Undersampling and Cumulative Class Re-decision Methods to Improve Detection of Agitation in People with Dementia

TL;DR

This study enhances agitation detection in dementia patients by applying undersampling techniques and a cumulative re-decision method to address data imbalance and label ambiguity, resulting in improved detection performance.

Contribution

The paper introduces a weighted undersampling approach and a cumulative class re-decision method to improve machine learning-based agitation detection in dementia patients.

Findings

Undersampling with 20% normal data suffices for effective models.

Weighted undersampling evaluates label ambiguity.

CCR improves detection metrics with less data and training time.

Abstract

Agitation is one of the most prevalent symptoms in people with dementia (PwD) that can place themselves and the caregiver's safety at risk. Developing objective agitation detection approaches is important to support health and safety of PwD living in a residential setting. In a previous study, we collected multimodal wearable sensor data from 17 participants for 600 days and developed machine learning models for detecting agitation in one-minute windows. However, there are significant limitations in the dataset, such as imbalance problem and potential imprecise labelsas the occurrence of agitation is much rarer in comparison to the normal behaviours. In this paper, we first implemented different undersampling methods to eliminate the imbalance problem, and came to the conclusion that only 20% of normal behaviour data were adequate to train a competitive agitation detection model. Then, we designed a weighted undersampling method to evaluate the manual labeling mechanism given the ambiguous time interval assumption. After that, the postprocessing method of cumulative class re-decision (CCR) was proposed based on the historical sequential information and continuity characteristic of agitation, improving the decision-making performance for the potential application of agitation detection system. The results showed that a combination of undersampling and CCR improved F1-score and other metrics to varying degrees with less training time and data.