Application of automated face coding (AFC) in older adults: A pilot study

Area of Science:

• Gerontology
• Psychology
• Biomedical Engineering

Background:

• Care-dependent older adults often have communication challenges.
• Understanding their emotional states is crucial for effective care, particularly in healthcare settings like dentistry.
• Automated face coding (AFC) offers a potential tool for objective emotional assessment.

Purpose of the Study:

• To assess the prevalence and nature of emotional expressions in care-dependent older adults using AFC software.
• To examine the manifestation of seven fundamental emotions in this population.
• To explore potential implications for dental care.

Main Methods:

• Fifty care-dependent older adults (mean age 78.90 ± 10.83) had their facial expressions analyzed using AFC software.
• Prevalence of seven fundamental emotions (neutral, happy, sad, angry, surprised, scared, disgusted) was measured.
• Correlations with demographic variables (sex, age, MMSE, sedation use) were explored using descriptive statistics, non-parametric tests, and Spearman's rho.

Main Results:

• Neutral expression was the most prevalent (0.732 ± 0.23).
• Other emotions were largely inactive, with a non-significant trace of happiness in women (0.110 ± 0.23).
• Significant correlations were found between happy expressions and left eye opening (p=0.021), and mouth opening and sad expressions (p=0.049). No associations with age, MMSE, or sedation were found.

Conclusions:

• AFC software effectively detects and quantifies emotions in care-dependent older adults.
• These individuals predominantly exhibit neutral expressions, with limited other emotional displays.
• Findings suggest AFC can inform personalized care approaches for this demographic.