Classification of Depression, Cognitive Disorders, and Co-Morbid Depression and Cognitive Disorders with Perfusion SPECT Neuroimaging.

ABSTRACT:

Background: Depression and cognitive disorders (CDs) are two common co-morbid afflictions that commonly present with overlapping symptoms.

Objective: To evaluate if perfusion neuroimaging with brain SPECT can distinguish persons with depression from those with CDs or both conditions.

Method: Inclusion criteria were persons with DSM-IV depression or CDs (Alzheimer’s dementia, vascular dementia, dementia not otherwise specified, and amnestic disorders not otherwise specified) including persons with both (total n = 4541; 874 CDs, 3269 depression, 425 with both).  Perfusion estimates were quantified using a standard atlas. Cerebral perfusion differences between the groups were calculated using two-sampled t-tests corrected for multiple comparisons. Diagnostic separation was determined with discriminant analysis of all subjects. Feature selection revealed predictive regions in delineating isolated depression from CDs and persons with both disorders. 

Results: Persons with CDs had lower cerebral perfusion in multiple brain regions compared to those with depression. In the co-morbid group with depression and CDs, cerebral hypoperfusion was additive, with regions showing lower regional cerebral blood flow in this group compared to either diagnosis alone. Discriminant analysis distinguished depression from CDs with both baseline and concentration SPECT regions yielding a correct classification of 86% and leave one out cross-validation of 83%. AUC analysis for SPECT regions showed 86% accuracy, 80% sensitivity and 75% specificity. Discriminant analysis delineated both depression and CDs from persons with either diagnosis with a correct classification of 90.8% and leave one out cross validated accuracy of 88.6%. The area under the curve was 83% with sensitivity of 80% and specificity of 70%. Feature selection showed left hippocampal, right insular, cerebellar, and frontal lobe regions as the most predictive in distinguishing depression from dementia. 

Conclusion: Quantitative perfusion SPECT neuroimaging distinguishes depression from dementia and those with both co-morbidities. These results suggest that perfusion brain SPECT can be utilized clinically to delineate between these two disorders with overlapping symptoms.