STAT Plus: Medical AI systems are disproportionately built with data from just three states, new research finds

Late last year, Stanford University researcher Amit Kaushal and a collaborator noticed something striking while sifting through the scientific literature on artificial intelligence systems designed to make a diagnosis by analyzing medical images.

“It became apparent that all the datasets [being used to train those algorithms] just seemed to be coming from the same sorts of places: the Stanfords and UCSFs and Mass Generals,” Kaushal said.

Continue to STAT Plus to read the full story…

Read Original Article: STAT Plus: Medical AI systems are disproportionately built with data from just three states, new research finds »