JMIR Publications

ABSTRACT

Background:

Chatbot-led digital health interventions have magnified in popularity in recent years and have been successfully applied to a variety of health contexts, notably treatment of non-communicable diseases. However, for maximum public health impact, chatbots must move from only a tool to treat selected subpopulations, to one which can tackle a variety of lifestyle health conditions holistically.

Objective:

The current paper details findings from Elena+: Care for COVID-19, an app developed by digital health researchers around the world to tackle the collateral damage caused by lockdowns and social distancing, by offering pandemic lifestyle coaching across seven health areas: anxiety, loneliness, mental resources, sleep, diet and nutrition, physical activity, and COVID-19 information.

Methods:

The Elena+ app functions as a single-arm interventional study. The research used paired samples T-test and within subjects ANOVA to examine changes in health outcome assessments and user experience evaluations over time. To investigate the mediating role of behavioral activation (i.e., users setting behavioral intentions and reporting actual behaviors) we use mixed-effect regression models. Free-text entries were analyzed qualitatively.

Results:

Results show that there is a strong appetite for publicly available lifestyle coaching during the pandemic, with total downloads (N= 7’135) and 55.8% of downloaders opening the app (n=3’928). Greatest areas of health vulnerability as assessed with screening measures included: physical activity with 62% (n=1000) and anxiety with 46.5% (n=760) of individuals classified as vulnerable in these areas. Results showed that the app was effective in treatment of mental health; with a significant decrease in depression between first (14 days), second (28 days), and third (42 days) follow-ups: F2,38=7.01, p=.003, with a small effect size (η2G=0.14), and anxiety between first and second follow up: t54=3.7, p=<.001 with a medium effect size (Cohen d=.499). Those that followed the coaching program increased in net promoter score between the first and second assessment: t36=2.08, p=.045 with a small to medium effect size (Cohen d=.342). Mediation analyses showed that while increasing number of subtopics completed increased behavioral activation (i.e., match between behavioral intentions and self-reported actual behaviors), this did not mediate the relationship to improvements in health outcome assessments. User evaluations showed that net promoter score increased between first and second assessments: t36=2.08, p=0.045, Cohen d=0.342, with a small to medium effect size.

Conclusions:

In totality, the results show that: (i) there is public demand for chatbot led digital coaching, (ii) such tools can be effective in delivering treatment success, and (iii) such tools are highly valued by their long-term user base. Due to the fact the current intervention was developed at rapid speed to meet the emergency pandemic context, the future looks bright for other chatbot-led digital health interventions that tackle population level health issues.