Tic Detection in Tourette Syndrome Patients Based on Unsupervised Visual Feature Learning.

Junya Wu,Yuting Lou,Jianhua Feng,Tianshu Zhou,Jingsong Li,Yufan Guo,Yu Tian,Hua Ru,Jialin Peng

doi:10.1155/2021/5531186

Abstract

A clinical diagnosis of tic disorder involves several complex processes, among which observation and evaluation of patient behavior usually require considerable time and effective cooperation between the doctor and the patient. The existing assessment scale has been simplified into qualitative and quantitative assessments of movements and sound twitches over a certain period, but it must still be completed manually. Therefore, we attempt to find an automatic method for detecting tic movement to assist in diagnosis and evaluation. Based on real clinical data, we propose a deep learning architecture that combines both unsupervised and supervised learning methods and learns features from videos for tic motion detection. The model is trained using leave-one-subject-out cross-validation for both binary and multiclass classification tasks. For these tasks, the model reaches average recognition precisions of 86.33% and 86.26% and recalls of 77.07% and 78.78%, respectively. The visualization of features learned from the unsupervised stage indicates the distinguishability of the two types of tics and the nontic. Further evaluation results suggest its potential clinical application for auxiliary diagnoses and evaluations of treatment effects.

Highlights

Tourette syndrome (TS) is a childhood-onset neurodevelopmental disorder characterized by the presence of fluctuating motor and vocal tics [1]. e core diagnostic features are both multiple motor and one or more phonic tics lasting more than one year
Approximately 20% of persons with TS are unaware that they have tics [4]. e clinical diagnosis of TS involves complex processes that require considerable time and effective cooperation between the doctor and the patient, especially observation and evaluation of the patient’s tic behaviors
All the preprocessed unlabeled video datasets were randomly split into a training set (70%) and a validation set (30%) at the patient level

Summary

Introduction

Tourette syndrome (TS) is a childhood-onset neurodevelopmental disorder characterized by the presence of fluctuating motor and vocal tics [1]. e core diagnostic features are both multiple motor and one or more phonic tics lasting more than one year. Tourette syndrome (TS) is a childhood-onset neurodevelopmental disorder characterized by the presence of fluctuating motor and vocal tics [1]. E core diagnostic features are both multiple motor and one or more phonic tics lasting more than one year. The same tic occurs at short-term periodicity with short intervals [2]. E simple tic forms are eye blinking, mouth twitching, head jerking, etc. As the understanding of this disease deepens, the number of children diagnosed with tic disorder has gradually increased, but most cases do not receive timely clinical attention in the early stages of the disease. E clinical diagnosis of TS involves complex processes that require considerable time and effective cooperation between the doctor and the patient, especially observation and evaluation of the patient’s tic behaviors. A number of instruments for tics and associated phenomena have been developed to assess tic severity [5] and differ in construct, comprehensiveness, and ease of administration

Objectives

Methods

Results

Discussion

Conclusion