Schizophrenia Research Forum - A Catalyst for Creative Thinking

Takayanagi Y, Takahashi T, Orikabe L, Mozue Y, Kawasaki Y, Nakamura K, Sato Y, Itokawa M, Yamasue H, Kasai K, Kurachi M, Okazaki Y, Suzuki M. Classification of first-episode schizophrenia patients and healthy subjects by automated MRI measures of regional brain volume and cortical thickness. PLoS One. 2011 Jan 1 ; 6(6):e21047. Pubmed Abstract
Comments on News and Primary Papers
Primary Papers: Classification of first-episode schizophrenia patients and healthy subjects by automated MRI measures of regional brain volume and cortical thickness.

Comment by:  Angus MacDonald, SRF Advisor
Submitted 11 July 2011 Posted 14 July 2011
  I recommend this paper

There are a few things we'll need to be careful about as we observe a Rise of the Machines (machine learning algorithms in this case): the sensitivity/specificity/positive predictive power/negative predictive power, and that the data generated on one scanner generalize to other scanners. The former will be the horserace that allows for comparison of these various pattern-based discriminant functions. (Keep in mind, interview-based diagnosis isn't perfect either.) The latter speaks to the deployability of these techniques for clinical applications.

View all comments by Angus MacDonald