Abstract
Background: Behavioral and psychological symptoms of dementia (BPSD) affect 90% of persons with dementia (PwD), resulting in various adverse outcomes and aggravating care burdens among their caretakers. This study aimed to explore the potential of artificial intelligence-based facial expression recognition systems (FERS) in predicting BPSDs among PwD.Methods: A hybrid of human labeling and a preconstructed deep learning model was used to differentiate basic facial expressions of individuals to predict the results of Neuropsychiatric Inventory (NPI) assessments by stepwise linear regression (LR), random forest (RF) with importance ranking, and ensemble method (EM) of equal importance, while the accuracy was determined by mean absolute error (MAE) and root-mean-square error (RMSE) methods.Results: Twenty-three PwD from an adult day care center were enrolled with ≥ 11,500 FERS data series and 38 comparative NPI scores. The overall accuracy was 86% on facial expression recognition. Negative facial expressions and variance in emotional switches were important features of BPSDs. A strong positive correlation was identified in each model (EM: r = 0.834, LR: r = 0.821, RF: r = 0.798 by the patientwise method; EM: r = 0.891, LR: r = 0.870, RF: r = 0.886 by the MinimPy method), and EM exhibited the lowest MAE and RMSE.Conclusions: FERS successfully predicted the BPSD of PwD by negative emotions and the variance in emotional switches. This finding enables early detection and management of BPSDs, thus improving the quality of dementia care.
Highlights
Behavioral and psychological symptoms of dementia (BPSDs), or neuropsychiatric symptoms, affect 90% of persons with dementia (PwD) over the course of their illness and are associated with greater morbidity, mortality, and distress between caretakers and their family members [1, 2]
More than 11,500 facial expression data series were collected with 38 corresponding Neuropsychiatric Inventory (NPI) scores from 23 participants, and data were divided into two groups (Stage 1 and Stage 2) based on their time of recruitment for analysis
To the best of our knowledge, this is the first study combining customized facial expression recognition systems (FERS) and deep learning algorithms to predict BPSDs in PwD based on facial expressions, and the ensemble method (EM) provided a superior approach to predict NPI scores with better accuracy
Summary
Behavioral and psychological symptoms of dementia (BPSDs), or neuropsychiatric symptoms, affect 90% of persons with dementia (PwD) over the course of their illness and are associated with greater morbidity, mortality, and distress between caretakers and their family members [1, 2]. The potential of artificial intelligence (AI)-based facial expression analysis using a facial expression recognition system (FERS) to identify emotions, pain, and nonverbal information among persons with psychiatric disorders has been documented [6,7,8,9]. The advanced development of AI technology and deep learning programs enables FERS to identify facial expressions and their changes over time from video streams, creating opportunities to develop the automatic detection of BPSDs to improve the quality of dementia care [7,8,9,10, 13]. Conclusions: FERS successfully predicted the BPSD of PwD by negative emotions and the variance in emotional switches This finding enables early detection and management of BPSDs, improving the quality of dementia care
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
