Artificial Intelligence to predict adverse perinatal outcomes
Dr Quiyan Yu, Department of Preventative Medicine, Wenzhou Medical University, China
Adverse perinatal outcomes, such as stillbirth, preterm birth, and small for gestational age, are major contributors to global neonatal and child mortality and morbidity. Accurate prediction of these outcomes is crucial to target preventative and therapeutic interventions. However, antenatal prediction of these outcomes is poor and limits progress in addressing these outcomes. Artificial intelligence holds promise to improve antenatal prediction of adverse perinatal outcome.
RESEARCH EXPERIENCE, RESEARCH METHODS AND TRAINING
The project will entail employing a range of different machine learning algorithms to predict adverse perinatal outcomes in large international pregnancy cohort data sets. This will involve data cleaning, data pre-processing, feature description and selection, development of predictive models, and model validation and interpretation.
FIELD WORK, SECONDMENTS, INDUSTRY PLACEMENTS AND TRAINING
It is anticipated that the work will be conducted in Oxford and all necessary facilities, equipment and training, including database, analytic and statistical training, will be provided by the supervisors.
A student with a background in epidemiology, statistics and/or modelling would be best suited to this project. The ideal candidate will have a Master's degree in a relevant area (e.g. statistics/epidemiology/computer science), with experience in modelling. The project has a broad scope and candidates are encouraged to contact Dr Joris Hemelaar to work out a specific project proposal.