Intensive Care: How AI Could Rejuvenate U.S. Healthcare

by Jamie Beckett

It’s no secret that the U.S. healthcare system needs help. What’s more surprising is the role AI can play in fixing it.

In a talk at the GPU Technology Conference, Dr. Michael Dahlweid, chief medical officer of digital solutions for GE Healthcare, described the myriad problems in U.S. healthcare, and the scope for finding fixes with the expanded use of deep learning.

The numbers can be depressing: About 100,000 people die needlessly every year, he said. Nearly a third of all healthcare spending — more than $690 billion — is money wasted. A third of all electronic medical records are inaccurate. And doctors are struggling with information overload.

“The focus for AI research in healthcare today is on imaging,” said Dahlweid. “We need to apply AI beyond that.”

AI in healthcare is most commonly used to read X-rays, MRIs and other medical images.

AI could one day read medical images faster and more accurately than radiologists.

How GE Uses AI in Healthcare

AI has already shown promise to read X-rays, MRIs and other medical images faster and more accurately than radiologists, speed the search for new medicines and provide more thorough and accurate diagnoses.

But there’s much more potential for AI in healthcare, Dahlweid said. GE is experimenting with deep learning for a wide range of tasks. Among these:

  • Identifying different types of cells in cancer tissue
  • Determining the most efficient treatment for each patient in intensive care units
  • Predicting whether ICU patients are likely to develop sepsis or infections
  • Assessing patients’ risk for heart problems with ultrasound
  • Predicting seizures

AI could also help doctors make decisions and to manage massive amounts of healthcare information, Dahlweid said.