Automated interventions for multiple health behaviors using conversational agents

Several randomized controlled trials of interventions involving embodied conversational agents have shown significant improvements in physical activity, fruit and vegetable consumption, and accessibility to online health information, among other outcomes.

“Several randomized controlled trials of interventions involving embodied conversational agents have shown significant improvements in physical activity, fruit and vegetable consumption, and accessibility to online health information, among other outcomes.”

Over the last two decades, a solid body of evidence has shown the potential benefits of using embodied conversational agents for health-related purposes.

“Over the last two decades, a solid body of evidence has shown the potential benefits of using embodied conversational agents for health-related purposes.”

Bickmore et al reported that the group with only diet-related intervention consumed significantly more fruits and vegetables than groups which received only physical activity intervention or both physical activity and diet intervention (P=.005); however, there were no significant differences among different groups for weight (P=.37).

“Bickmore et al [33] reported that the group with only diet-related intervention consumed significantly more fruits and vegetables than the groups which received only physical activity intervention or both physical activity and diet intervention (P=.005); however, there were no significant differences among different groups for weight (P=.37).”

The theory of motivational interviewing was used to devise interview questions addressed by NAO and motivation reinforcement messages provided by Bickmore et al's Chat1.

“The theory of motivational interviewing was also used to devise interview questions addressed by NAO [5] (the social robot) and the motivation reinforcement messages provided by Bickmore et al’s [33] Chat1.”

80% (4/5) of studies reported an increase in physical activity.

“First, 80% (4/5) of studies [33] reported an increase in physical activity.”

Bickmore et al reported no significant differences among conditions in the International Physical Activity Questionnaire (P=.37).

“However, only Bickmore et al [33] reported no significant differences among the conditions in the International Physical Activity Questionnaire (P=.37).”

20% (3/15) of studies reported an improvement in diet.

“Second, 20% (3/15) of studies [22,28,33] reported an improvement in diet.”

Of the 15 studies, 7 (47%) targeted healthy lifestyles, and 5 (33%) assessed efficacy of AI chatbots in promoting healthy lifestyles.

“Out of the 15 studies, 7 (47%) studies [5,21,22,28,29,32,33] targeted healthy lifestyles, and 5 (33%) studies [21,22,28,32,33] assessed the efficacy of AI chatbots in promoting healthy lifestyles through (1) physical activity levels, (2) healthy diet, (3) blood pressure, and (4) BMI.”

The findings add to the mixed evidence base on nutritional ECAs.

“Our findings might, on first sight, contradict our hypotheses, and add to the mixed evidence base on nutritional ECAs [5,6,44].”

The ECA shows particular promise for conveying behavioral change strategies to patients.

“One technology, called the embodied conversational agent (ECA), shows particular promise for conveying behavioral change strategies to patients [9, 12].”

Other studies have yielded positive outcomes for ECAs to deliver health education on topics such as exercise, eating fruits and vegetables, and preconception care.

“Other studies have also yielded positive outcomes for ECAs to deliver health education on topics such as: exercise, eating fruits and vegetables, and preconception care [12, 16, 21–24].”