Coming to a Clinic Near You: Computers That Diagnose and Treat Patients

aNewDomain.net — You trust your doctor’s diagnosis, hopefully. How about a medical computer equipped with artificial intelligence to diagnose and treat you?

New research out of Indiana University suggests “machine learning” — the technology behind voice recognition systems, self-driving cars to name a few — could help cut healthcare costs by more than 50 percent and improve patient outcomes by nearly 50 percent.

Image credit: Wikimedia Commons

Researchers in the study were able to successfully get computers to “think like a doctor” by using computer models to simulate numerous alternative treatment paths in the future, in addition to continuously planning treatments as new information surfaced.

The studies were not disease-specific, indicating the tech could work for any diagnosis or disorder when relevant information is imputed.

“We’re using modern computational approaches to learn from clinical data and develop complex plans through the simulation of numerous, alternative sequential decision paths,” said Casey Bennett, a researcher involved in the study. “The framework here easily outperforms the current treatment-as-usual, case-rate/fee-for-service models of health care.”

The research, according to the university, addresses three primary healthcare issues in the U.S.:

  • Rising healthcare costs expected to reach 30 percent of the gross domestic product by 2050
  • Quality of care where patients only receive the correct diagnosis and treatment less than half the time on a first visit
  • A lag time of 13-17 years between research and practice in clinical care

Researchers had access to clinical data, demographics and other data from 6,700 patients kept by the Centerstone Research Institute, a nonprofit provider of community-based behavioral healthcare. Between 65 and 70 percent of the patients had major clinical depression diagnoses, as well as chronic physical disorders like diabetes, hypertension and cardiovascular disease, which were used in the simulations.

By using 500 randomly selected patients and data from that group, the researchers compared actual physician performance and patient outcomes against sequential decision-making models. They found the artificial intelligence medical cost to be $189, compared to the treatment-as-usual cost of $497.

“This was at the same time that the AI approach obtained a 30 to 35 percent increase in patient outcomes,” Bennett said. “And we determined that tweaking certain model parameters could enhance the outcome advantage to about 50 percent more improvement at about half the cost.”

Quality healthcare backed by tech at a lower cost may be in a clinic near you sooner than you think.

Chandler Harris is a freelance business and technology writer located in Silicon Valley. He has written for numerous publications including Entrepreneur, InformationWeek, San Jose Magazine, Government Technology, Public CIO, AllBusiness.com, U.S. Banker, Digital Communities Magazine, Converge Magazine, Surfer’s Journal, Adventure Sports Magazine, ClearanceJobs.com, and the San Jose Business Journal.

Chandler Harris
Chandler Harris is a freelance business and technology writer based in Silicon Valley and contributor at aNewDomain.net. He has written for Entrepreneur, InformationWeek, San Jose Magazine, Government Technology, Public CIO, AllBusiness.com, U.S. Banker and the San Jose Business Journal.
Chandler Harris
Tags: Healthcare,Technology,Uncategorized