Validation of the Salzburg Dementia Test Prediction (SDTP) as a Cognitive Screening Tool in an English-Speaking Inpatient Medical Setting

Abstract

Background:

The Salzburg Dementia Test Prediction (SDTP), developed using artificial intelligence and based on the Mini-Mental State Examination (MMSE), was recently introduced as a brief cognitive screening tool for cognitive impairment.

Objective:

In the current study, we investigated whether the STDP can be used as a valid bed-side cognitive screening tool for dementia patients, in an English-speaking, medical inpatient setting.

Methods:

216 medically ill older patients who had completed the MMSE (from which the SDTP scores can be calculated), with a subsample 58 patients who had also completed the ACE-R/ACE-III scales. Diagnosis of one of four dementia types (n = 127) and socio-demographic information were also collected. MMSE, SDTP, ACE-R/ACE-III, and dementia diagnosis were used to examine the construct validity of the SDTP through assessments of the structural, concurrent, and convergent validity.

Results:

The SDTP shows structural validity through demonstrating uni-dimensionality. Construct validity was demonstrated by sufficient correlation sizes with MMSE scores against a benchmark correlation size for most of the subsample, except vascular dementia. Convergent validity was demonstrated for the STDP with equivalent correlations sizes with ACE-R/ACE-III as the MMSE across all samples, though for vascular dementia the magnitude of this correlation was not as strong.

Conclusions:

Our findings support using STDP as a brief assessment tool among patients who have been diagnosed with Alzheimer’s disease, Lewy body disease, and mixed dementia; however, there is some statistical variability to overall MMSE scores and correlations with the ACE-R/ACE-III among patients diagnosed with vascular dementia.