The Human Behaviour-Change Project: harnessing the power of artificial intelligence and machine learning for evidence synthesis and interpretation

Abstract

BackgroundBehaviour change is key to addressing both the challenges facing human health and wellbeing and to promoting the uptake of research findings in health policy and practice. We need to make better use of the vast amount of accumulating evidence from behaviour change intervention (BCI) evaluations and promote the uptake of that evidence into a wide range of contexts. The scale and complexity of the task of synthesising and interpreting this evidence, and increasing evidence timeliness and accessibility, will require increased computer support.The Human Behaviour-Change Project (HBCP) will use Artificial Intelligence and Machine Learning to (i) develop and evaluate a ‘Knowledge System’ that automatically extracts, synthesises and interprets findings from BCI evaluation reports to generate new insights about behaviour change and improve prediction of intervention effectiveness and (ii) allow users, such as practitioners, policy makers and researchers, to easily and efficiently query the system to get answers to variants of the question ‘What works, compared with what, how well, with what exposure, with what behaviours (for how long), for whom, in what settings and why?’.MethodsThe HBCP will: a) develop an ontology of BCI evaluations and their reports linking effect sizes for given target behaviours with intervention content and delivery and mechanisms of action, as moderated by exposure, populations and settings; b) develop and train an automated feature extraction system to annotate BCI evaluation reports using this ontology; c) develop and train machine learning and reasoning algorithms to use the annotated BCI evaluation reports to predict effect sizes for particular combinations of behaviours, interventions, populations and settings; d) build user and machine interfaces for interrogating and updating the knowledge base; and e) evaluate all the above in terms of performance and utility.DiscussionThe HBCP aims to revolutionise our ability to synthesise, interpret and deliver evidence on behaviour change interventions that is up-to-date and tailored to user need and context. This will enhance the usefulness, and support the implementation of, that evidence.Electronic supplementary materialThe online version of this article (10.1186/s13012-017-0641-5) contains supplementary material, which is available to authorized users.

Semiautomated text analytics for qualitative data synthesis

“…In recent years, technological advances in automation have enhanced the efficiency of the review and analysis process. These advances have primarily focused on expediting the identification and synthesis of quantitative data . However, qualitative evidence syntheses are increasingly conducted as stand‐alone or mixed‐method systematic reviews, and automation is less developed in these types of review.…”

“…Expediting the process has been the subject of recent investigation, and potential approaches include the application of artificial intelligence and machine learning. 1 Despite its conventional roots in quantitative data, the ability of machine learning and associated technologies to automatically and efficiently code large sets of data makes it potentially valuable for qualitative research, particularly given the recent increase in availability of large textual datasets within widely available public data repositories 11 and other accessible platforms such as social media data. [12][13][14] Inevitably, the benefits of applying machine learning to qualitative data are matched with limitations.…”

Health Behavior Change for Obesity Management

“…While considerable progress is evident in this area, there are still many questions to be answered and challenges ahead, as shown for example by the variability of the effects of HBCIs and limited results from meta-analyses examining interactions between intervention features. The Human Behavior-Change Project led by Michie and colleagues ( humanbehaviorchange.org ) is an example of the most recent efforts in the field of Health behavior change science to promote evidence-based practice [51]. The project consists of a multidisciplinary team of behavioral scientists, computer scientists, and system architects, aiming to build an ontology of behavior change interventions that will classify and organize HBCI features (e.g.…”

“…The project consists of a multidisciplinary team of behavioral scientists, computer scientists, and system architects, aiming to build an ontology of behavior change interventions that will classify and organize HBCI features (e.g. BCTs, mechanisms of action, delivery, context) and develop a ‘knowledge system' that, through artificial intelligence and machine learning, will automatically extract, synthetize, and interpret information from HBCI research reports, therefore contributing to the design of effective evidence-based interventions [51]. Another landmark project is the US Science of Behavior Change project ( scienceofbehaviorchange.org ), which also seeks to standardize and synthetize assessment methods and research protocols in the area of human behavior change.…”

Addiction Theories and Constructs: a new series

“…The Human Behaviour Change Project (HBCP) is developing an ontology [the Behaviour Change Intervention Ontology (BCIO)] to underpin the extraction of key information from evaluations of behaviour change interventions [2]. The Human Behaviour Change Project (HBCP) is developing an ontology [the Behaviour Change Intervention Ontology (BCIO)] to underpin the extraction of key information from evaluations of behaviour change interventions [2].…”