Format

Send to

Choose Destination
Sensors (Basel). 2015 Oct 21;15(10):26756-68. doi: 10.3390/s151026756.

A smartphone-based automatic diagnosis system for facial nerve palsy.

Author information

1
Interdisciplinary Program of Bioengineering, Seoul National University, Seoul 03080, Korea. khs0330kr@bmsil.snu.ac.kr.
2
Department of Otorhinolaryngology, Head and Neck Surgery, Seoul National University, Boramae Medical Center, Seoul 07061, Korea. sossi81@hanmail.net.
3
Department of Otorhinolaryngology, Head and Neck Surgery, Seoul National University, Boramae Medical Center, Seoul 07061, Korea. yhkiment@gmail.com.
4
Department of Biomedical Engineering, College of Medicine, Seoul National University, Seoul 03080, Korea. pks@bmsil.snu.ac.kr.

Abstract

Facial nerve palsy induces a weakness or loss of facial expression through damage of the facial nerve. A quantitative and reliable assessment system for facial nerve palsy is required for both patients and clinicians. In this study, we propose a rapid and portable smartphone-based automatic diagnosis system that discriminates facial nerve palsy from normal subjects. Facial landmarks are localized and tracked by an incremental parallel cascade of the linear regression method. An asymmetry index is computed using the displacement ratio between the left and right side of the forehead and mouth regions during three motions: resting, raising eye-brow and smiling. To classify facial nerve palsy, we used Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM), and Leave-one-out Cross Validation (LOOCV) with 36 subjects. The classification accuracy rate was 88.9%.

KEYWORDS:

assessment system; asymmetry; automatic diagnosis; facial nerve palsy; smartphone

PMID:
26506352
PMCID:
PMC4634507
DOI:
10.3390/s151026756
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center