Health informatics research projects
Automated Remote Pulse Oximetry
The Automated Remote Pulse Oximetry System (ARPOS) uses non-contact automated remote sensing using camera-based technology to measure vital signs (heart rate and blood oxygen level) in real-time at a distance of up to 4.5m away, measuring up to 6 people at once.
Modelling transgenic mosquitoes
Malaria is one of the major global killers. Modern attempts at improving
control centre around the use of transgenic mosquitoes to interrupt the
cycle of infection, introducing mosquitoes that have been engineered to
be less transmissive of the malarial parasites into wild populations.
For such approaches to be effective, the new mosquitoes must breed
sufficiently to dilute the (human) reservoir of infection, but without
indefinitely changing the host population’s gene pool.
Complex networks have long been used to epidemiological research. In
this project we looked to deploy complex adaptive coupled networks to
model malarial infection and the propagation of transgenic
characteristics within populations with complex structure. The use of
networks allows researchers to address the behaviour of diseases in
inhomogeneous media, which can challenge traditional approaches. An
example of this is the use of social networks in which the probabilities
with which individuals come into contact are highly irregular.
This work was hosted by a $20,000 in-kind grant from Microsoft Azure.
Normative Modelling in Psychology and Endocrinology
Using data from our labs, our research partners and from the published literature, we develop and validate age-related models that allow the assessment of individuals against the general healthy population. In addition we perform investigations and meta-analyses that use the models as a benchmark to gain new insights in the diagnosis and treatment of (for example) breast cancer, diabetes and PCOS.
Health Psychology Using Mobile Devices
We have developed mobile apps for use by patients referred for help with dental anxiety or smoking cessation. The apps, which are currently undergoing clinical validation in Scotland, Sweden, Finland and Japan, provide useful data for designing and monitoring individualised interventions and treatments, and also help the research community by providing longitudinal follow-up data from a wide range of subjects.
IntelliScreen - Combining artificial intelligence and applied epidemiology to enhance Cancer Screening
In this study the team seek to bring together three areas of expertise under the umbrella of the Sir James Mackenzie Institute for Early Diagnosis; clinical, epidemiological and computer science (artificial intelligence) with the aim of designing a system that maximizes the number of cancers found early whilst minimizing unnecessary investigation which is a nuisance for patients and a burden on the NHS.
Quantified-self and remote patient monitoring
Collecting biological data (e.g. heart rate, blood pressure) for diagnosis and for monitoring efficacy of treatments can be time-consuming and expensive in terms of staff resources. With growing health needs globally, there needs to be a more sustainable and participatory approach to the collection of biological data so that medical staff can focus their time on helping patients.
We are developing a quantified-self approach within the context of a ‘carer network’, an online social network that includes patients, healthcare professionals, and informal caregivers for gathering biological data for diagnosis and treatment.
