recent report by the Government Accountability Office (GAO) is encouraging those in the medical field to leverage machine learning (ML) to detect diseases earlier, broaden healthcare access, and improve the consistency and accuracy of patients’ diagnoses.

Diagnostic errors, the report says, are the “most common, catastrophic, and costly” of medical errors – annually affecting more than 12 million Americans and resulting in over $100 billion in additional costs. ML, GAO found, can help.

Innovation Unleashed
Explore the latest emerging technologies and trends and engage in innovative demonstrations. Learn more.

“Machine learning technologies are trained to identify patterns that may be hidden or complex,” the Nov. 10 blog post said. “For example, after providing a computer with large amounts of data, machine learning can identify structure and patterns in the data.”

“Then it can use those patterns to predict answers to problems, or cluster information into useful groups for comparison, such as similar images of cancerous lesions . . . details within the imagery of x-rays, ultrasounds, and magnetic resonance imaging,” GAO wrote.

GAO also found that ML can detect diseases earlier. The technology’s advantage in computer power allows it to conduct analysis more quickly than human medical professionals, which could reduce wait times and lessen the burden on clinics.

Automation of certain tasks could reduce clinical workloads and empower non-specialists to perform more complicated work – like cardiac imaging and analysis. According to the report, this could allow medical professionals to reach larger portions of the population and broaden healthcare access.

Finally, GAO found that ML can improve consistency and accuracy of diagnosis by removing situations that contribute to human error.

“While researchers continue to expand AI and machine learning capabilities in medical diagnostics, these technologies have generally not been widely adopted,” the report said.

“A lack of familiarity among some medical professionals about how machine learning would fit within and enhance their workflow, along with gaps in regulatory guidance and requirements, and the cost of implementation and maintenance, may also limit its development and use,” GAO wrote.

The agency offered lawmakers three policy options to consider:

  • Encourage or require the evaluation of machine learning diagnostic technologies across a range of real-world settings;
  • Expand access to high-quality medical data; and
  • Promote collaboration between developers, providers, and regulators.
Read More About
Recent
More Topics
About
Cate Burgan
Cate Burgan
Cate Burgan is a MeriTalk Senior Technology Reporter covering the intersection of government and technology.
Tags