Predicting Cognitive Assessment Scores in Older Adults with Cognitive Impairment Using Wearable Sensors

2025-11-07

AI Summary

This study addresses the limitations of conventional cognitive screening tools—namely, their time-consuming nature and high ecological interference—by proposing a non-invasive, continuous cognitive assessment paradigm leveraging wearable-derived physiological signals. Using the Empatica EmbracePlus device, we collected photoplethysmography (PPG), electrodermal activity (EDA), skin temperature, and motion data. We applied wavelet transform, segmented feature extraction, and small-sample supervised learning to predict domain-specific cognitive scores—working memory, processing speed, and attention—in older adults with mild cognitive impairment or mild dementia. Our multimodal model achieved Spearman correlations of 0.73–0.82 and mean absolute errors of 0.14–0.16, significantly outperforming baseline methods. The key contribution lies in identifying sensor-specific predictive advantages for distinct cognitive domains, thereby establishing an interpretable, deployable framework for remote, dynamic cognitive monitoring.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Humans and AI: Brain-Sensing and Analysis
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Background and Objectives: This paper focuses on using AI to assess the cognitive function of older adults with mild cognitive impairment or mild dementia using physiological data provided by a wearable device. Cognitive screening tools are disruptive, time-consuming, and only capture brief snapshots of activity. Wearable sensors offer an attractive alternative by continuously monitoring physiological signals. This study investigated whether physiological data can accurately predict scores on established cognitive tests. Research Design and Methods: We recorded physiological signals from 23 older adults completing three NIH Toolbox Cognitive Battery tests, which assess working memory, processing speed, and attention. The Empatica EmbracePlus, a wearable device, measured blood volume pulse, skin conductance, temperature, and movement. Statistical features were extracted using wavelet-based and segmentation methods. We then applied supervised learning and validated predictions via cross-validation, hold-out testing, and bootstrapping. Results: Our models showed strong performance with Spearman's ho of 0.73-0.82 and mean absolute errors of 0.14-0.16, significantly outperforming a naive mean predictor. Sensor roles varied: heart-related signals combined with movement and temperature best predicted working memory, movement paired with skin conductance was most informative for processing speed, and heart in tandem with skin conductance worked best for attention. Discussion and Implications: These findings suggest that wearable sensors paired with AI tools such as supervised learning and feature engineering can noninvasively track specific cognitive functions in older adults, enabling continuous monitoring. Our study demonstrates how AI can be leveraged when the data sample is small. This approach may support remote assessments and facilitate clinical interventions.

Problem

• Predicting cognitive test scores using wearable sensor data
• Assessing specific cognitive functions through physiological signals
• Enabling continuous cognitive monitoring via AI and wearables

Innovation

• Using wearable sensors for continuous physiological monitoring
• Applying supervised learning with wavelet-based feature extraction
• Combining heart signals with movement for cognitive prediction