Over 90 Total Lots Up For Auction at One Location - WA 04/08

Beyond bright and shiny: Practical applications for AI in healthcare

by Lisa Chamoff, Contributing Reporter | November 16, 2018
Artificial Intelligence
While much of the focus on artificial intelligence (AI) in healthcare involves its role in diagnosing diseases, machine learning can also help with day-to-day hospital operations, from critical goals like fall prevention to the more mundane work of paying bills.

Early this week, healthcare leaders from around the country came to midtown Manhattan to discuss how AI is transforming healthcare during Ai4 Healthcare, one in a series of conferences focused on the role of AI in various industries.

The two-day event opened with a panel discussion on “Hospital-Wide AI Transformation.”
stats
DOTmed text ad

Reveal Mobi Pro now available for sale in the US

Reveal Mobi Pro integrates the Reveal 35C detector with SpectralDR technology into a modern mobile X-ray solution. Mobi Pro allows for simultaneous acquisition of conventional & dual-energy images with a single exposure. Contact us for a demo at no cost.

stats
David Tsay, associate chief transformation officer for NewYork-Presbyterian, spoke about how AI can help hospitals handle the “boring stuff,” such as timekeeping for employees and invoice processing, making these processes more efficient so that the hospital system can push more resources toward the front lines.

Tsay described how NewYork-Presbyterian used a machine learning model to read hundreds of thousands of invoices for medical supplies and surgical tools, using a “digital robot” to key-in necessary information.

“What’s really impactful about this is it not only creates a higher service level, with less resources to do that, but the impact on the workforce is great,” Tsay said. “So now, instead of our workers doing data entry, they supervise the bots and correct it. It’s not just about machine learning, but machine training as well.”

Robbie Freeman, the senior director of clinical operations at the Mount Sinai Health System, spoke about the system creating a machine learning model to predict which patients are most likely to fall. This replaced the traditional model of patients wearing special colored bracelets to indicate that they were at risk of falling.

Using an AI algorithm that was trained on five years of data, Freeman said the health system was able to reduce the number of patients in the fall risk category by 40 percent and supplement their interventions with remote patient monitoring.

“Now we’re able to tailor our interventions for the patients at highest risk for falling to that smaller cohort of patients who are truly at the highest risk,” Freeman said.

While the panelists admitted that AI was going to cause a shift in the healthcare workforce, they stressed that would help improve patient care.

Peter Fleischut, senior vice president and chief transformation officer for NewYork-Presbyterian, spoke about how using AI in the system’s 45 pharmacies allowed pharmacists to focus on medication reconciliation. This also allowed doctors to get away from that task and spend more time performing procedures and consulting with their patients about other important issues.

“It allows people to work at the top of their license, so that we increase our workforce at the bedside and contract our workforce in the back office,” Fleischut said.

Discussing which issues might stem the flow of AI, Freeman warned that the lack of broadband in rural areas of the country is going to be a major hurdle for adoption of AI in healthcare.

“People [not having] access to buy something on Amazon or Jet is one thing, but when we start to offer health services online, and telemedicine and AI, and we’re finding that there’s a segment of the population that is not going to be able to get access to that because they don’t have broadband, it's a major issue and needs to be addressed pretty quickly,” Freeman said.

You Must Be Logged In To Post A Comment