Patient-rated scales improve the classification accuracy for patients with depression and anxiety disorder: a linear discriminant analysis

Abstract

Abstract Background The current study aimed to investigate the performances of clinical scales rated by clinicians and patients as well as cognitive function tests in distinguishing patients with affective and anxiety disorders from healthy controls (HCs). Methods We recruited a total of 122 subjects, comprising 24 patients with bipolar disorder (BD), 34 patients with major depressive disorder (MDD), 29 patients with anxiety disorder (AD), and 35 matched HCs. Three clinician-rated scales and five patient-rated scales were used to quantify clinical symptoms, while four cognitive tests were employed to measure cognitive functions in all subjects. Fisher’s discriminant analysis (FDA) was employed to distinguish patients from HCs, as well as to discriminate patient sub-groups from each other. In the FDA model, the prior probability of each group was set as 0.5 in the two-group classification and 0.25 in the four-group classification. Results The results showed that patient-rated scales achieved higher classification accuracies than clinician-rated scales in identifying MDD and AD from HCs. In contrast, cognitive tests exhibited the lowest accuracy. Conclusions These findings suggest that patient-rated scales might improve the classification accuracy for patients with MDD and AD.

Keywords

• Clinician-rated scales
• Patient-rated scales
• Cognition
• Cross-validation
• Classification
• Discrimination