Reader Comments
Post a new comment on this article
Post Your Discussion Comment
Please follow our guidelines for comments and review our competing interests policy. Comments that do not conform to our guidelines will be promptly removed and the user account disabled. The following must be avoided:
- Remarks that could be interpreted as allegations of misconduct
- Unsupported assertions or statements
- Inflammatory or insulting language
Thank You!
Thank you for taking the time to flag this posting; we review flagged postings on a regular basis.
closeClinical utility: The problem of differential diagnosis
Posted by lknouse on 11 Dec 2013 at 19:16 GMT
I want to thank the authors for their work in this important area. I found the results intriguing. However, they did not address one crucial point: the fact that their algorithm performs well when differentiating ADHD vs. healthy controls BUT that real-world clinical diagnosis rarely involves making this judgment. (Indeed, most clinicians would probably be fairly accurate in differentiating children with ADHD from those with no psychiatric diagnoses or significant functional impairments at all.) Instead, clinicians are asked to differentiate ADHD from other conditions producing similar symptoms that might account for functional impairment. In addition, ADHD is highly comorbid with other psychiatric diagnoses, further complicating the diagnostic task. So, although these results are promising, I believe an important next-step study would be to see how well the algorithm differentiates people with ADHD from people with other psychiatric diagnoses. If accuracy is achieved under those conditions, that would truly be a major step toward a system with true clinical utility.