support HIVST in low-income and middle-income countries. Although we wait to see the full benefits of mobile health, technological interventions including conversational agents or chatbots provide us with an excellent opportunity to improve HIVST by addressing the barriers associated with clinic-based HIV testing.