AI Approaches Towards Prechtl's Assessment of General Movements: A Systematic Literature Review
Muhammad Tausif Irshad1,2, Muhammad Adeel Nisar1,2, Philip Gouverneur1
1Institute of Medical Informatics, University of Lübeck, Ratzeburger Allee 160, 23562 Lübeck, Germany.
Insights
General movements (GMs) assessment is crucial for detecting neuromotor deficits like cerebral palsy in infants. This study analyzes AI approaches for GM assessment, identifying limitations and proposing a novel Deep Learning solution for improved accuracy.
Area of Science:
- Neuroscience
- Developmental Pediatrics
- Computer Science
Background:
- General movements (GMs) are spontaneous whole-body movements in infants crucial for assessing neuromotor deficits, including cerebral palsy.
- Current GM assessment relies on time-consuming and expensive expert video analysis.
- Artificial Intelligence (AI) offers potential for automated GM assessment, but existing methods face challenges.
Purpose of the Study:
- To systematically analyze existing AI-based technological approaches for computer-based General Movements assessment.
- To identify shared shortcomings and methodological limitations of current AI methods in GM analysis.
- To propose a novel methodological solution leveraging Deep Learning for improved GM assessment.
Main Methods:
- Systematic literature review of AI-based approaches for Prechtl's General Movements assessment.
- Analysis of design features, performance, and classification rates of existing technological solutions.
- Conceptual proposal of a Deep Learning-based methodology.
Main Results:
- Existing AI approaches for GM assessment share common limitations affecting practical performance.
- Methodological shortcomings hinder the accuracy and reliability of current computer-based GM analysis.
- A gap exists for advanced AI solutions to accurately capture the nuances of infant movements.
Conclusions:
- Current AI methods for General Movements assessment require significant improvement.
- Deep Learning presents a promising avenue for developing more accurate and efficient automated GM assessment tools.
- The proposed Deep Learning approach aims to overcome the limitations of existing AI techniques for early detection of neuromotor impairments.
Abstract:
General movements (GMs) are spontaneous movements of infants up to five months post-term involving the whole body varying in sequence, speed, and amplitude. The assessment of GMs has shown its importance for identifying infants at risk for neuromotor deficits, especially for the detection of cerebral palsy. As the assessment is based on videos of the infant that are rated by trained professionals, the method is time-consuming and expensive. Therefore, approaches based on Artificial Intelligence have gained significantly increased attention in the last years. In this article, we systematically analyze and discuss the main design features of all existing technological approaches seeking to transfer the Prechtl's assessment of general movements from an individual visual perception to computer-based analysis. After identifying their shared shortcomings, we explain the methodological reasons for their limited practical performance and classification rates. As a conclusion of our literature study, we conceptually propose a methodological solution to the defined problem based on the groundbreaking innovation in the area of Deep Learning.
