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

Susan Michie, James Thomas, Marie Johnston, Pol Mac Aonghusa, John Shawe-Taylor, Michael P. Kelly, Léa A. Deleris, Ailbhe N. Finnerty, Marta M. Marques, Emma Norris, Alison O'Mara-Eves, Robert West

Research output: Contribution to journalArticle

24 Citations (Scopus)
4 Downloads (Pure)

Abstract

Background
Behaviour 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?’.

Methods
The 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.

Discussion
The 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.
Original languageEnglish
Article number121
Pages (from-to)1-12
Number of pages12
JournalImplementation Science
Volume12
DOIs
Publication statusPublished - 18 Oct 2017

Fingerprint

Artificial Intelligence
Machine Learning
Power (Psychology)
Aptitude
Knowledge Bases
Health Policy
Administrative Personnel
Population

Keywords

  • Behaviour change interventions
  • Implementation
  • Ontology
  • Machine learning
  • Natural language processing
  • Evidence synthesis
  • Artificial intelligence

Cite this

The Human Behaviour-Change Project : harnessing the power of artificial intelligence and machine learning for evidence synthesis and interpretation. / Michie, Susan; Thomas, James; Johnston, Marie; Mac Aonghusa, Pol; Shawe-Taylor, John; Kelly, Michael P.; Deleris, Léa A.; Finnerty, Ailbhe N.; Marques, Marta M.; Norris, Emma; O'Mara-Eves, Alison; West, Robert.

In: Implementation Science, Vol. 12, 121, 18.10.2017, p. 1-12.

Research output: Contribution to journalArticle

Michie, S, Thomas, J, Johnston, M, Mac Aonghusa, P, Shawe-Taylor, J, Kelly, MP, Deleris, LA, Finnerty, AN, Marques, MM, Norris, E, O'Mara-Eves, A & West, R 2017, 'The Human Behaviour-Change Project: harnessing the power of artificial intelligence and machine learning for evidence synthesis and interpretation', Implementation Science, vol. 12, 121, pp. 1-12. https://doi.org/10.1186/s13012-017-0641-5
Michie, Susan ; Thomas, James ; Johnston, Marie ; Mac Aonghusa, Pol ; Shawe-Taylor, John ; Kelly, Michael P. ; Deleris, Léa A. ; Finnerty, Ailbhe N. ; Marques, Marta M. ; Norris, Emma ; O'Mara-Eves, Alison ; West, Robert. / The Human Behaviour-Change Project : harnessing the power of artificial intelligence and machine learning for evidence synthesis and interpretation. In: Implementation Science. 2017 ; Vol. 12. pp. 1-12.
@article{e63b7767f0784c8b84d8051ad49156ed,
title = "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.",
keywords = "Behaviour change interventions, Implementation, Ontology, Machine learning, Natural language processing, Evidence synthesis, Artificial intelligence",
author = "Susan Michie and James Thomas and Marie Johnston and {Mac Aonghusa}, Pol and John Shawe-Taylor and Kelly, {Michael P.} and Deleris, {L{\'e}a A.} and Finnerty, {Ailbhe N.} and Marques, {Marta M.} and Emma Norris and Alison O'Mara-Eves and Robert West",
note = "The project is funded by a Wellcome Trust collaborative award [The Human Behaviour-Change Project: Building the science of behaviour change for complex intervention development’, 201,524/Z/16/Z]. During the preparation of the manuscript RW’s salary was funded by Cancer Research UK.",
year = "2017",
month = "10",
day = "18",
doi = "10.1186/s13012-017-0641-5",
language = "English",
volume = "12",
pages = "1--12",
journal = "Implementation Science",
issn = "1748-5908",
publisher = "BioMed Central",

}

TY - JOUR

T1 - The Human Behaviour-Change Project

T2 - harnessing the power of artificial intelligence and machine learning for evidence synthesis and interpretation

AU - Michie, Susan

AU - Thomas, James

AU - Johnston, Marie

AU - Mac Aonghusa, Pol

AU - Shawe-Taylor, John

AU - Kelly, Michael P.

AU - Deleris, Léa A.

AU - Finnerty, Ailbhe N.

AU - Marques, Marta M.

AU - Norris, Emma

AU - O'Mara-Eves, Alison

AU - West, Robert

N1 - The project is funded by a Wellcome Trust collaborative award [The Human Behaviour-Change Project: Building the science of behaviour change for complex intervention development’, 201,524/Z/16/Z]. During the preparation of the manuscript RW’s salary was funded by Cancer Research UK.

PY - 2017/10/18

Y1 - 2017/10/18

N2 - 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.

AB - 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.

KW - Behaviour change interventions

KW - Implementation

KW - Ontology

KW - Machine learning

KW - Natural language processing

KW - Evidence synthesis

KW - Artificial intelligence

U2 - 10.1186/s13012-017-0641-5

DO - 10.1186/s13012-017-0641-5

M3 - Article

VL - 12

SP - 1

EP - 12

JO - Implementation Science

JF - Implementation Science

SN - 1748-5908

M1 - 121

ER -