JMIR Publications

ABSTRACT

Background:

Dementia is a neurodegenerative condition that combines several diseases and impacts millions around the world and those around them. Although cognitive impairment is profoundly disabling, it is the noncognitive features of dementia, referred to as Neuropsychiatric Symptoms (NPS), that are most closely associated with a diminished quality of life. Agitation and aggression (AA) in people living with dementia (PwD) contribute to distress and increased healthcare demands. Current assessment methods rely on caregiver intervention and reporting of incidents, introducing subjectivity and bias. Artificial Intelligence (AI) and predictive algorithms offer a potential solution for detecting AA episodes in PwD when utilized in real-time.

Objective:

The system aims to detect AA in PwD using raw data collected from wearable sensors. It also tries identifying pre-agitation patterns from raw data and digital biometrics collected by the same device. Moreover, the system uses cameras to record the agitation events and accurately label the start and end times. A video detection system runs separately to detect agitation using only the participants' skeletal data to preserve privacy.

Methods:

We present a 5-year study system that integrates a multimodal approach, utilizing the EmbracePlus wristband and a video detection system to predict AA in severe dementia patients. We conducted a pilot study with three participants at the Ontario Shores Mental Health Institute to validate the functionality of the system. The system collects and processes raw and digital biomarkers from the EmbracePlus wristband to accurately predict AA. The system also detected pre-agitation patterns at least six minutes before the AA event, which was not previously discovered from the EmbracePlus wristband. Furthermore, the privacy-preserving video system uses a masking tool to hide the features of the people in frames and employs a deep learning model for AA detection. The video system also helps identify the actual start and end time of the agitation events for labeling.

Results:

The system can achieve 98.67% in detecting AA events from biometric data and identify pre-agitation patterns six minutes before the AA event. The privacy-preserving video system uses a masking tool to hide the physical features and achieves an accuracy of 98% in AA detection.

Conclusions:

The promising results of the preliminary data analysis underscore the ability of the system to predict AA events. The ability of the proposed system to run autonomously in real-time and identify AA and pre-agitation symptoms without external assistance represents a significant milestone in this research field.