In a recent study published in npj Digital Medicine, researchers evaluate the efficacy of chatbot interventions in improving individuals’ activity, food plan, and sleep patterns across various age- and ethnic groups. These virtual assistants were found to enhance an individual’s food selections and lifestyle, with text-based chatbots found to be simpler than their more vocal counterparts.

Study: Systematic review and meta-analysis of the effectiveness of chatbots on lifestyle behaviors. Image Credit: TZIDO SUN / Shutterstock.com

The advantages of healthcare chatbots

Poor lifestyle selections, specifically those pertaining to physical activity, food plan, and quality and quantity of sleep, are significant contributors to mental health issues and chronic diseases. Since 2010, the economic costs of chronic diseases alone will likely reach $45 trillion USD globally by 2025. Fortunately, these selections may be significantly improved with interventions from trained healthcare practitioners and, more recently, virtual assistants.

Chatbots, a variety of software that utilizes various types of communication to emulate human interaction, can improve physical and mental health through positive prompts, timely reminders, and knowledge delivery aimed toward lifestyle, food plan, and sleep interventions. Unlike their living healthcare counterparts, chatbots present quite a few benefits, including significant time-, travel-, and money savings. These advantages, combined with the ubiquity of the web and smartphones, make chatbots ideal for tackling the worldwide pandemics of poor food plan, sleep, and fitness.

Previous research has analyzed the efficacy of chatbots in improving lifestyle selections. Nevertheless, these studies have focused on specific improvements in food plan or physical activity in isolation or have been population or region specific, thereby inherently lacking a holistic, global outlook.

In regards to the study

In the current study, researchers conducted a review of scientific studies to elucidate the effectiveness of varied chatbots aimed toward improving sleep, food plan, and physical activity habits. Two thousand five hundred fourteen papers were reviewed through 4 rounds of title and abstract screened, with only 19 studies included in the ultimate review. The ultimate dataset comprised 3,567 participants between nine and 71 years of age, with sample sizes in individual studies between 25 and 958.

Research goal groups included spanned the health spectrum, including those with insomnia to sufficient sleep and cancer survivors. Furthermore, fifteen of the 19 papers analyzed physical activity, seven focused on food plan patterns, and five involved sleep.

Chatbot-only interventions comprised 58% of the raw data. The remaining studies involved multi-component interventions that utilized each virtual assistants and extra wearables or trackers that helped provide the chatbot with additional individualized information.

The aim of this review was to elucidate changes in total physical activity, which was evaluated by the variety of steps and activity minutes per week, the variety of fruit and veggies consumed as a proxy for food plan, and the duration and quality of sleep of the study participants.

Various kinds of chatbots, including those utilizing artificial intelligence [AI], text- and voice-based, in addition to non-AI chatbots, were also compared. This information allowed the researchers to find out which chatbots performed best at improving overall participant lifestyle.

Study findings

Every study reported a positive effect of chatbot intervention on total physical activity and the variety of weekly steps. On average, chatbot interventions contributed to the rise of 735 steps every day across the studies, no matter age, population, or region.

Similar results were noted for sleep, with a median increase of 45 minutes per night, and food plan, as demonstrated by no less than one additional fruit or vegetable serving every day, in chatbot-intervention groups. These results remained positive independent of the duration or intervention type, thereby establishing the advantages of employing chatbot interventions in healthcare.

Multi-component interventions could also be more helpful than chatbot-only interventions in regard to sleep. To this end, wearable trackers may provide chatbots with information on individual sleep quality that the participants themselves couldn’t provide to enhance the accuracy of chatbot recommendations ultimately.

Although no difference was noted between text- and voice-based chatbots in modifying sleep or physical activity, text-based chatbots were superior to voice-based chatbots in improving food plan. This will likely be because of the implementation of text-based chatbots in smartphone apps which might be all the time available, while voice-based chatbots are restricted to home use, reminiscent of smart speakers.

This statement contradicts previous research highlighting how the convenience of use of voice-based chatbots over text-based chatbots improves engagement and retention.

Conclusions

The study findings highlight how chatbots can provide an economical, in addition to a time- and travel-efficient alternative to traditional ‘in-person’ visits to healthcare professionals to combat the growing pandemic of lifestyle-related chronic health issues. Each AI and non-AI-based chatbots were found to be effective at improving individuals’ physical activity, food plan, and sleep patterns. Thus, chatbots are promising well-being management tools, no matter age, population, or nation-state of deployment.

Users may not fully understand the implications of sharing personal information with chatbots, which can collect data beyond their expectations and control.”

Importantly, data breaches have gotten increasingly common. Thus, the sensitivity of knowledge collected by chatbots, including age, sex, mental and physical state, and even personal preferences, can now not be circumvented by individually masking data points through grouping/categorizing.

This field of research remains to be in its infancy and listing out recommendations for future work, including larger sample sizes, improved a priori study design, and long-term follow-up, which, if done appropriately, might see us in a world where our smart devices ubiquitously aid healthcare practitioners (and apples) in keeping us fit and healthy.