Long-Term Test-Retest Reliability of the UPSIT in Cognitively Intact Older Adults

Abstract

The objective of this study was to determine the long-term test-retest reliability of the University of Pennsylvania Smell Identification Test (UPSIT), and its individual items, in cognitively intact older adults. A community sample of older adults received a neuropsychological test battery, including the 12-item, 6-trial Selective Reminding Test (SRT). The UPSIT was administered at baseline and follow-up that occurred between 1 and 4 years after baseline. UPSIT scores of participants who were cognitively intact and did not decline cognitively were examined for test-retest reliability. In 92 older adults with mean age 77.6 years followed for 2.79 (standard deviation [SD] 0.69) years, mean UPSIT score declined from 30.29 (SD 5.83) to 27.80 (SD 5.50). In linear mixed models that adjusted for time, age, sex, and education, intraclass correlation coefficients for UPSIT were 0.65, SRT delayed recall 0.59, and SRT total immediate recall 0.49. Among 4 possible response combinations, the largest proportion of participants had correct responses at both visits for 35 out of 40 items. Consistency of item responses ranged from 50% to 90% across the 2 time points. The long-term test-retest reliability of the UPSIT was moderately strong without practice effects over long periods of time in older adults. These results provide indirect support to prior findings on odor identification impairment predicting cognitive decline and dementia, and suggest potential use of olfactory testing as a biomarker in prevention and treatment trials of cognitive enhancers.

Keywords: aging; item analysis; odor identification; olfaction; reliability; test–retest.