Loading

A method for machine learning generation of realistic synthetic datasets for validating healthcare applications

HDR UK Applied Analytics Seminar led by George Despotou

As part of the HDR UK Applied Analytics scientific theme this seminar on A method for machine learning generation of realistic synthetic datasets for validating healthcare applications led by Dr George Despotou will take place on Wednesday 7th September 2022 from 16:00-17:00 UK time.

This seminar will be recorded.

Digital health applications can improve quality and effectiveness of healthcare, by offering a number of new tools to users, which are often considered a medical device. Assuring their safe operation requires, amongst others, clinical validation, needing large datasets to test them in realistic clinical scenarios. Access to datasets is challenging, due to patient privacy concerns. This may result in overheads such as delays and additional cost, that may ultimately deprive patients from potential benefits from innovations. Use of synthetic datasets is increasingly seen as a way for early validation of applications, overcoming the privacy issues. However, the synthetic datasets will need to be demonstrably equivalent to the real datasets. The presentation will give an overview of a method for the generation of realistic synthetic datasets, statistically equivalent to real clinical datasets, using Generative Adversarial Networks (GAN). (Dr George Despotou)

George Despotou

Dr George Despotou

Eur Ing Dr George Despotou, is an associate professor in digital health systems and assured IT, and a chartered engineer, working at WMG, University of Warwick. His research interest focus on complex systems integration, clinical decision support, health IT interoperability, artificial intelligence and machine learning in healthcare, safety and assurance cases, and certification. He has worked and led a number of european and national projects in healthcare such as C3-Cloud, and ADLIFE.