Dr David Ryan interviews Dr Xiao Liu about machine learning in diagnostic testing, the current state of research and use in real-world medicine.

Dr Liu is an ophthalmology doctor and clinical researcher at the University of Birmingham and University Hospitals Birmingham. She is interested in clinical evaluation and implementation of digital health technologies (particularly machine learning algorithms as diagnostic tests) to improve patient care and healthcare delivery.

Her recent work has been around identifying gaps in reporting and methodology in clinical AI studies, and providing guidance for clinicians to critically appraise the evidence supporting AI health systems. She led the development of the SPIRIT-AI and CONSORT-AI guidelines - new reporting guidelines for AI clinical trials. She also plays an advisory role to NHS X, the AI in health and care award and the WHO/ITU focus group for AI for Health.

-- Resources --

A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis - https://doi.org/10.1016/S2589-7500(19)30123-2

-Spirit and Consort AI-

https://www.spirit-statement.org/

http://www.consort-statement.org/

In silico - by means of computer modelling or computer simulation.