Leveraging Self-Training and Variational Autoencoder for Agitation Detection in People with Dementia Using Wearable Sensors

2024-12-26

AI Summary

To address the challenge of scarce physiological data annotations and heavy reliance on manual labeling in early agitation detection (AD) among individuals with dementia, this paper proposes a semi-supervised automatic AD detection framework leveraging Empatica E4 wearable wristbands. Methodologically, we introduce a novel synergistic paradigm integrating variational autoencoder (VAE)-based representation learning with self-training: the VAE learns robust physiological feature representations from unlabeled data, while self-training iteratively generates high-quality pseudo-labels to augment supervision; the resulting features and labels are fed into an XGBoost classifier for end-to-end agitation classification. Evaluated on real-world wearable data from three clinical centers comprising 14 patients, our framework achieves 90.16% accuracy—significantly outperforming fully supervised baselines. This work overcomes the annotation bottleneck and establishes a generalizable, unobtrusive, and low-burden technical pathway for continuous agitation monitoring in dementia care.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Multiagent Systems: Adversarial Agents

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Dementia is a neurodegenerative disorder that has been growing among elder people over the past decades. This growth profoundly impacts the quality of life for patients and caregivers due to the symptoms arising from it. Agitation and aggression (AA) are some of the symptoms of people with severe dementia (PwD) in long-term care or hospitals. AA not only causes discomfort but also puts the patients or others at potential risk. Existing monitoring solutions utilizing different wearable sensors integrated with Artificial Intelligence (AI) offer a way to detect AA early enough for timely and adequate medical intervention. However, most studies are limited by the availability of accurately labeled datasets, which significantly affects the efficacy of such solutions in real-world scenarios. This study presents a novel comprehensive approach to detect AA in PwD using physiological data from the Empatica E4 wristbands. The research creates a diverse dataset, consisting of three distinct datasets gathered from 14 participants across multiple hospitals in Canada. These datasets have not been extensively explored due to their limited labeling. We propose a novel approach employing self-training and a variational autoencoder (VAE) to detect AA in PwD effectively. The proposed approach aims to learn the representation of the features extracted using the VAE and then uses a semi-supervised block to generate labels, classify events, and detect AA. We demonstrate that combining Self-Training and Variational Autoencoder mechanism significantly improves model performance in classifying AA in PwD. Among the tested techniques, the XGBoost classifier achieved the highest accuracy of 90.16%. By effectively addressing the challenge of limited labeled data, the proposed system not only learns new labels but also proves its superiority in detecting AA.

Problem

• Dementia
• Agitation Recognition
• Wearable Technology

Innovation

• Smartband Data
• Variational Autoencoder
• XGBoost Classifier