Abstract

AbstractBackgroundPatients tend to lose the ability to smile during the clinical course of dementia. However, details of such impairment remain obscure presumably due to difficulty of quantifying facial expression. Feature extraction is now automated as a result of recent developments in artificial intelligence (AI). The authors applied a model to quantify impaired smile expression in patients with Alzheimer disease (AD). The relationship between the expression of a smile and subcortical volumes was also investigated.MethodThis study included 280 and 190 participants with AD and with normal cognition (NC), respectively. The faces of the participants were photographed as they smiled or maintained a neutral expression. Subcortical brain volume was assessed in 210 and 90 of those with AD and NC, respectively, using MRI and the FSL‐FIRST algorithm. Datasets of the photographs were prepared with combinations of smiling and neutral expression in NC and AD, smiling in AD and NC, and neutral expression in AD and NC, then binary discrimination proceeded using the VGG‐Face convolutional neural network (CNN).ResultThe accuracy of discriminating a smile from a neutral expression was of 92.3% in NC, and 61.2% in AD, indicating that a considerable proportion of patients with AD have difficulties forming a natural smile. 48.5% of smile AD were classified as negative in NC dataset. The smile/neutral‐NC scores for AD were robustly associated with the volume of the bilateral nucleus accumbens (right, r = 0.51, p = 2.59 × 10−15; left, r = 0.493, p = 2.89 × 10−14) and the bilateral pallidum (right, r = 0.266, p = 0.0000981; left, r = 0.256, p = 0.000174). The accuracy of discriminating between AD and NC was 95.2% with smile and 90.1% with a neutral expression, respectively (p = 0.0045). The neutral‐AD/NC score inversely correlated with the results of the MMSE (p = 1.62 × 10−7), but not with smile/neutral‐NC or smile‐AD/NC scores.ConclusionThe ability to form smile was impaired in AD and associated with nucleus accumbens and pallidum shrinkage. Such impairment enhanced the accuracy of facial discrimination between AD and NC, whereas a neutral expression was associated with cognitive function.

Full Text
Published version (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