Validation of ANAM for cognitive screening in a mixed clinical sample

Abstract

The Automated Neuropsychological Assessment Metrics (ANAM) is a library of computer based tests designed to measure cognitive function at a single time-point or longitudinally for detection of cognitive change. This study sought to validate ANAM as a cognitive screening tool for presence of confirmed neuropsychological diagnosis in an outpatient setting. Retrospective data analysis was conducted for 139 patients referred for outpatient neuropsychological assessment. Clinical diagnosis was made independent of ANAM test results and resulted in a diagnostic mix of both neurologic and psychologic etiologies. ANAM scores predictive of presence of confirmed diagnosis were identified using multiple logistic regression and the predictive ability of the resulting model was quantified using receiver operator characteristic analysis. Sensitivity and specificity for the ANAM when combined with anger and depressive symptom scores were 71% and 91%, respectively, with a positive predictive value of 97.5 and negative predictive value of 40.4. This combined approach provided the greatest accuracy for individual tests as well as the composite score of the ANAM in identifying those who received a subsequent clinical diagnosis. Although data should be replicated in larger samples, these results suggest that ANAM may have predictive value and may be a useful screening tool for identifying those who would likely benefit from neuropsychological services.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 12 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.