Applying machine learning and natural language processing to better identify risk groups for the surveillance of blood borne viruses and sexually transmissible infections
Share via
Carol El-Hayek BSc MEpi CHIA
Supervisors: Prof Margaret Hellard, Prof Jane Hocking, Prof Douglas Boyle and Prof Adam Dunn
Public health surveillance relies on the characterisation of risk populations to monitor burden of disease and inform interventions. Real-world clinical data are becoming increasingly available for this purpose but their secondary use is complicated by data quality and patient privacy issues, necessitating new large-scale methods. This PhD explores the application of machine learning and natural language processing techniques for identifying risk populations using electronic medical records from primary care. The research aimed to develop a machine learning algorithm to classify risk, assess its utility and fairness in practical application, and evaluate NLP tools for de-identified information extraction.
Location:
Microsoft Teams meeting
Join on your computer, mobile app or room device
Click here to join the meeting
Meeting ID: 477 254 500 078
Passcode: 6rX7ER