Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Action-Based ADHD Diagnosis in Video

Yichun Li, Yuxing Yang, Syed Nohsen Naqvi

TL;DR

The video-based frame-level action recognition network is introduced to ADHD diagnosis for the first time and three action classes from the video modality are extracted from the video modality for ADHD diagnosis.

Abstract

Attention Deficit Hyperactivity Disorder (ADHD) causes significant impairment in various domains. Early diagnosis of ADHD and treatment could significantly improve the quality of life and functioning. Recently, machine learning methods have improved the accuracy and efficiency of the ADHD diagnosis process. However, the cost of the equipment and trained staff required by the existing methods are generally huge. Therefore, we introduce the video-based frame-level action recognition network to ADHD diagnosis for the first time. We also record a real multi-modal ADHD dataset and extract three action classes from the video modality for ADHD diagnosis. The whole process data have been reported to CNTW-NHS Foundation Trust, which would be reviewed by medical consultants/professionals and will be made public in due course.

Action-Based ADHD Diagnosis in Video

TL;DR

The video-based frame-level action recognition network is introduced to ADHD diagnosis for the first time and three action classes from the video modality are extracted from the video modality for ADHD diagnosis.

Abstract

Attention Deficit Hyperactivity Disorder (ADHD) causes significant impairment in various domains. Early diagnosis of ADHD and treatment could significantly improve the quality of life and functioning. Recently, machine learning methods have improved the accuracy and efficiency of the ADHD diagnosis process. However, the cost of the equipment and trained staff required by the existing methods are generally huge. Therefore, we introduce the video-based frame-level action recognition network to ADHD diagnosis for the first time. We also record a real multi-modal ADHD dataset and extract three action classes from the video modality for ADHD diagnosis. The whole process data have been reported to CNTW-NHS Foundation Trust, which would be reviewed by medical consultants/professionals and will be made public in due course.
Paper Structure (9 sections, 2 equations, 2 figures, 3 tables)

This paper contains 9 sections, 2 equations, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Participants and Procedure
  3. Experiments
  4. Datasets and Data Processing
  5. Experiment Set up and Comparisons
  6. Action Recognition and ADHD Diagnosis Results
  7. Time-Action Based Analysis
  8. Comparison with State-of-the-Art
  9. Conclusions

Figures (2)

  • Figure 1: Flow diagram of the ADHD diagnosis system. The training dataset for the action recognition function is based on 3 classes and is named ADHD-3. The three action classes are still-position, limb-fridges, and torso-movements.
  • Figure 2: Action change timeline chart of three ADHD subjects (top in red box) and three controls (bottom in blue box) recorded by Camera2 (left) and Camera3 (right).