Performance-Based Cognitive Screening Instruments: An Extended Analysis of the Time versus Accuracy Trade-off

Abstract

Early and accurate diagnosis of dementia is key to appropriate treatment and management. Clinical assessment, including the use of cognitive screening instruments, remains integral to the diagnostic process. Many cognitive screening instruments have been described, varying in length and hence administration time, but it is not known whether longer tests offer greater diagnostic accuracy than shorter tests. Data from several pragmatic diagnostic test accuracy studies examining various cognitive screening instruments in a secondary care setting were analysed to correlate measures of test diagnostic accuracy and test duration, building on the findings of a preliminary study. High correlations which were statistically significant were found between one measure of diagnostic accuracy, area under the receiver operating characteristic curve, and surrogate measures of test duration, namely total test score and total number of test items/questions. Longer cognitive screening instruments may offer greater accuracy for the diagnosis of dementia, an observation which has possible implications for the optimal organisation of dedicated cognitive disorders clinics.

Keywords: accuracy; cognitive screening instruments; dementia; diagnosis.

Figure 1

Scatter plot of test correct classification accuracy versus total test score (= surrogate measure of test administration time).

Figure 2

Scatter plot of test correct classification accuracy versus total number of test items/questions (= surrogate measure of test administration time).

Figure 3

Scatter plot of area under ROC curve versus total test score (= surrogate measure of test administration time).

Figure 4

Scatter plot of area under ROC curve versus total number of test items/questions (= surrogate measure of test administration time).

Figure 5

Scatter plot of test correct classification accuracy versus approximate test administration time.

Figure 6

Scatter plot of area under ROC curve versus approximate test administration time.