Beyond Missing Data: Questionnaire Uncertainty Responses as Early Digital Biomarkers of Cognitive Decline and Neurodegenerative Diseases

2025-12-15

AI Summary

Early detection of neurodegenerative diseases remains challenging due to the lack of scalable, non-invasive preclinical biomarkers reflecting incipient cognitive vulnerability. Method: Leveraging the UK Biobank cohort (n = 502,625), we redefined “don’t know”/“can’t remember” (DK) response frequency in touchscreen questionnaires as a quantifiable, dose-dependent behavioral biomarker—departing from conventional missing-data imputation paradigms. We integrated Cox proportional hazards modeling with plasma proteomics (Aβ40/42, neurofilament light [NFL], pTau-181) and metabolomics. Contribution/Results: Elevated DK frequency independently predicted increased risk of Alzheimer’s disease (HR = 1.64, 95% CI: 1.52–1.77) and vascular dementia (HR = 1.93, 95% CI: 1.69–2.20). It correlated significantly with early neurodegeneration biomarkers and dysregulated lipid metabolism. This work establishes the first systematic, multi-omic bridge linking digital behavior to underlying neuropathological mechanisms, enabling large-scale, non-invasive risk stratification.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Data transparency and provenance
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Identifying preclinical biomarkers of neurodegenerative diseases remains a major challenge in aging research. In this study, we demonstrate that frequent "Don't know/can't remember" (DK) responses, often treated as missing data in touchscreen questionnaires, serve as a novel digital behavioral biomarker of early cognitive vulnerability and neurodegenerative disease risk. Using data from 502,234 UK Biobank participants, we stratified individuals based on DK response frequency (0-1, 2-4, 5-7, >7) and observed a robust, dose-dependent association with an increased risk of Alzheimer's disease (HR = 1.64, 95% CI: 1.26-2.14) and vascular dementia (HR = 1.93, 95% CI: 1.37-2.72), independent of established risk factors. As DK response frequency increased, participants exhibited higher BMI, reduced physical activity, higher smoking rates, and a higher prevalence of chronic diseases, particularly hypertension, diabetes, and depression. Further analysis revealed a dose-dependent relationship between DK response frequency and the risk of Alzheimer's disease and vascular dementia, with high DK responders showing early neurodegenerative changes, marked by elevated levels of Abeta40, Abeta42, NFL, and pTau-181. Metabolomic analysis also revealed lipid metabolism abnormalities, which may mediate this relationship. Together, these findings reframe DK response patterns as clinically meaningful signals of multidimensional neurobiological alterations, offering a scalable, low-cost, non-invasive tool for early risk identification and prevention at the population level.

Problem

• Frequent 'Don't know' responses predict early cognitive decline risk
• These responses link to neurodegenerative disease biomarkers and metabolic changes
• They offer a scalable tool for early population-level risk identification

Innovation

• Treating 'Don't know' responses as digital biomarkers for cognitive decline
• Using DK frequency to predict Alzheimer's and vascular dementia risk
• Linking DK patterns to neurobiological changes via metabolomic analysis