Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, United Kingdom; UK Dementia Research Institute Care Research and Technology Centre, Imperial College, London, United Kingdom.
Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, United Kingdom.
Comput Biol Med. 2024 Dec;183:109287. doi: 10.1016/j.compbiomed.2024.109287. Epub 2024 Oct 25.
Sensor-based remote health monitoring is increasingly used to detect adverse health in people living with dementia (PLwD) at home, aiming to prevent hospitalizations and reduce caregiver burden. However, home sensor data is often noisy, overly granular, and suffers from unreliable labeling, data drift and high variability between households. Current anomaly detection methods lack generalizability and personalization, often requiring anomaly-free training data and frequent model updates.
To develop a lightweight, explainable, self-supervised approach with personalized alert thresholds to detect adverse health events in PLwD, using changes in home activity.
We hypothesized that health downturns manifest as detectable shifts in household movement patterns. Our approach leverages a Graph Barlow Twins contrastive model, which uses granular activity data and a macroscopic view to extract noise-robust, high-level and low-level discriminative features that represent daily activity patterns. Household-personalized alert thresholds are calculated based on clinician-set target alert rates, and daily anomaly scores are compared against these thresholds, triggering alerts for the clinical monitoring team. Model attention weights support explainability. Data were collected from a real-world dataset by the UK Dementia Research Institute (August 2019-April 2022).
Our model outperformed state-of-the-art temporal graph algorithms in detecting agitation and fall events across three patient cohorts, achieving 81% average recall and 88% generalizability at a target alert rate of 7%.
We developed a novel, lightweight, explainable, and personalized Graph Barlow Twins model for real-world remote health monitoring in dementia care, with potential for broader applications in healthcare and sensor-based environments.
基于传感器的远程健康监测越来越多地用于在家中检测患有痴呆症（PLwD）的人的不良健康状况，旨在预防住院和减轻护理人员的负担。然而，家庭传感器数据通常存在噪声、过于琐碎、标签不可靠、数据漂移以及家庭之间的高度可变性等问题。当前的异常检测方法缺乏泛化性和个性化，通常需要无异常的训练数据和频繁的模型更新。
开发一种轻量级、可解释、自监督的方法，使用家庭活动的变化来检测 PLwD 中的不良健康事件，并具有个性化的警报阈值。
我们假设健康状况下降表现为可检测的家庭活动模式变化。我们的方法利用了图 Barlow Twins 对比模型，该模型使用粒度活动数据和宏观视图来提取噪声鲁棒、高级和低级的有区分性特征，这些特征代表日常活动模式。根据临床医生设定的目标警报率计算家庭个性化的警报阈值，并将每日异常分数与这些阈值进行比较，为临床监测团队触发警报。模型的注意力权重支持可解释性。数据是由英国痴呆症研究所（2019 年 8 月至 2022 年 4 月）的真实数据集收集的。
我们的模型在检测三个患者队列的激动和跌倒事件方面优于最先进的时间图算法，在目标警报率为 7%的情况下，平均召回率达到 81%，通用性达到 88%。
我们开发了一种新颖的、轻量级的、可解释的、个性化的基于图的 Barlow Twins 模型，用于痴呆症护理的真实世界远程健康监测，具有在医疗保健和基于传感器的环境中更广泛应用的潜力。
