Primary care providers generate higher-quality notes than AI scribes, illustrating the need for humans to continue reviewing and editing drafts created by the technology, a new study found.
Researchers with the U.S. Department of Veterans Affairs had 30 humans blindly rate medical notes produced by 11 AI scribes and 18 human clinicians based on audio from five simulated cases. The raters evaluated each note across 10 domains using the modified Physician Documentation Quality Instrument, aka the PDQI-9.
The human-written notes scored better in every category, particularly standing out in thoroughness, organization and usefulness, according to the April 17 study in Annals of Internal Medicine.
“Although ambient AI scribes hold promise for reducing clinician burden, independent, vendor-neutral evaluations of note quality are essential before large-scale clinical deployment,” the researchers concluded.
