The problem is getting objective outcome data. Surgeons evaluating their own results, augmented merely by patient surveys, is not objective.

It’s almost comical for Plastic and Reconstructive Surgery to be publishing articles about AI applications in plastic surgery when the highest level of evidence in their journal is surgeons evaluating their own results, usually with a tremendous level of bias. Or they’ll claim “no serious complications” after sending out a flawed survey with a response rate of ~50%.

Before technology can be used to analyze outcome data, we need better, more objective outcome data to work with as a starting point. There is also a need for better information quality. Plastic Surgeons are especially guilty of publishing bs they pulled out of their asses. All claims should be supported by research and reference a primary source.