ODSC East 2019: Major Applications of AI in Healthcare ODSC East 2019: Major Applications of AI in Healthcare
The healthcare industry has come a long way to arrive at what we know today as modern medicine. Medical professionals have spent decades putting... ODSC East 2019: Major Applications of AI in Healthcare

The healthcare industry has come a long way to arrive at what we know today as modern medicine. Medical professionals have spent decades putting their research to work in order to create a healthier population. But there’s always room for growth and innovation, especially with the help of technology.

Alex Ermolaev, Director of Artificial Intelligence at Change Healthcare, delivered a presentation on what the healthcare industry can do to harness the power of AI to make the lives of both patients and medical professionals easier. He cited the difficult process of diagnosing certain conditions as an area of concern.

[Related article: Using AI to Revolutionize Child Behavioral Diagnostics and Therapeutics]

“Traditional healthcare misses nonspecific symptoms of Sepsis,” Ermolaev said. “For example, your heart rate goes up, then it goes up a little more, and then by the time definitive symptoms show, it may be too late. So this is good for AI because it can detect what your normal heart rate should be.”

Sepsis is a debilitating condition that the human body experiences in response to infections and with 1.6 million diagnoses per year coupled with a 25-30 percent mortality rate, it is one of the leading causes of death in the United States. Using machine learning models to predict the likelihood of a patient having Sepsis based on vital signs could have the potential to catch life-threatening diseases quickly enough to intervene in a timely manner.

As with any industry, the healthcare sector could also benefit from streamlining the minutiae. Ermolaev proposes creating a more personalized profile for patients, where health metrics and other information regarding specific medication can be found in one hub. Additionally, this hub could be backed by reinforcement learning, which can take patient data and give suggestions for proper dosing and medical actions.

On the practitioners’ side, AI can also cut lengthy processes significantly, allowing them to focus on providing the best care possible. Deep learning models can turn a process like sifting through medical documents and test records into a one-click insight with the help of a single program.

[Related article: Machine Learning and Compression Systems in Communications and Healthcare]

According to Ermolaev, nearly a third of healthcare spending in the U.S. is wasted on unnecessary services, excess admin costs, and billing errors. Eliminating these costs could leave room for more developments in medical technology, and artificial intelligence could be the bridge that gets us there.

Kailen Santos

Kailen Santos

I’m a freelance data journalist based in Boston, MA. Formally trained in both data science and journalism at Boston University, I aspire to make working with data easy and fun. If you work in a newsroom or if you’re just data-curious, I hope to help you explore data clearly. https://www.kailenjsantos.wordpress.com/

1