A Self-Administered Digital Test Battery for Early Detection of Cognitive Impairment in Alzheimer’s Disease
Preprint
Abstract
Introduction Early detection of cognitive decline is crucial for timely intervention in Alzheimer’s disease (AD). Traditional paper-pencil assessments often face limitations in accessibility, lengthy administration, and interrater reliability, restricting their broader application across diverse populations. Digital tools may overcome these restrictions by offering user-friendly, non-verbal, and scalable assessments. This study investigated the diagnostic accuracy of BraincheX, a newly developed digital test battery designed with a focus on accessibility and usability, by comparing its subtest performance to equivalents of the Consortium to Establish a Registry for AD (CERAD)-Plus battery. Methods Fifty-six participants with early AD and healthy controls were recruited from the LMU hospital memory clinic. Diagnostic groups were defined by amyloid positivity and clinical expert consensus. Participants completed both the BraincheX digital battery and the CERAD-Plus assessment. A total BraincheX score was calculated by summing standardized subtest scores. Data were analyzed using receiver operating curve (ROC) analysis and the Youden Index to determine diagnostic accuracy. Correlations between BraincheX and CERAD-Plus subtests were examined, and group differences were analyzed via ANOVA. Results ROC analysis revealed strong diagnostic accuracy for the BraincheX total score in differentiating between early AD and controls (AUC = .86; optimal cut-off = -1.51), with a sensitivity of 89.7% and a specificity of 32%. BraincheX total scores correlated strongly with CERAD total scores (r = .73, p < .001). BraincheX demonstrated high internal consistency (Cronbach’s α = .84). ANOVA confirmed significant group differences across all BraincheX subtests (p < .01). Additionally, individual BraincheX subtests showed strong correlations with their CERAD-Plus equivalents, such as the Clock Drawing Test (r = .73) and TMT-B (r = .48). Discussion These findings support BraincheX as a promising, accessible digital screening tool for cognitive decline, offering advantages such as automated scoring, immediate feedback, and reduced examiner bias. Its design promotes greater equity and inclusivity in cognitive assessment. Future research is underway to validate BraincheX in larger and more diverse populations.Keywords
This publication has 33 references indexed in Scilit:
- Artificial intelligence as a tool for cognitive impairment screening: Patient perspectives about benefits and limitationsAlzheimer's & Dementia: Behavior & Socioeconomics of Aging, 2025
- Revised criteria for diagnosis and staging of Alzheimer's disease: Alzheimer's Association WorkgroupAlzheimer's & Dementia, 2024
- Digitale Teilhabe in der Hochaltrigkeit2023
- Diagnostic performance of digital cognitive tests for the identification of MCI and dementia: A systematic reviewAgeing Research Reviews, 2021
- Digitale Transformation in den Haushalten älterer MenschenZeitschrift für Gerontologie und Geriatrie, 2021
- Demenzprädiktion als ethische Herausforderung: Stakeholder fordern Beratungsstandards für DeutschlandDer Nervenarzt, 2020
- Utility of the RBANS in detecting cognitive impairment associated with Alzheimer's disease: Sensitivity, specificity, and positive and negative predictive powersArchives of Clinical Neuropsychology, 2008
- Trail Making Test errors in normal aging, mild cognitive impairment, and dementiaArchives of Clinical Neuropsychology, 2008
- Clock‐drawing and dementia in the community: A longitudinal studyInternational Journal of Geriatric Psychiatry, 1993
- “Mini-mental state”Journal of Psychiatric Research, 1975