Anaemia and micronutrient deficiencies are serious health challenges in low and middle-income countries. It primarily impacts on young children, adolescent females, and pregnant women. Anaemia in childhood and adolescence can affect physical growth and cognitive function, with likely further impacts on reproductive health in women. In India, anaemia prevention and control programmes have been unable to reduce its prevalence. The reasons for this are unclear, but are likely to be multifactorial due to heterogeneity in the population. Data-science approaches, and in particular machine learning techniques, offer new opportunities to explore this further, with the potential to reveal previously unrecognised patterns of anaemia, micronutrient deficiencies, health outcomes during childhood and adolescence over time. Using the MAS3 dataset, developed as part of the Pune Maternal Nutrition Study (PMNS), which captures longitudinal health, clinical, nutritional, environmental and social data on 700 women during pregnancy and their children, this project aims at identifying subgroups of mothers and children with varying patterns of anaemia and relevant associations with health-related outcomes. The proposed PhD studentship project will use the MAS3 database to achieve the following objectives. 1. Apply machine learning techniques to study anaemia, micronutrient deficiencies, and health outcomes in mothers during pregnancy and in their children from birth to 18 years of life. 2. Investigate how different subgroups in the population associate with development during childhood and adolescence progress, and socioeconomic, nutritional, environmental exposures from birth to 18 years of life. 3. Apply advanced statistics and data modelling techniques to conduct risk analysis and adverse outcomes prediction related to anaemia, micronutrient deficiencies, physical and cognitive developments. This PhD programme offers a great opportunity for an enthusiastic student to be trained in health data sciences, combining the cutting-edge disciplines of artificial intelligence (AI) and machine learning, with medicine and public health. Applicants are expected to hold a minimum upper second-class undergraduate degree (or equivalent) in epidemiology, public health, statistics, data science, computing, machine learning or a related field. A Master’s degree in a relevant subject/discipline with some prior experience in AI/machine learning is desirable. The successful candidate will work with a multidisciplinary team of researchers based at the University of Surrey. The project is expected to yield a number of high-impact publications. Support will be provided for developing skills in research design, data analysis, and peer reviewed publication.
Principle Supervisor: Dr Haomiao Jin
Dr Haomiao Jin has expertise in data science and advanced statistical modelling as applied to health and social care. He completed his PhD studies in Industrial and Systems Engineering and has had postdoctoral training in Social Work in the University of Southern California. He is the Surrey PI of two subawards from the U.S. National Institutes of Health (NIH) and has been involved in 6 NIH-funded projects in his career.
[Email Address Removed]
Open to UK and international students with the project starting in October 2023. Note that a maximum of 30% of the studentships will be offered to international students.
You will need to meet the minimum entry requirements for our PhD programme https://www.surrey.ac.uk/postgraduate/health-sciences-phd#entry.
How to apply
Applicants are strongly encouraged to contact the relevant principal supervisor(s) to discuss the project(s) before submitting their application.
Applications should be submitted via the https://www.surrey.ac.uk/postgraduate/health-sciences-phd#apply programme page (N.B. Please select the October 2023 start date when applying).
You may opt to apply for a single project or for 2 of these Faculty-funded studentship projects.
When completing your application, in place of a research proposal, please provide a brief motivational document (1 page maximum) which specifies:
- the reference numbers(s) for the project or two projects you are applying for
- the project title(s) and principal supervisor name(s)
- if applying for two projects, please also indicate your order of preference for the projects
- an explanation of your motivations for wanting to study for a PhD
- an explanation of your reasons for selecting the project(s) you have chosen
Additionally, to complete a full application, you MUST also email a copy of your CV and 1-page motivational document directly to the relevant project principal supervisor of each project you apply for. Due to short turnaround times for applicant shortlisting, failure to do this may mean that your application is not considered.
Please note that online interviews for shortlisted applicants are expected to take place during the week commencing 30th January.