Even though hundreds of algorithms were developed to ease the weight on front-line worker’s shoulders, there aren’t any stand-out programs. Some might even have been “harmful,” the report said.
Six things to know:
- A June report from the Turing Institute, the U.K.’s center for data science and artificial intelligence, found that AI tools made little to no effect in combatting COVID-19.
- A separate study published in the British Medical Journal analyzed 232 algorithms designed to diagnose patients or predict how sick they may become with COVID-19. Researchers found none of them were fit for clinical use and only two were promising enough for future testing.
- A study published in Nature Machine Intelligence looked at 415 deep-learning models created to diagnose COVID-19 patients and predict patient risk from medical images. Researchers concluded none of them were fit for clinical use.
- Amid staff shortages and towering patient loads, physicians are still using AI to triage COVID-19 patients. Researchers found these tools don’t work the way they are supposed to, but the pressure to use AI to alleviate patient loads may have put tools into hospitals before they were ready.
- Researchers discovered several factors that reduced the accuracy of the AI tools. Algorithms started to associate a hospital’s fonts with patient caseload. Some hospitals had high numbers of COVID-19 patients and used a specific font. Now, AI tools associate that font as a COVID-19 risk factor.
- Some AI tools were built with mislabeled data or used data from unknown sources. Too many algorithms were developed by researchers who lacked the medical expertise to spot flaws in data or by medical researchers that didn’t have the skills needed to compensate for those flaws, the report said.
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.
