Aging
Navigate
Submit an Article
Research Paper|Volume 13, Issue 2|pp 1765—1772

Screening of Alzheimer’s disease by facial complexion using artificial intelligence

Yumi Umeda-Kameyama1, Masashi Kameyama2, Tomoki Tanaka3, Bo-Kyung Son3,6, Taro Kojima1, Makoto Fukasawa4, Tomomichi Iizuka5, Sumito Ogawa1, Katsuya Iijima3,6, Masahiro Akishita1
  • 1Department of Geriatric Medicine, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
  • 2Department of Diagnostic Radiology, Tokyo Metropolitan Geriatric Hospital and Institute of Gerontology, Tokyo, Japan
  • 3Institute of Gerontology, The University of Tokyo, Tokyo, Japan
  • 4Department of Nuclear Medicine, Fukujuji Hospital, Japan Anti-Tuberculosis Association, Kiyose, Japan
  • 5Center for Dementia, Fukujuji Hospital, Japan Anti-Tuberculosis Association, Kiyose, Japan
  • 6Institute for Future Initiatives, The University of Tokyo, Tokyo, Japan
Received: November 3, 2020Accepted: December 10, 2020Published: January 25, 2021
https://doi.org/10.18632/aging.202545

Copyright: © 2021 Umeda-Kameyama et al. This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Abstract

Despite the increasing incidence and high morbidity associated with dementia, a simple, non-invasive, and inexpensive method of screening for dementia is yet to be discovered. This study aimed to examine whether artificial intelligence (AI) could distinguish between the faces of people with cognitive impairment and those without dementia.121 patients with cognitive impairment and 117 cognitively sound participants were recruited for the study. 5 deep learning models with 2 optimizers were tested. The binary differentiation of dementia / non-dementia facial image was expressed as a “Face AI score”. Xception with Adam was the model that showed the best performance. Overall sensitivity, specificity, and accuracy by the Xception AI system and AUC of the ROC curve were 87.31%, 94.57%, 92.56%, and 0.9717, respectively. Close and significant correlations were found between Face AI score and MMSE (r = −0.599, p < 0.0001). Significant correlation between Face AI score and chronological age was also found (r = 0.321, p < 0.0001). However, MMSE score showed significantly stronger correlation with Face AI score than chronological age (p < 0.0001). The study showed that deep learning programs such as Xception have the ability to differentiate the faces of patients with mild dementia from that of patients without dementia, paving the way for future studies into the development of a facial biomarker for dementia.