Send to

Choose Destination

See 1 citation found by title matching your search:

Acta Psychiatr Scand. 2018 Nov;138(5):472-482. doi: 10.1111/acps.12945. Epub 2018 Aug 6.

Complexity in mood disorder diagnosis: fMRI connectivity networks predicted medication-class of response in complex patients.

Osuch E1,2,3, Gao S4,5, Wammes M2, Théberge J1,2,3, Willimason P2,3, Neufeld RJ6, Du Y7,8, Sui J4,5,7,9, Calhoun V7,10.

Author information

Lawson Health Research Institute, London Health Sciences Centre, London, ON, Canada.
Department of Psychiatry, University of Western Ontario Schulich School of Medicine and Dentistry, London, ON, Canada.
Department of Medical Biophysics, University of Western Ontario, London, ON, Canada.
Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China.
University of Chinese Academy of Sciences, Beijing, China.
Department of Psychology, University of Western Ontario, London, ON, Canada.
The Mind Research Network, Albuquerque, NM, USA.
School of Computer and Information Technology, Shanxi University, Taiyuan, China.
CAS Center for Excellence in Brain Science and Intelligence Technology, Institute of Automation, Chinese Academy of Sciences, Beijing, China.
Department of Electrical and Computer Engineering, University of New Mexico, Albuquerque, NM, USA.



This study determined the clinical utility of an fMRI classification algorithm predicting medication-class of response in patients with challenging mood diagnoses.


Ninety-nine 16-27-year-olds underwent resting state fMRI scans in three groups-BD, MDD and healthy controls. A predictive algorithm was trained and cross-validated on the known-diagnosis patients using maximally spatially independent components (ICs), constructing a similarity matrix among subjects, partitioning the matrix in kernel space and optimizing support vector machine classifiers and IC combinations. This classifier was also applied to each of 12 new individual patients with unclear mood disorder diagnoses.


Classification within the known-diagnosis group was approximately 92.4% accurate. The five maximally contributory ICs were identified. Applied to the complicated patients, the algorithm diagnosis was consistent with optimal medication-class of response to sustained recovery in 11 of 12 cases (i.e., almost 92% accuracy).


This classification algorithm performed well for the know-diagnosis but also predicted medication-class of response in difficult-to-diagnose patients. Further research can enhance this approach and extend these findings to be more clinically accessible.


bipolar disorder; differential diagnosis; functional neuroimaging; machine learning; mood disorders

Supplemental Content

Full text links

Icon for Wiley Icon for PubMed Central
Loading ...
Support Center