Scalable TRansdiagnostic Early Assessment of Mental Health (STREAM)

Worldwide, over 250 million children are at risk of not obtaining their developmental potential due to exposure to adverse circumstances. India and Malawi house some of the most disadvantaged populations in the world, with over 10% of all children aged 2 to 9 years estimated to have neurodevelopmental disorders. However, social and economic barriers to access qualified health personnel mean that most of these children do not receive any assessment of neurodevelopment or a clinical diagnosis when needed. Moreover, many parents are unaware of developmental milestones, so clinical opinion is sought only when symptoms become more pronounced and begin to impact daily life with a lost opportunity for early interventions. This avoidable delay is an unfolding tragedy in light of evidence showing that frontline worker delivered interventions can lead to better behavioural and social outcomes and improve long term developmental trajectories. Scalable methods to assess child neurodevelopment and mental health would promote early referral to specialist facilities, ultimately connecting families with affordable, community-based interventions. Directly measuring neurodevelopment allows us to identify the most vulnerable children as early as possible, allowing limited resources to be focused on those most likely to benefit from preventive approaches. Taken together, focusing on brain development in early childhood is critical to revolutionising global mental health of young children.
We will realise this goal by developing a Scalable Transdiagnostic Assessment of Mental Health (STREAM), a mobile platform usable in the home or in a routine health facility by non-specialist workers. STREAM will be delivered on a tablet PC and will collect different types of data from 4000 children in India and Malawi. First, parents will be asked simple questions about their child's everyday behaviour, based on established questionnaires that have been validated in low income settings. Second, gamified tasks designed to measure motor, social, and cognitive abilities will be administered on the tablet. Additionally, novel low-cost eye-tracking technology on the same tablet PC will be used to monitor the child's eye movements in simple tasks, such as those assessing preference for social versus non-social images, and measuring how quickly attention shifts to new objects appearing on the screen. Finally, a segment of parent and child interaction will be recorded using the inbuilt camera, and used to code for signs of atypical behaviour. This combination of multiple measures will provide independent channels of data collected on a single platform, significantly improving on current assessment methods that often rely on one technique and expensive, highly skilled but scarce human resources. STREAM will be designed such that it will require minimal training to be administered by non-specialist workers in low and middle income countries, thereby promoting task-sharing, a concept endorsed by the World Health Organization to reach wider populations. This task-sharing approach reduces the burden on the small number of highly-skilled mental-health and child development professionals in these low resource settings. STREAM can also help develop community awareness and, in the longer term, address the barrier of low demand for services in these areas. The development and application of the STREAM platform involves collaborations across the breadth of basic and applied sciences. Our network comprising clinicians, neuroscientists, public health specialists and data scientists spread across UK, India and Malawi is optimally suited to leading this challenge because of our combined expertise deploying novel technologies to measure early childhood neurodevelopment in low-resource settings.

Monitoring child neurodevelopment is essential for early identification of children faltering in their developmental trajectory and their eventual referral to effective interventions. Typically, such assessments depend on highly trained professionals administering expensive, proprietary and time consuming tools. This high resource demand poses a challenge in low and middle income countries (LMICs) where skilled personnel are scarce and public awareness of neurodevelopmental symptoms is low. The resulting delay or outright absence of identification of children vulnerable to developmental problems (i.e. 'detection gap') effectively obstructs community-based interventions that have been shown to improve outcomes. Closing this detection gap will depend on task-shifting from scarce experts to more plentiful non-specialist community health workers, via scalable neurodevelopmental assessment tools.

The proposed research programme will develop a scalable platform for neurodevelopmental assessment in 0-6 year olds (STREAM) by consolidating work from four current projects by the project team on child mental health in LMIC settings. This open-source platform, running on Android tablet PCs, will be administered on 4000 children in India and Malawi by non-specialist workers. It will comprise a diverse set of assessments of child behaviour, parent-report, and parent-child interaction, and use technological innovations in computer vision and machine learning. Known prenatal and perinatal risk factors will be mapped to the measures generated by STREAM to test the sensitivity of the platform. A random subset of the sample in both countries will be clinically evaluated, to test the utility of the platform in identifying clinical needs and diagnoses.

The project objectives will be achieved by an interdisciplinary team of neuroscientists, public health researchers, clinicians, computer scientists, and app developers from UK, India, and Malawi.

Good mental health in childhood contributes significantly to positive outcomes in later life, improving school readiness and adult productivity. Yet interventions are only effective if impairments are detected in a timely manner. Between 10-20% of children worldwide have mental health problems, and the burden in low and middle income countries (LMICs) far outweighs that in higher income countries. Recent studies estimate that over 250 million children in LMICs are at risk of not reaching their full development potential, with 60 million of these children in India alone. The vast majority (nearly 100%) of child mental health problems are currently undetected and untreated in most LMICs due to a) the paucity of mental health professionals, b) their concentration in urban private healthcare facilities, c) the use of expensive proprietary time-consuming tools for diagnosis, and d) the lack of awareness of neuropsychiatric symptoms and consequent failures to seek treatment.

The proposed platform aims to harness the potential of mobile technology to allow for the provision of mental health assessment at scale, be administered by non-specialist healthcare workers, and across diverse cultural settings. We have identified the following beneficiaries:

1. Families of young children in India and Malawi
Our primary and immediate beneficiaries will be the families of 4000 young children who will be assessed by the STREAM platform. Children identified to have clinical needs will be referred to early interventions through existing referral systems. All parents will benefit by becoming more aware of the signs of atypical development. This increased awareness is expected not only to improve early treatment seeking behaviour, but over time, can lead to reduced stigma associated with these disorders in families and communities. In the longer term, this increased awareness can potentially result in benefits to health, wellbeing and productivity.

2. Community-based healthcare providers
The project will take the first steps to building capacity in the form of local expertise, through training cadres of community health workers. These community health workers form the pillars of the healthcare system in LMICs and this training will strengthen these pillars through building awareness and skill in child development and mental health.

3. State healthcare managers and policymakers
The project will identify the presence of neurodevelopmental disorders as well as clinical needs through testing a large group of children in India and Malawi using the STREAM platform. This information will then be passed on to state healthcare managers to facilitate the delivery of interventions to the children identified with a clinical need. At the end of the project, policymakers will be briefed with the evidence generated on the efficacy of the platform in tracking mental health through the early years of life.

4. International policymakers and advisors
Results of the study will inform international policymakers on the feasibility, acceptability, and utility of a platform for early assessment of mental health in low-resource settings.
Perhaps most significantly for the long term, the implementation of such a non-specialist mediated mental health monitoring approach using mHealth technology will be codified into public policy via links with government organisations and advisory bodies such as the WHO.