Developing Effective Behavior Change Interventions: Some Lessons Learned from Behavioral Research

Author(s):  
Martin Fishbein
2020 ◽  
Vol 54 (12) ◽  
pp. 942-947
Author(s):  
Pol Mac Aonghusa ◽  
Susan Michie

Abstract Background Artificial Intelligence (AI) is transforming the process of scientific research. AI, coupled with availability of large datasets and increasing computational power, is accelerating progress in areas such as genetics, climate change and astronomy [NeurIPS 2019 Workshop Tackling Climate Change with Machine Learning, Vancouver, Canada; Hausen R, Robertson BE. Morpheus: A deep learning framework for the pixel-level analysis of astronomical image data. Astrophys J Suppl Ser. 2020;248:20; Dias R, Torkamani A. AI in clinical and genomic diagnostics. Genome Med. 2019;11:70.]. The application of AI in behavioral science is still in its infancy and realizing the promise of AI requires adapting current practices. Purposes By using AI to synthesize and interpret behavior change intervention evaluation report findings at a scale beyond human capability, the HBCP seeks to improve the efficiency and effectiveness of research activities. We explore challenges facing AI adoption in behavioral science through the lens of lessons learned during the Human Behaviour-Change Project (HBCP). Methods The project used an iterative cycle of development and testing of AI algorithms. Using a corpus of published research reports of randomized controlled trials of behavioral interventions, behavioral science experts annotated occurrences of interventions and outcomes. AI algorithms were trained to recognize natural language patterns associated with interventions and outcomes from the expert human annotations. Once trained, the AI algorithms were used to predict outcomes for interventions that were checked by behavioral scientists. Results Intervention reports contain many items of information needing to be extracted and these are expressed in hugely variable and idiosyncratic language used in research reports to convey information makes developing algorithms to extract all the information with near perfect accuracy impractical. However, statistical matching algorithms combined with advanced machine learning approaches created reasonably accurate outcome predictions from incomplete data. Conclusions AI holds promise for achieving the goal of predicting outcomes of behavior change interventions, based on information that is automatically extracted from intervention evaluation reports. This information can be used to train knowledge systems using machine learning and reasoning algorithms.


2021 ◽  
Vol 1 (2) ◽  
Author(s):  
Manuel Ester ◽  
Julianna Dreger ◽  
Utkarsh Subnis ◽  
Shaneel Pathak ◽  
S.Nicole Culos-Reed

The promotion of physical activity behavior change among adults with cancer is a research priority. Within this field, increasing attention is being devoted to the use of health technology, which includes mobile phones and applications, or apps, to support and deliver physical activity behavior change interventions. While building a mobile app is a popular proposal among exercise oncology researchers, little practical information exists on how this process should be done or what considerations researchers should take in collaboration with participants and industry. The present article provides an overview of recent experiences with app development in exercise oncology and outlines several recommendations for future research. Methods and Results: After forming an interdisciplinary team of researchers, industry partners, and exercise oncology program participants, an iterative, user-centered app improvement process was followed to collect feedback and make meaningful changes to an existing mobile health app for its use in exercise oncology. Participant feedback was summarized and addressed collaboratively via open discussion and detailed action plans. Changes made include enhanced introductory materials for the app and improvements to usability and personalization. Some requests remain to be addressed in future updates. Two challenges identified during the app improvement process were balancing the unique needs and priorities of all parties, as well as addressing the variable feedback from a variable population of adults with cancer. Conclusions and significance: A multidisciplinary participant-oriented app improvement process led to meaningful updates to the mobile application of interest, preparing researchers to carry out an evaluation of its effectiveness within exercise oncology. Furthermore, based on lessons learned, the research team present key recommendations to consider in future mobile app research before, during, and after the development process.


Author(s):  
Amanda Whittal ◽  
Lou Atkins ◽  
Oliver Rudolf Herber

Abstract Substantial inconsistency exists in the effectiveness of existing interventions to improve heart failure (HF) self-care, which can be partially explained by the fact that self-management interventions often lack theoretical models that underpin intervention development. The COM-B behavior model is a comprehensive theoretical framework that can be used to develop effective, theory-based interventions. The aim of this article is to highlight the challenges and practical solutions when applying the COM-B model to HF self-care, in order to provide useful support for researchers intending to use the model for designing behavior change interventions. “The Behaviour Change Wheel” handbook provides a step-by-step guide to understand and change behavior. When following the guide, some practical and methodological challenges were encountered. Lessons learnt to overcome these challenges are reported. Although the handbook is a comprehensive guide for designing behavior change interventions, a number of challenges arose. For example, the descriptions provided in the guide were not always sufficient to make solid judgments on how to categorize determinants; narrowing down intervention possibilities to a manageable number and prioritizing potential behavior change techniques over others involved a certain amount of subjectivity in an otherwise highly systematic and structured approach. For the encountered challenges, solutions are provided to illustrate how the model was applied practically to design theory-based behavior change interventions. This article provides a useful reference for researchers’ use of the COM-B behavior model, as it outlines challenges that may occur and potential solutions to overcome them.


2017 ◽  
Vol 25 (4) ◽  
pp. 387-400 ◽  
Author(s):  
Eszter Balku ◽  
Gergely Tóth ◽  
Erzsébet Nárai ◽  
Emese Zsiros ◽  
Péter Varsányi ◽  
...  

Author(s):  
Ana Paula Delgado Bomtempo Batalha ◽  
Isabela Coelho Ponciano ◽  
Gabriela Chaves ◽  
Diogo Carvalho Felício ◽  
Raquel Rodrigues Britto ◽  
...  

2021 ◽  
Vol 27 (1) ◽  
pp. 48-63
Author(s):  
Angela Makris ◽  
Mahmooda Khaliq ◽  
Elizabeth Perkins

Background: One in four Americans have a disability but remain an overlooked minority population at risk for health care disparities. Adults with disabilities can be high users of primary care but often face unmet needs and poor-quality care. Providers lack training, knowledge and have biased practices and behaviors toward people with disabilities (PWD); which ultimately undermines their quality of care. Focus of the Article: The aim is to identify behavior change interventions for decreasing health care disparities for people with disabilities in a healthcare setting, determine whether those interventions used key features of social marketing and identify gaps in research and practice. Research Question: To what extent has the social marketing framework been used to improve health care for PWD by influencing the behavior of health care providers in a primary health care setting? Program Design/Approach: Scoping Review. Importance to the Social Marketing Field: Social marketing has a long and robust history in health education and public health promotion, yet limited work has been done in the disabilities sector. The social marketing framework encompasses the appropriate features to aligned with the core principles of the social model of disability, which espouses that the barriers for PWD lie within society and not within the individual. Incorporating elements of the social model of disability into the social marketing framework could foster a better understanding of the separation of impairment and disability in the healthcare sector and open a new area of research for the field. Results: Four articles were found that target primary care providers. Overall, the studies aimed to increase knowledge, mostly for clinically practices and processes, not clinical behavior change. None were designed to capture if initial knowledge gains led to changes in behavior toward PWD. Recommendations: The lack of published research provides an opportunity to investigate both the applicability and efficacy of social marketing in reducing health care disparities for PWD in a primary care setting. Integrating the social model of disability into the social marketing framework may be an avenue to inform future interventions aimed to increase health equity and inclusiveness through behavior change interventions at a systems level.


Sign in / Sign up

Export Citation Format

Share Document