AI in Healthcare spent 2019 tracking the steady evolution of AI and other advanced technologies, paying close attention to how they could change patient care forever. We’ve gathered 10 of the site’s most popular—and compelling—articles from the past 12 months. Read the full list below:
More than 1,200 industry professionals contributed to AI in Healthcare’s 2020 Leadership Survey, with 40% of respondents saying they already use AI on a regular basis. The survey, a collaboration with Pure Storage, included input on research, implementation and other areas related AI and healthcare.
AI in Healthcare was in Chicago for RSNA 2019, speaking with researchers, vendors and other attendees about radiology’s close connection to AI. These two stories showcase the fascinating perspective of vendors working to develop AI-powered solutions in today’s ever-changing healthcare marketplace. While the first story looks at common mistakes being made by health systems, the second examines the technology’s long-term impact on radiology.
More coverage from RSNA 2019 and other industry conferences can be read here.
The American Hospital Association’s 2019 report, AI and the Health Care Workforce, examined the many ways providers can successfully integrate AI technologies. The report also explores how AI will be affecting the healthcare workforce, suggesting it should improve care—and the performance of physicians—in a number of ways
AI has impacted radiology more than any other specialty, a trend that is sure to carry on through 2020 and beyond. According to a new commentary published in the Journal of the American College of Radiology, radiologists will see significant benefits from the continued rise of AI.
“If we sit back and do nothing, there is a chance we could be marginalized by AI,” wrote lead author Bibb Allen, MD, chief medical officer of the American College of Radiology Data Science Institute (ACR DSI), and colleagues. “On the other hand, if we play a leadership role in AI development, the best days for radiologists, our specialty and our patients are yet to come.”
An analysis published in Nursing Management looked at things nurses should know about AI, robotics and what it takes to introduce advanced technologies into existing workflows.
One of the more notable AI stories from the beginning of 2019 involved AI-powered software that can identify schizophrenia in fMRI scans with 87% accuracy.
“Two individuals with the same diagnosis might still present different symptoms,” lead author Sunil Kalmady, PhD, said in a statement at the time. “This often leads to misdiagnosis. Machine learning, in this case, is able to drive an evidence-based approach that looks at thousands of features in a brain scan to lead to an optimal prediction.”
A machine learning algorithm has been trained predict the appearance of sepsis one to two days advance, according to researchers who shared their findings in Computers in Biology and Medicine. The team noted that sepsis results in nearly 270,000 deaths annually throughout the United States, so the algorithm shows the potential to help a whole lot of patients.
AI algorithms can be developed that change imaging findings on purpose, leading to incorrect diagnoses. It sounds bizarre, but a study published in the European Journal of Radiology explored why it remains a very real possibility that could have a devastating impact on healthcare providers.
A report put together by the Brookings Institution provided insight into some of the many risks associated with AI. Those risks included privacy concerns, bias and much more.