Diagnostic accuracy and agreement across three depression assessment measures for Parkinson's disease

Abstract

Purpose: To assess diagnostic accuracy of two self-administered depression measures compared to an interviewer-administered measure in subjects with Parkinson's disease (PD), and to analyze clinical and sociodemographic factors associated with disagreement among the three depression assessment tools.

Methods: We assessed 214 PD subjects using the Patient Health Questionnaire-9 (PHQ-9), the Geriatric Depression Scale-15 (GDS-15), and the Structured Clinical Interview for the DSM-IV depression module (SCID). Diagnostic accuracy of the PHQ-9 and GDS-15 compared to the SCID was evaluated. Multivariate logistic regression was conducted to analyze factors associated with measure disagreement. We compared item agreement between the PHQ-9 and SCID to test the hypothesis that there would be less agreement between items assessing depression symptoms overlapping with common PD symptoms, compared to items having minimal overlap with PD manifestations.

Results: Compared to SCID diagnosis of major depression, PHQ-9 sensitivity is 50% and specificity is 93%; GDS-15 sensitivity is 43% and specificity is 96%. The GDS-15 has 85% sensitivity and 79% specificity and the PHQ-9 has 54% sensitivity and 85% specificity compared to SCID diagnosis of minor or major depression. The PHQ-9 and SCID show more agreement on items unrelated to PD manifestations. Pain was the only factor associated with disagreement between the SCID and PHQ-9.

Conclusion: Compared to the PHQ-9, the GDS-15 had higher sensitivity and similar positive predictive value, suggesting it is a superior screening tool in clinical applications for PD. On future depression screening or diagnostic instruments, consideration should be given to excluding depression items overlapping with PD manifestations.