Becker's Healthcare June 28, 2019
Incorporating increasingly larger datasets into medical artificial intelligence is a double-edged sword: While more data leads to more accurate algorithms and thus improved outcomes, it also requires more extensive and time-consuming processes of validation.
In an op-ed published June 28 in the journal npj Digital Medicine, D. Douglas Miller, MD, senior associate dean for medical education at the Medical College of Georgia in Augusta, described the risks associated with inputting data into complex medical AI, and how physicians can avoid them.
“Modern physicians know that the grounding premise of medical practice remains scientific knowledge,” Dr. Miller wrote. “However, the undisciplined pursuit of neo-technologies by AI-enthused medical users in the absence of transparent input data quality assurances could unknowingly do harm...