Healthcare leaders call for better datasets to power AI innovation

Healthcare leaders call for better datasets to power AI innovation

Facebook
Twitter
LinkedIn

[ad_1]

Ho cites a question on the Tia intake form that asks patients if they have experienced sexual abuse or assault, both of which are linked to a wide range of health problems.

Mark Solazzo, president of strategic initiatives and chief operating officer, said Northwell is improving its data on the maternal health of black women by working with 100 faith-based collaborators in the black community.

Empire BlueCross BlueShield CEO Alan Murray said data related to where patients live and type of employer should also be included, adding that insurers can work with their employer clients to make these data sets more robust.

Download the Modern Healthcare app to stay informed as industry news emerges.

Then, stakeholders at different points of care need to better connect these data to map a Patient health picture All of their providers have access and use to inform care decisions, Murray said.

However, Mark Michalski, Amazon Web Services’ global head of healthcare and life sciences, said these datasets need to be accompanied by context on how to compile and label the data to produce better AI models.

The first step, Michalski says, is for innovators to articulate exactly what they want to build so they can spot failures. They also need to develop algorithms that provide explanations, not just answers.

“I don’t think anyone has cracked the problem,” he said.

This story first appeared in our sister publication, Crane’s New York business.

[ad_2]

Source link

More to explorer