About this Research Topic
This Research Topic will address research on applications of Artificial Intelligence for supporting change of health related behaviors and will focus on various aspects and stages of AI deployment: design, implementation, user experience and behavioral effect (in the short term and long term, from an individual and public health point of view ).
Health-related behaviors are crucial for our quality of life and have tremendous impact both at the stage of disease prevention and disease treatment. These are actions and habits individuals engage in that have an effect on their health and well-being, such as lifestyle choices, daily routines and related decision-making processes. Examples of health-related behaviors are physical exercise, sleep patterns, stress management addictions and substance use, adherence to medication regimens, and preventive health practices like vaccinations and screenings. Changing behavioral patterns is a complex and challenging process for most people because it involves multiple external and internal factors and tailored individual approaches but is an important aspect of public health, impacting both individuals and communities.
There are several examples of Artificial Intelligence (AI) technologies that have shown promise in supporting health-related behavior change. AI-powered Chatbots and Virtual Assistants can provide personalized health advice, answer questions and offer support and coaching for behavior change. They can engage in conversations, offer reminders and motivate individuals seeking to adopt healthier habits. AI-enabled wearable devices, such as fitness trackers and smartwatches, can collect data on physical activity, sleep patterns, and other health-related metrics, and interpret this data. This allows for tailored and personalized feedback, insights and individual recommendations to encourage individuals to make positive and sustained changes in their behaviors. Strengthened further by assisted self-monitoring of behaviors (medication, physical activity and stress management), these systems can provide personalized recommendations and suggest healthy alternatives.
Finally, AI-related methods (e.g., reinforcement learning, agent-based modelling) have been used to formally model users’ health-related behaviors and uses of digital health apps. These formal user representations can further support behavioral predictions and personalized intervention deliveries, as well as contribute to an improved adherence and behavior change effects at a population level
The World Health Organisation (WHO) recommends being cautious with using AI in healthcare due to ethical and risk related issues: for example, risks of AI to patient safety, cybersecurity and risks related to a reduced autonomy of users. Other challenges include: bias in AI algorithms, validation of AI-based approaches, dependency, user engagement and long-term sustainability. AI models and algorithms contain biases present in the data they are trained on, potentially leading to biased recommendations or interventions. These biases can disproportionately affect certain demographic groups and lead to widening health disparities. It is crucial to conduct rigorous research studies to evaluate not only the effectiveness, but also the safety, ethical implications and long-term impact of AI interventions. Ensuring long-term sustainability and adherence to interventions requires ongoing user involvement and feedback mechanisms for all groups.
The current issue will address various aspects of AI for health behavior change, including:
-Collaboration between AI and Public Health Experts: Studies highlighting successful collaborations between AI researchers and public health experts in designing, implementing, and evaluating behavior change interventions.
-Evaluation and Impact Assessment: Research that evaluates the effectiveness of AI-powered interventions on both individual and public health behavior outcomes, and the sustainability of behavior change over time.
-Risk Considerations: Articles discussing the ethical implications of using AI in health behavior change interventions, with a focus on equity, privacy, and transparency.
-Health Policy and Implementation: Contributions that discuss the integration of AI-driven behavior change strategies into public health policies and programs, including considerations of feasibility and scalability.
Health-related behaviors are crucial for our quality of life and have tremendous impact both at the stage of disease prevention and disease treatment. These are actions and habits individuals engage in that have an effect on their health and well-being, such as lifestyle choices, daily routines and related decision-making processes. Examples of health-related behaviors are physical exercise, sleep patterns, stress management addictions and substance use, adherence to medication regimens, and preventive health practices like vaccinations and screenings. Changing behavioral patterns is a complex and challenging process for most people because it involves multiple external and internal factors and tailored individual approaches but is an important aspect of public health, impacting both individuals and communities.
There are several examples of Artificial Intelligence (AI) technologies that have shown promise in supporting health-related behavior change. AI-powered Chatbots and Virtual Assistants can provide personalized health advice, answer questions and offer support and coaching for behavior change. They can engage in conversations, offer reminders and motivate individuals seeking to adopt healthier habits. AI-enabled wearable devices, such as fitness trackers and smartwatches, can collect data on physical activity, sleep patterns, and other health-related metrics, and interpret this data. This allows for tailored and personalized feedback, insights and individual recommendations to encourage individuals to make positive and sustained changes in their behaviors. Strengthened further by assisted self-monitoring of behaviors (medication, physical activity and stress management), these systems can provide personalized recommendations and suggest healthy alternatives.
Finally, AI-related methods (e.g., reinforcement learning, agent-based modelling) have been used to formally model users’ health-related behaviors and uses of digital health apps. These formal user representations can further support behavioral predictions and personalized intervention deliveries, as well as contribute to an improved adherence and behavior change effects at a population level
The World Health Organisation (WHO) recommends being cautious with using AI in healthcare due to ethical and risk related issues: for example, risks of AI to patient safety, cybersecurity and risks related to a reduced autonomy of users. Other challenges include: bias in AI algorithms, validation of AI-based approaches, dependency, user engagement and long-term sustainability. AI models and algorithms contain biases present in the data they are trained on, potentially leading to biased recommendations or interventions. These biases can disproportionately affect certain demographic groups and lead to widening health disparities. It is crucial to conduct rigorous research studies to evaluate not only the effectiveness, but also the safety, ethical implications and long-term impact of AI interventions. Ensuring long-term sustainability and adherence to interventions requires ongoing user involvement and feedback mechanisms for all groups.
The current issue will address various aspects of AI for health behavior change, including:
-Collaboration between AI and Public Health Experts: Studies highlighting successful collaborations between AI researchers and public health experts in designing, implementing, and evaluating behavior change interventions.
-Evaluation and Impact Assessment: Research that evaluates the effectiveness of AI-powered interventions on both individual and public health behavior outcomes, and the sustainability of behavior change over time.
-Risk Considerations: Articles discussing the ethical implications of using AI in health behavior change interventions, with a focus on equity, privacy, and transparency.
-Health Policy and Implementation: Contributions that discuss the integration of AI-driven behavior change strategies into public health policies and programs, including considerations of feasibility and scalability.
Keywords: Public health, Behaviour change, Digital health, Artificial Intelligence, Behaviour support
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
