AAIC 2026 Abstract Submission

Authors

Carlos Estebas Armas ¹, Alejandro Medina López¹, Daniel Blanco de Miguel¹, María Hernández Barral¹, Elisa Alonso López^1,2, Sergio Henche Rodriguez ¹, Oscar Ocampo Perez¹, María Alonso de Leciñana Cases¹, Ana Frank García^1,2, Ángel Martín Montes ¹                   

 

¹ Department of Neurology and Stroke Center. La Paz University Hospital. Universidad Autónoma de Madrid. La Paz University Hospital Research Institute (IdiPAZ). Madrid, Spain.

² Networking Research Center on Neurodegenerative Diseases (CIBERNED), Instituto de Salud Carlos III, Madrid, Spain

 

Title:

CogniPaz: validation of an ecologically oriented digital tool for detecting mild cognitive impairment

Background

Accurately discriminating amnestic mild cognitive impairment (aMCI) from subjective cognitive decline (SCD) and healthy controls (HC) remains a significant diagnostic challenge in clinical practice. We aimed to validate the diagnostic accuracy of CogniPaz, an ecologically oriented digital cognitive assessment composed of nine tasks designed to evaluate memory and executive functions, in discriminating MCI/aMCI from SCD and HC.

Methods

We conducted a prospective observational study including participants with subjective cognitive complaints or asymptomatic controls recruited between April 2025 and January 2026 at La Paz University Hospital Cognitive Impairment Unit. Participants were classified after clinical assessment and Montreal Cognitive Assessment (MoCA) into HC (asymptomatic; MoCA ≥26), SCD (cognitive complaints; MoCA ≥26), and MCI/aMCI (cognitive complaints without functional impairment; MoCA <26). CogniPaz was administered after MoCA by a blinded evaluator under minimal supervision, following a standardized protocol. Correlation between CogniPaz and MoCA scores was assessed using Pearson, diagnostic accuracy was evaluated using ROC analyses and usability was measured with a satisfaction questionnaire scored on a 0–9 scale.

Results

84 participants were recruited: 40 with MCI (22 aMCI), 18 with SCD and 27 HC. The aMCI group was significantly older (mean 76.5 years) than SCD group (mean 59 years; p<0.05). Mean CogniPaz administration time was 9.4 minutes. Total scores correlated strongly with MoCA (r=0.81, p<0.001). Specific memory tasks correlated highly with MoCA memory domains (r=0.68, p<0.001). CogniPaz demonstrated excellent diagnostic accuracy in distinguishing MCI vs HC (AUC=0.880), MCI vs SCD (AUC=0.915), aMCI vs HC (AUC=0.910) and aMCI vs SCD (AUC=0.943). At the<28.5 points cutoff, sensitivity ranged from 85.0% to 90.9% and specificity from 74.1% to 82.4% across comparisons. Particularly, it was accurate in differentiating aMCI vs SCD (90.9% sensitivity, 82.4% specificity). In an exploratory subanalysis in patient with available biomarker data it also discriminated neurodegenerative from non-neurodegenerative cases (AUC=0.810). User satisfaction was high (median 8.4/9).

Conclusions

CogniPaz demonstrates excellent discrimination, independent of age, in distinguishing MCI and aMCI from SCD and HC, and promising capacity for identifying neurodegeneration suggestive of AD at an unified cutoff of 28.5 points, with a strong correlation with MoCA. These results support its use as a rapid digital screening tool for early-stage cognitive impairment. External longitudinal validation is essential before implementation.