Mitigating sex and gender biases in artificial intelligence for biomedicine, healthcare and behaviour change
By CBC Digi-Hub Blog, on 20 July 2020
Written by Dr Silvina Catuara Solarz on behalf of the Women’s Brain Project
Over the past two decades, there has been an emergence of digital health tools for the prevention and management of chronic disease arising from both the academic and industry sectors. A particularly prolific area is digital health tools relating to the promotion of mental health as well as physical health, with a focus on behaviour change and habit formation.
A central role in the advancement of these digital health tools is played by Artificial Intelligence (AI) systems, which aim to identify patterns of behaviour and provide personalised recommendations to the user according to their profile, with a view to optimising health outcomes. Al is also accelerating the progress on a myriad of complex tasks in the biomedical field, such as image recognition for diagnosis, identification of gene profiles associated with vulnerability of disease and prediction of disease prognosis based on electronic health records, that are aligned with the precision medicine approach.
AI and digital health tools are promising means for providing scalable, effective and accessible health solutions. However, a critical gap that exists on the path to achieving successful digital health tools is the robust and rigorous analysis of sex and gender differences in health. Sex and gender differences have been reported in chronic diseases such as diabetes, cardiovascular disorders, neurological diseases, mental health disorders, cancer, and there are plenty of health areas that remain unexplored.
Neglecting sex and gender differences in both the generation of health data and the development of AI for use within digital health tools will lead not only to suboptimal health practices but also to discrimination. In this regard, AI can act as a double-edged sword. On the one hand, if developed without removing existing biases and accounting for potential confounding factors, it risks magnifying and perpetuating existing sex and gender inequalities. On the other hand, if designed properly, AI has the potential to mitigate inequalities by accounting for sex and gender differences in disease and using this information for more accurate diagnosis and treatment.
Our work, recently published in npj Digital Medicine, focuses on the existing sex and gender biases in the generation of biomedical, clinical and digital health data as well as AI-based technological areas that are largely exposed to the risk of including sex and gender biases, namely big data analytics, digital biomarkers, natural language processing (NLP), and robotics.
In the context of mental health and behaviour change, some efforts have been made to include a sex and gender dimension to the implementation of theoretical frameworks for social and behaviour change communication. Still, further collection of data of the influence of sex and gender on aspects such as user experience, engagement and efficacy of digital health tools will provide a valuable starting point for the identification of optimal paths for efficient and tailored interventions.
Active and passive data input from users can be explored to derive sex and gender-associated insights through NLP and digital phenotyping. While these insights will shed light on how to optimise digital health tools for individual users, attention must be paid to potential biases that may arise. For example, NLP inferences from textual data used for training algorithms (an approach that is frequently used by mental health chatbots) are known to incorporate existing sex and gender biases (e.g. gendered semantic context of non-definitional words like ‘babysitter’ or ‘nurse’).
To avoid undesired biases, we strongly recommend pursuing ‘explainability’ in AI. This refers to activities focusing on the uncovering of reasons why and how a certain outcome, prediction or recommendation is generated by the AI system, thus increasing the transparency of the machine decisions that are otherwise unintelligible for humans.
Finally, we advocate that awareness of sex and gender differences and biases is increased by incorporating policy regulations and ethical considerations at each stage of data generation and AI development, to ensure that the systems maximise wellbeing and the health of the population.
This article was written on behalf of the Women’s Brain Project (WBP) www.womensbrainproject.com, an international non-profit organisation based in Switzerland. Composed largely by scientists, WBP aims at raising awareness, stimulating a global political discussion and performing research on sex and gender differences in brain and mental health, from basic science to novel technologies, as a gateway for precision medicine.
- Is sex and gender accounted for in available behaviour change apps ?
- Is sex and gender considered in the frameworks used in the evaluation of effectiveness of behaviour change apps ?
- What are the risks of excluding sex and gender data when developing and evaluating behaviour change apps? What are the potential privacy challenges associated with their inclusion?
Silvina Catuara Solarz holds a PhD in Biomedicine specialised in Translational Neuroscience by the Universitat Pompeu Fabra (Barcelona, Spain) and currently works as a Strategy Manager at Telefonica Innovation Alpha Health, a company focused on digital mental health solutions. As a member of the Women’s Brain Project executive committee team, she performs research on innovative technologies and their role in understanding sex and gender differences in health and disease. Her main interests include the application of digital technologies and AI into products to prevent and manage health conditions in a personalised and scalable way.
Find Silvina here:
By CBC Digi-Hub Blog, on 11 June 2020
Written by Dr Emma Norris & Professor Susan Michie on behalf of the HBCP team
Behaviour change is key to addressing many of the challenges facing the human population (e.g. reducing carbon emissions, preventing overuse of antibiotics, stopping tobacco use and reducing transmission of infectious diseases). A huge amount of information is being gathered on how best to achieve this in different situations but we have very limited capacity to collate it, synthesise it and use it to make recommendations.
What is the Human Behaviour-Change Project?
The Human Behaviour-Change Project (HBCP) is a Wellcome-funded project aiming to support decisions about behaviour change interventions using cutting-edge Artificial Intelligence (AI). The project aims to largely automate the process of collating, synthesising and interpreting evidence from the vast and growing literature on behaviour change intervention evaluations.
The project is a collaboration between behavioural and computer scientists and system architects that aims to create an AI-based Knowledge System that will scan the world’s published reports of behavioural intervention evaluations. This system will extract and analyse relevant information on interventions and their effectiveness organised using a ‘Behaviour Change Intervention Ontology’ (BCIO), developed as part of the project. You can read more on what ontologies are and how they can be used to structure knowledge here.
The Knowledge System will answer user queries and make recommendations as to what interventions are likely to work in a given scenario. It will also outline the level of confidence in and explain the process behind its answers. The first behaviour we are investigating is smoking cessation, drawing on published reports of randomised controlled trials.
The key activities involved in the project are to develop:
- An ontology of behaviour change interventions and evaluation reports: the Behaviour Change Intervention Ontology (BCIO).
- An automated system to extract information from behaviour change intervention evaluation reports using Natural Language Processing.
- A representation of that information structured according to the BCIO.
- Reasoning and Machine Learning algorithms to synthesise this information and make inferences in response to user queries.
- An interface for computers and human users to interact with the system.
We have now completed various parts of the Behaviour Change Intervention Ontology and are publishing these as the first papers in a collection within Wellcome Open Research.
Why are we publishing this collection in Wellcome Open Research?
In behaviour change, open access to knowledge is essential to enable the development of effective interventions by researchers, policy-makers and practitioners. The establishment of effective health interventions benefits all. We want to publish our key findings in one easily accessible place, providing free access to all the outputs from the project. Wellcome Open Research is a platform where all articles are made publicly available upon submission, before a transparent peer review process and a final Open Access version.
We are also making our methods, working papers and resources available via Open Science Framework. We would like to receive feedback on our papers via Wellcome Open Research. The HBCP is a huge undertaking and it will require involvement of much of the research community working together to advance it at the speed required.
Articles included in the collection so far
Our initial launch of papers in the collection contains five papers:
- Editorial – introducing the project.
- Methodology paper – explaining the methods we used for ontology development.
- Upper-level Ontology paper – specifying the overarching structure of the Behaviour Change Intervention Ontology.
- Mode of Delivery Ontology paper – describing a part of the BCIO that characterises ways that behaviour change interventions are delivered (e.g. by face-to-face contact, websites, video)
- Setting Ontology paper – describing a part of the BCIO that characterises the locations in which interventions are delivered (e.g. what country they are in, whether they are in hospitals or primary care)
We will continue to publish papers in the collection as other parts of the project are completed, with several currently in the pipeline.
Questions for discussion
- What are your thoughts on Open Access publishing and peer review?
- How could outputs from the Human Behaviour-Change Project be useful to your work?
Dr Emma Norris (@EJ_Norris) is a Research Fellow on the Behavioural Science team on the Human Behaviour-Change Project at UCL. Her research interests include the synthesis of health behaviour change research and development and evaluation of physical activity interventions.
Professor Susan Michie (@SusanMichie) is Principal Investigator of the Human Behaviour-Change Project, Professor of Health Psychology and Director of the Centre for Behaviour Change at UCL. Her research focuses on developing the science of behaviour change interventions and applying behavioural science to interventions. She works with a wide range of disciplines, practitioners and policy-makers and holds grants from a large number of organisations including the Wellcome Trust, National Institute of Health Research, Economic and Social Research Council and Cancer Research UK.
By CBC Digi-Hub Blog, on 16 April 2020
Written by Dr David Crane
What is happening now is a mass, shared, life-changing psychological event. Potentially. The long-term effects of any event are of course impossible to predict for individuals. But on a global level, the substantial changes so-far wrought by this pandemic suggests COVID-19 could have a lasting effect on the behaviour of a large number of people.
In the space of three months, a threat has gone in public consciousness from theoretical to powerful enough to force billions of people to make fundamental changes to their daily lives. Behaviours unthinkable a short time ago, such as staying at home for weeks on end, are now so commonly accepted as to make being outside feel uncomfortable. Behaviours still largely unconscious, such as touching one’s face, somehow need to be changed because there is a non-trivial chance that something so simple and commonplace could now lead to our, or somebody else’s, demise.
Everything we are doing to develop a vaccine and change our behaviour will hopefully mean that when compared to previous pandemics the number of deaths will be low. And it is probably true that our ancestors had to live with more uncertainty on a regular basis than we are experiencing now. So why might this event be so significant psychologically? Because it could result in a paradigm shift in our awareness of the fragility of life and the benefits of collaboration. One experienced by a great many people over a large swathe of the world at more or less the same time.
The chance that we or our loved ones might die in the near future has, for most of us, gone from effectively zero to something noticeably greater in a short space of time. The risk remains mercifully small but cannot be dismissed entirely, even by the young, healthy, rich and/or powerful. Those who downplay the risk will still probably be more careful about keeping their distance and washing their hands, even when not demanded by new social norms. And if the only reason this is done is for fear of infecting others, that still represents a substantial change in threat perception since Christmas.
By the time this is pandemic is over, it is likely that almost all of us will know people who have died and others who have suffered, even if we escape suffering ourselves. Awareness of death’s proximity will be increased by the availability of its news. TV, newspapers and radio will tell us about people we have heard of who have died, or tragedies that people we can relate to have suffered. Social media will be full of heart-wrenching stories from people we know who have lost people they loved; the most moving of which will be shared more widely themselves, so enlarging the circle of grief far beyond usual bounds.
A subject many people prefer not to think about will be pushed into consciousness for a considerable period of time. Reactions will fall along a spectrum of course, from totally unaffected to completely petrified. Though many people unaffected by a change in their proximity to death are likely to be affected by one or other of the loss of their job (now or possibly soon), wider concerns about the economy, fears for what society is about to go through, worries for other people, or just that deeply unsettling feeling that many of the things that used to be relied upon are now less secure.
Something microscopic has seemingly come out of nowhere to upend our world with astonishing speed. Finding this a destabilising experience seems a perfectly appropriate response. This is a profound change.
But profound changes do not have wholly negative outcomes. Human beings have the inherent capacity – and tendency – to make life-altering events turn to our advantage. In normal times we carry on doing what we’ve always done until it’s abundantly obvious it no longer works. It can take years of disconfirming experiences before we accept that things which used to relieve pain or bring pleasure now have the opposite effect. And those are the big, noticeable, things. Much of our now ineffective behaviour is too small to be seen.
In exceptional times change is thrust upon us. Routines are forcibly broken, usual behaviour prevented. We can’t do what we’ve always done because it is impossible, impractical or obviously ineffective. Which makes it easier to see what’s as it should be and what needs adjustment. Behaviour that might otherwise be automatic and habitual (like drinking alcohol when stressed), is brought into awareness, from where decisions about whether to continue are more easily made. Opportunities to gain clarity on our priorities happen rarely in our lifetime, it is hard to think when previously they have happened to so many people at the same time.
A force multiplier of COVID-19 is that along with opportunity to change, it also provides a significant amount of motivation too. Because the virus only makes obvious that which has always, and will always, be true: life is fragile and the future is uncertain. It’s easy to procrastinate when we think we’ve got plenty of time. We tend to be more proactive when we realise that’s not so. This principle is something we understand intellectually and have probably experienced mildly. The difference now is how salient it could become.
In addition to opportunity and motivation, the third element for behaviour change to take place, capability, could also be increased by the pandemic. Or rather, by its survival. Simply getting through this will boost many people’s self-efficacy and sense of resilience and resourcefulness; with people who experienced more doubts likely to see greater increases than people who experienced few. Capability is also increased by motivation to change, which could increase substantially, and skills teaching, which is abundant.
Thoughts of everyone doing whatever they want may inspire fears of a hedonistic, anarchic, free-for-all. But if that were true, we would expect to see people being at least equally selfish when they felt most threatened. If our evolutionary tendency was towards self-interest, surely that would be more obvious when our survival was at risk.
But selfish behaviour does not appear to be prevalent. The opposite, in fact. Millions of people are risking their lives so we can live ours. Hundreds of thousands of support groups have spontaneously formed so people can look after each other. Acts of generosity and thoughtfulness abound, amongst friends and strangers alike. This represents, I suggest, large-scale evidence of enlightened self-interest: the understanding that our interests are best served by helping others. Because there is nothing like feeling vulnerable to make us realise how much we need other people. And perhaps nothing has made more people feel more vulnerable than this.
By talking about positive outcomes I do not mean to belittle the great suffering that will occur. Many people will be left in dire circumstances as a result of this crisis, some may never fully recover from losing people they love, others might find the threat too overwhelming to deal with, let alone make the most of. We cannot forget that a great many people will need help through and after this.
We also should not expect positive change to be guaranteed. Bad actors will seek to use this for their benefit. Our motivation to change will fluctuate and we should anticipate resistance internally and from others. Changing behaviour takes time and requires persistence. It does not come easy on an individual level, let alone a societal one.
Reasons for optimism come from three places. First, we are not talking about people having an intellectual appreciation of why change is important, these are visceral experiences, which are usually more salient. Second, even if only a tiny percentage are driven to change, that still represents a very large number in absolute terms. Third, the visceral experience large numbers of people are having is unlikely to be for more separateness. We might hope.
The world before COVID-19 seemed headed towards greater inequality and protectionism. What we are presented with now is a lesson in cooperation. To get through this crisis we need strangers to risk their safety to take care of our health, keep us supplied and perform the other services we now know are essential. Almost everyone has agreed to make sacrifices to prevent the transmission of disease, even those who feel the risk to themselves be small. Perhaps most importantly, the opportunity to help others allows a great many more of us to experience the primal boost to self-worth that comes from feeling of value.
We sometimes forget that we are a group species whose success lies more in our ability to cooperate than compete. Competition doesn’t work in a crisis, challenges like these can only be overcome by working together. The experience of this even being possible, how good it feels and how effective it can be, is perhaps what is needed for us to address the even bigger challenges the world will soon face.
Dr David Crane is founder of the popular smoking cessation app, Smoke Free. His interest in behaviour change started in primary school and hasn’t really stopped since.
By CBC Digi-Hub Blog, on 18 February 2020
The UCL TechSharing Seminar Series aims to foster knowledge exchange between academics, clinicians, policy makers and industry professionals working at the intersection of healthcare and digital technologies. The first seminar in the 2020 iteration of the series (supported by the UCL Institute of Healthcare Engineering) took place on January 16th and was hosted in collaboration with the London School of Hygiene and Tropical Medicine (LSHTM). The seminar focused on healthcare delivery (e.g. point of care diagnostics, clinical decision-making, remote data collection) via smartphone apps and related technologies in low resource settings. Four speakers provided fascinating insights into the opportunities and challenges of conducting digital health research in a global context. A number of important lessons were highlighted across the presentations, summarised below.
The next seminar in the series will focus on ethics in multidisciplinary digital health collaborations (date TBD).
In his keynote presentation, Dr Andrew Bastawrous talked about his journey to setting up PeekVision – an organisation which uses smartphone technology and related software to support eye testing and care in remote locations. While cost-effective solutions are available (e.g. glasses, cataract surgery), accessibility issues mean that millions of people in need of eye care are not catered for. Dr Bastawrous drew on his personal and clinical experiences to demonstrate how a technology like PeekVision can help meet such healthcare needs. He talked about how the ideas behind the project evolved, starting from early, logistically cumbersome population-based research (e.g. screening programmes) which required the transport of costly NHS diagnostic equipment to remote and poorly connected areas in sub-Saharan Africa, to projects involving teacher-led and smartphone-enabled eye tests. Peek Vision’s story highlights the importance of adapting to the local context, engaging a wide range of community members (e.g. parents, headmasters, teachers) and seizing unexpected opportunities – in communities where access to running water, high quality roads, or electricity is limited, the majority of people might still have access to mobile phones.
Lessons learnt: (1) without diligent and transparent data collection and analysis at each stage of the project, it would not have had the same impact, as the data collected allowed the project team to identify areas for improvement; (2) simple solutions are often preferable to complex ones, such as using a piece of string (as opposed to sophisticated algorithms) to measure the right distance for conducting smartphone-enabled eye tests.
The second talk was delivered by Dr Cathy Holloway who shared the story behind the UCL Global Disability Innovation Hub. The Hub brings together international organisations, including the World Health Organisation, and local partners in India and Africa, to support a range of initiatives focused on improving the lives of people living with disabilities. For example, the Hub is involved in the building and testing of innovative assistive technologies such as prosthetics in low resource settings. Dr Holloway shared insights into both practical and ethical challenges facing researchers working in the field of assistive technologies. First, many countries have other health priorities, such as poorly controlled malaria or HIV, and struggle to fund core healthcare services, such as teaching and nursing. In this context, initiatives that immediately save lives are more likely to be adopted and supported by governments and charitable organisations. Second, assistive technologies can sometimes increase disability and dependence. For example, providing people with smartphones may require that the majority of features/functionalities are first removed to reduce costs, or create dependence on carers or other intermediaries who are tasked with accessing and handling sensitive data on the devices (e.g. bank accounts).
Lessons learnt: (1) securing sustainable funding for global disability research and related activities remains challenging; (2) project partners often possess useful domain expertise, but may have less experience working within multidisciplinary collaborations with technology developers and researchers; (3) securing ethical approval for research conducted across different countries can take much longer than anticipated; (4) the success of global health projects relies on trust and regular communication with stakeholders and partners – it is therefore key to budget for site visits to strengthen links between project partners and better understand the context where the work is taking place.
Dr Michelle Heys from the UCL Institute of Child Health presented on NeoTree, a not-for-profit and open source smartphone app to support clinical decision-making in neonatal care. In the absence of specialist paediatricians in many low resource settings, target end-users include nurses and healthcare assistants who oversee the day-to-day care of the newborns. NeoTree was developed in line with the Medical Research Council’s framework for the development and evaluation of complex interventions and is grounded in co-design and participatory research with relevant stakeholders, including nurses and doctors. NeoTree also aims to improve the ways in which data are collected and managed in neonatal units. The NeoTree platform is currently used for the admission and discharge of babies across hospitals in Malawi and Zimbabwe and offers diagnostic support for nursing staff. Dr Heys discussed the potential for the platform to deliver training and behaviour change interventions for healthcare workers in the near future.
Lessons learnt: (1) technology can be an important part of the solution, but capacity building and education of healthcare workers remain necessary to improve health outcomes; (2) building and implementing algorithms to support clinical decision making in the real world remains a challenge – there are still grey areas that are difficult for algorithms to replace, which are normally addressed by humans drawing on their accumulated experience and clinical judgement.
The final talk was delivered by Dr Chrissy Roberts (LSHTM) and focused on technology platforms that enable high quality data collection ‘for the masses’, i.e. for anyone without specialist IT skills. Dr Roberts has set up and is now curating the Open Data Research Kits. His work has spanned the establishment of secure servers at LSHTM which support data collection and management for global partners, through to establishing a tablet-rental scheme for data capture, training for field workers, and curating online learning resources. Currently, the Open Data Research Kits are used by researchers globally, including the recent Ebola outbreak in the Democratic Republic of the Congo. Dr Robert’s work is grounded in the need for a system that can be used to reliably and securely collect high quality data in global contexts, particularly in resource-poor and challenging environments (including extreme weather conditions!). Dr Roberts outlined how the Open Data Research Kits help to meet core requirements that he and other global health researchers have for a data capturing system: being able to work both off- and online; encryption, zero cost, remote/automated monitoring, instant data sharing, media assisted surveys (to capture images, barcodes, audio and video), third party app integration and sustainability.
Lessons learnt: (1) with the right tools (many are open access and affordable), anyone can collect high quality data in low resource settings; (2) community-based technologies and software can be more sustainable and up-to-date than commercial software thanks to the existence of a wide network of users and contributors; (3) demystification through training can help to increase uptake of new technologies among those who remain skeptical (e.g. teaching MSc students and field workers how to use new software can help promote such technologies to senior team members).
Dr Aleksandra Herbec is a mixed-methods researcher specialising in tobacco control, behavioural science and digital health. She is based at the UCL Centre for Behaviour Change where she investigates ways to improve antibiotic stewardship and infection prevention and control and leads evaluations of smartphone-based aids for medication adherence and smoking cessation.
Dr Nikki Newhouse is an interdisciplinary qualitative researcher whose primary research interest is in human-computer interaction, in particular the development and evaluation of complex digital interventions to support physical and psychological wellbeing across the lifespan. She is based at the Nuffield Department of Primary Care Health Sciences at the University of Oxford.
Dr Olga Perski is an interdisciplinary researcher working at the intersection of behavioural science and technology. She is a Research Associate in the UCL Tobacco and Alcohol Research Group, where her work is focused on the development and evaluation of digital interventions for smoking cessation and alcohol reduction.
How to design a health app for users who are not motivated to change? Insights from the Precious app
By CBC Digi-Hub Blog, on 4 February 2020
The Precious app was designed to support healthy living: a physically active lifestyle, balanced nutrition and stress management. In a study published in JMIR mHealth and uHealth, we describe how we designed the Precious physical activity app features for users whose needs are not met by traditional activity tracker apps.
Most available physical activity apps provide factual information on performance with numbers and graphs, and they can be a great resource for those who are already active and who want to monitor their progress. Millions of users regularly log their running and cycling routes using smartphone sensors or wearables that connect with apps such as Strava. However, not everyone enjoys physical activity, and not everyone finds numerical data meaningful. For some, constantly failing to reach the goals set by exercise apps (such as 10,000 steps a day) can be a major stressor. Although good health is the goal for many, sometimes people only feel motivated to take care of themselves after facing a serious health concern.
Physical activity is good for our physical and mental wellbeing and those with the lowest levels of activity would benefit most from adopting some exercise in their life. Building on psychological research on motivation and self-regulation, we came up with two ways of catering to users with low motivation for activity in the Precious app: reflective and spontaneous support.
Reflective support through Motivational Interviewing
Most of us know about the health benefits of a physically active lifestyle. Thus, there is little need to remind people what they should do. Somewhat surprisingly, psychological research shows that a much more effective strategy is to help people think what they want to do .
In the Precious app, we used Motivational Interviewing techniques  to support people who struggle to fit physical activity into their daily lives. One of the key techniques is to ask questions that help the users reflect on how healthy behaviours could help them reach goals that are meaningful for them. When users start to express their desire to change or the reasons to become active, they are eliciting change talk. This is a central concept in Motivational Interviewing: helping people to put into words how behavioural changes can help them live a life that corresponds to their values.
In the Precious app, users are first guided to think about what really matters to them. This does not need to be health related: the basic psychological needs for human motivation are connectedness to others, experiencing competence in their actions, and having the freedom to pursue personally meaningful goals.  This thinking is based on Self-Determination Theory which has repeatedly shown that individuals engage in behaviours when these are in line with their values and identity .
Once the users have reflected on their life values, they are encouraged to think about if physical activity could help them achieve those things. Among the test users of the Precious app, physical activity was typically perceived as helpful, as physical exercise can, for instance, increase energy levels and help to manage stress. Whether people prioritise their family, their health or their career, improved physical and mental well-being is an asset.
The next step is to help users think about practical ways in which physical activity can take them closer to their life goals. For instance, if a user has indicated that feeling connected to others is most important to them, they can choose activities that can be done together with family or friends. The aim of the Motivational Interviewing tools is not simply to engage users with the app, but to engage them in the behaviour change process: to actively consider reasons for change and to take practical steps toward change (see Figure 1).
Figure 1. Screenshots from the Precious app.
Spontaneous support through gamification
Behaviour change does not necessarily require active reflection but can tap into the motivational effect of intrinsic pleasure. Gamification is the use of game elements for making a task more engaging and entertaining. For instance, the Conquer the city feature in the Precious app was designed to increase walking by making users conquer and defend areas in the area they live in by walking around buildings or blocks. Game elements can change users’ focus from feeling like they are ‘just walking’ to the task at hand and make people spontaneously active without even realising. Similar ideas have gained success in games like Ingress, Pokemon Go or Zombies, run!, where augmented reality elements lure players to walk further or run faster. An activity that is not necessarily fascinating in itself can become more enjoyable with augmented reality elements. People who do not find physical activity pleasurable may enjoy gamified visualisations, goals and challenges that they only achieve while being active.
The ‘Mountain climber’ tool provides a visual interpretation of activity and goal achievement
Following these principles, the evidence-based self-regulatory behaviour change techniques  in the Precious app were built into a Mountain climber tool (see Figure 2). It depicts daily activity as a mountain and shows a little flag on top of the mountain on days when users achieved their personal step goal. This self-regulation tool was designed so that people could monitor their daily steps even without looking at numbers. They can see if their mountain panorama is growing over time and learn what type of activities lead to the highest mountains.
Figure 2. The ‘Mountain climber’ tool.
To help users estimate more accurately how much activity they have done every day, the planning tool in the Precious app indicates how many steps each activity corresponds to. Users can fill in the minutes they spent swimming, lifting weights, etc., and the app will display how many steps these activities correspond to using MET values. All activities contribute to the daily step count and are visualised as one mountain, providing an easy day-to-day comparison.
The Precious app tries to convey that people do not need to become athletes in order to be physically active. Vacuuming the house or helping a friend to move can be the dose of daily physical activity – a realisation that can be a relief for someone with a busy schedule! The main thing is to make physical activity more enjoyable, or to at least see how it can help achieve things that matter most.
- The Precious app helped users elicit change talk in the interview situation. Will the effect carry on in a natural environment, over time?
- Health apps can be tailored to meet the needs of people with low technology literacy and little motivation for behaviour change, but how do we reach these potential users?
Nurmi J, Knittle K, Ginchev T, Khattak F, Helf C, Zwickl P, Castellano-Tejedor C, Lusilla-Palacios P, Costa-Requena J, Ravaja N, Haukkala A. (2020). Engaging Users in the Behavior Change Process With Digitalized Motivational Interviewing and Gamification: Development and Feasibility Testing of the Precious App. JMIR mHealth and uHealth. DOI: 10.2196/12884 URL: https://mhealth.jmir.org/2020/1/e12884/
Johanna Nurmi is finalising her PhD in Social Psychology at the University of Helsinki and working as a visiting researcher at the Behavioural Science Group, University of Cambridge. She studies how motivational techniques and related cognitions affect individuals’ daily physical activity. Johanna’s research has been supported by the University of Helsinki; the Yrjö Jahnsson foundation; and the KAUTE foundation.
The Precious project was funded by the European Union’s Seventh Framework Programme for research, technological development and demonstration under grant agreement number 611366, and built in multidisciplinary collaborations with partners across Europe.
Find Johanna here: