Can AI-chatbots promote healthy lifestyle changes?

Artificial intelligence (AI) chatbots are capable of imitating human interactions with the help of spoken, written, or verbal communication with users. AI chatbots can provide critical health-related information and services, ultimately leading to promising technology-facilitated interventions.

Study: Artificial Intelligence (AI)-based Chatbots in Promoting Health Behavior Change: A Systematic Overview. Image Credit: TippaPatt / Shutterstock.com

AI chatbot in healthcare

Today’s telehealth and digital therapeutic interventions are associated with several challenges including discontinuity, low adherence, and inflexibility. AI chatbots are able to overcome these challenges and provide personalized on-demand support, higher interactivity and higher sustainability.

The AI ​​chatbot utilizes input data from various sources, followed by data analysis that is completed through natural language processing (NLP) and machine learning (ML). The data output then helps users achieve their health behavioral goals.

Thus, AI chatbots are able to promote a variety of health behaviors by providing effective interventions. In addition, this technology can provide additional benefits for health behavior change by integrating it into the embodied function.

Most of the previous research done on AI chatbots was aimed at improving mental health outcomes. Comparatively, recent research is increasingly focusing on using AI chatbots to trigger health behavior change.

However, one systematic review of the impact of AI chatbots on lifestyle modification was associated with several limitations. This includes the author’s inability to distinguish AI chatbots from other chatbots. In addition, this study only targets a limited set of behaviors and does not cover all potential platforms that could benefit from AI chatbots.

New systematic review published on the preprint server medRxiv* discusses the results of previous research on the characteristics, functions, and components of AI chatbot interventions, as well as their impact on various health behaviors.

About study

The current study was conducted in June 2022 and follows PRISMA guidelines. Here, the three authors searched seven bibliographic databases including IEEE Xplore, PubMed, JMIR publications, EMBASE, ACM Digital Library, Web of Science, and PsychINFO.

The search involves a combination of keywords that fall into three categories. The first category includes keywords related to AI-based chatbots, the second includes keywords related to health behaviors, and the third focuses on interventions.

The inclusion criteria for the search were studies involving intervention research focused on health behaviors, developed on existing AI platforms or AI algorithms, empirical studies using chatbots, English articles published between 1980 and 2022, as well as studies reporting intervention outcomes. quantitative or qualitative. All data were extracted from this study and underwent a quality assessment according to the National Institutes of Health (NIH) Quality Assessment Toolkit.

Study findings

A total of 15 studies matched the inclusion criteria, most of which were distributed in developed countries. The median sample size was 116 participants, while the mean was 7,200 participants.

Most of the studies included adult participants, while only two participants were less than 18 years old. All study participants had pre-existing conditions and included individuals with lower physical exercise, obesity, smokers, substance abusers, breast cancer patients, and Medicare recipients.

Targeted health behaviors include smoking cessation, promotion of a healthy lifestyle, reduction of substance abuse, and adherence to medication or medication. Moreover, only four studies reported using randomized control trials (RCTs), while the others used quasi-experimental designs.

The risk of reporting outcomes and bias in the randomization process was low, the risk of bias from the intended intervention was low to moderate, the risk of bias in the measurement of outcomes was moderate, and the risk of outcomes from unintended sources was high. All factors describing the AI ​​component are sufficient, except for handling unavailable input data and input data characteristics.

Of the 15 studies, six reported eligibility in terms of the average number of messages exchanged with chatbots per month and security. Additionally, 11 studies report usability in terms of content usability, ease of use of chatbots, user-initiated conversations, non-judgmental safe spaces, and out-of-office support. Acceptance and engagement were reported in 12 studies in terms of satisfaction, retention rate, technical issues, and duration of engagement.

Increases in physical activity were reported in six studies, along with improvements in diet in three studies via chatbot-based interventions. Smoking cessation was reported in four of the studies assessed, whereas one study reported a reduction in substance use and two studies reported increased adherence to medication or medication through the use of chatbots.

Several behavioral change theories are integrated into the chatbots including the transtheoretical model (TTM), cognitive behavioral therapy (CBT), social cognitive theory (SCT), the habit formation model, motivational interviewing, Mohr’s Supporting Accountability Model, and emotionally focused therapy to provide support. motivation and track participant behavior. Most of the studies targeted behavioral goal setting, used behavior monitoring, and offered behavior-related information, while four studies also provided emotional support.

Most studies use different AI techniques such as ML, NLP, Hybrid Health Recommender Systems (HHRS), hybrid techniques (ML and NLP), and facial tracking technologies to deliver personalized interventions. Chatbots primarily use text-based communication and are integrated into pre-existing platforms or delivered as independent platforms. In addition, most chatbots require data about users’ background information, their goals, and feedback on behavioral performance to ensure the delivery of personalized services.

Conclusion

Overall, AI chatbots can efficiently promote a healthy lifestyle, smoking cessation, and adherence to medication or medication. In addition, current research finds that AI chatbots demonstrate significant usability, feasibility, and acceptability.

Overall, AI chatbots are capable of delivering personalized and scalable interventions for a large and diverse population. However, further studies are needed to get an accurate description of AI-related processes, as AI chatbot intervention is still in its early stages.

Limitations

The current study did not include a meta-analysis and focused only on three behavioral outcomes. In addition, articles from unselected databases, articles in other languages, gray literature, and unpublished articles were not included in the study.

An additional limitation is that the intervention cannot provide a clear description of the excluded AI chatbots. This study also lacks generalizability and patient safety information is limited.

*Important Notice

medRxiv publish preliminary scientific reports that are not peer reviewed and, as such, should not be construed as conclusive, guide health-related clinical practice/behavior, or be treated as well-established information.

#AIchatbots #promote #healthy #lifestyle