AI can guess racial categories from heart scans – what it means and why it matters

By Tiarna Lee, Doctoral Candidate, School of Biomedical Engineering & Imaging Sciences, King's College London

Imagine an AI model that can use a heart scan to guess what racial category you’re likely to be put in – even when it hasn’t been told what race is, or what to look for. It sounds like science fiction, but it’s real.

My recent study, which I conducted with colleagues, found that an AI model could guess whether a patient identified as Black or white from heart images with up to 96% accuracy – despite no explicit information about racial categories being given.

Read complete article

~	Feeling anxious before surgery? Anxiety can harm healing but innovative mental health support could help

~	Trump’s bid to end birthright citizenship heads to the Supreme Court

~	Should Joan Didion’s therapy notes to her husband about their daughter have been published?

~	Dementia risk depends on more than lifestyle factors. Overstating this can cause stigma and blame

~	A looming workforce crisis in NZ tourism and hospitality threatens industry growth plans

~	Free food and beer are common perks for hospitality workers – but are they masking unfairness?

~	Range anxiety – or charger drama? Australians are buying hybrid cars because they don’t trust public chargers

~	What did the parties say on TikTok in the election, and how? Here’s the campaign broken down in 5 charts

~	How Donald Trump could remain president of the United States

~	‘Elbows up’ in Canada means sustainable resource development