Video-Based Automatic Baby Motion Analysis for Early Neurological Disorder Diagnosis: State of the Art and Future Directions

Video-based assessments of activities of daily living: generating real-world evidence in pediatric rare diseases

INTRODUCTION

Preserving function and independence to perform activities of daily living (ADL) is critical for patients and carers to manage the burden of care and improve quality of life. In children living with rare diseases, video recording ADLs offer the opportunity to collect the patients' experience in a real-life setting and accurately reflect treatment effectiveness on outcomes that matter to patients and families.

AREAS COVERED

We reviewed the measurement of ADL in pediatric rare diseases and the use of video to develop at-home electronic clinical outcome assessments (eCOA) by leveraging smartphone apps and artificial intelligence-based analysis. We broadly searched PubMed using Boolean combinations of the following MeSH terms 'Rare Diseases,' 'Quality of Life,' 'Activities of Daily Living,' 'Child,' 'Video Recording,' 'Outcome Assessment, Healthcare,' 'Intellectual disability,' and 'Genetic Diseases, Inborn.' Non-controlled vocabulary was used to include human pose estimation in movement analysis.

EXPERT OPINION

Broad uptake of video eCOA in drug development is linked to the generation of technical and clinical validation evidence to confidently assess a patient's functional abilities. Software platforms handling video data must align with quality regulations to ensure data integrity, security, and privacy. Regulatory flexibility and optimized validation processes should facilitate video eCOA to support benefit/risk drug assessment.

A Novel Video-Based Methodology for Automated Classification of Dystonia and Choreoathetosis in Dyskinetic Cerebral Palsy During a Lower Extremity Task

BACKGROUND

Movement disorders in children and adolescents with dyskinetic cerebral palsy (CP) are commonly assessed from video recordings, however scoring is time-consuming and expert knowledge is required for an appropriate assessment.

OBJECTIVE

To explore a machine learning approach for automated classification of amplitude and duration of distal leg dystonia and choreoathetosis within short video sequences.

METHODS

Available videos of a heel-toe tapping task were preprocessed to optimize key point extraction using markerless motion analysis. Postprocessed key point data were passed to a time series classification ensemble algorithm to classify dystonia and choreoathetosis duration and amplitude classes (scores 0, 1, 2, 3, and 4), respectively. As ground truth clinical scoring of dystonia and choreoathetosis by the Dyskinesia Impairment Scale was used. Multiclass performance metrics as well as metrics for summarized scores: absence (score 0) and presence (score 1-4) were determined.

RESULTS

Thirty-three participants were included: 29 with dyskinetic CP and 4 typically developing, age 14 years:6 months ± 5 years:15 months. The multiclass accuracy results for dystonia were 77% for duration and 68% for amplitude; for choreoathetosis 30% for duration and 38% for amplitude. The metrics for score 0 versus score 1 to 4 revealed an accuracy of 81% for dystonia duration, 77% for dystonia amplitude, 53% for choreoathetosis duration and amplitude.

CONCLUSIONS

This methodology study yielded encouraging results in distinguishing between presence and absence of dystonia, but not for choreoathetosis. A larger dataset is required for models to accurately represent distinct classes/scores. This study presents a novel methodology of automated assessment of movement disorders solely from video data.

Mapping autism's research landscape: trends in autism screening and its alignment with sustainable development goals

Introduction

Autism Spectrum Disorder is a complex neurodevelopmental syndrome that profoundly affects social interactions, communication, and sensory perception. The research traced the evolution of autism research from 2011-2022, specifically focusing on the screening and diagnosis of children and students.

Methods

Through an analysis of 12,262 publications using the PRISMA framework, bibliographic coupling, science mapping, and citation analysis, this study illuminates the growth trajectory of ASD research and significant disparities in diagnosis and services.

Results

The study indicates an increasing trend in autism research, with a strong representation of female authorship. Open Access journals show a higher average citation impact compared to their closed counterparts. A keyword co-occurrence analysis revealed four central research themes: Child Development and Support Systems, Early Identification and Intervention, Prevalence and Etiology, and Mental Health. The pandemic's onset has prioritized research areas like mental health, telehealth, and service accessibility.

Discussion

Recommendations on a global level stress the importance of developing timely biological markers for ASD, amplifying Disability Inclusion research, and personalizing mental health services to bridge these critical service gaps. These strategies, underpinned by interdisciplinary collaboration and telehealth innovation, particularly in low-resource settings, can offer a roadmap for inclusive, context-sensitive interventions at local levels that directly support SDG3's aim for health and well-being for all.

Automating General Movements Assessment with quantitative deep learning to facilitate early screening of cerebral palsy

The Prechtl General Movements Assessment (GMA) is increasingly recognized for its role in evaluating the integrity of the developing nervous system and predicting motor dysfunctions, particularly in conditions such as cerebral palsy (CP). However, the necessity for highly trained professionals has hindered the adoption of GMA as an early screening tool in some countries. In this study, we propose a deep learning-based motor assessment model (MAM) that combines infant videos and basic characteristics, with the aim of automating GMA at the fidgety movements (FMs) stage. MAM demonstrates strong performance, achieving an Area Under the Curve (AUC) of 0.967 during external validation. Importantly, it adheres closely to the principles of GMA and exhibits robust interpretability, as it can accurately identify FMs within videos, showing substantial agreement with expert assessments. Leveraging the predicted FMs frequency, a quantitative GMA method is introduced, which achieves an AUC of 0.956 and enhances the diagnostic accuracy of GMA beginners by 11.0%. The development of MAM holds the potential to significantly streamline early CP screening and revolutionize the field of video-based quantitative medical diagnostics.

Automated anomalous child repetitive head movement identification through transformer networks

The increasing prevalence of behavioral disorders in children is of growing concern within the medical community. Recognising the significance of early identification and intervention for atypical behaviors, there is a consensus on their pivotal role in improving outcomes. Due to inadequate facilities and a shortage of medical professionals with specialized expertise, traditional diagnostic methods have been unable to effectively address the rising incidence of behavioral disorders. Hence, there is a need to develop automated approaches for the diagnosis of behavioral disorders in children, to overcome the challenges with traditional methods. The purpose of this study is to develop an automated model capable of analyzing videos to differentiate between typical and atypical repetitive head movements in. To address problems resulting from the limited availability of child datasets, various learning methods are employed to mitigate these issues. In this work, we present a fusion of transformer networks, and Non-deterministic Finite Automata (NFA) techniques, which classify repetitive head movements of a child as typical or atypical based on an analysis of gender, age, and type of repetitive head movement, along with count, duration, and frequency of each repetitive head movement. Experimentation was carried out with different transfer learning methods to enhance the performance of the model. The experimental results on five datasets: NIR face dataset, Bosphorus 3D face dataset, ASD dataset, SSBD dataset, and the Head Movements in the Wild dataset, indicate that our proposed model has outperformed many state-of-the-art frameworks when distinguishing typical and atypical repetitive head movements in children.

Mobile Device-Based Video Screening for Infant Head Lag: An Exploratory Study

INTRODUCTION

Video-based automatic motion analysis has been employed to identify infant motor development delays. To overcome the limitations of lab-recorded images and training datasets, this study aimed to develop an artificial intelligence (AI) model using videos taken by mobile phone to assess infants' motor skills.

METHODS

A total of 270 videos of 41 high-risk infants were taken by parents using a mobile device. Based on the Pull to Sit (PTS) levels from the Hammersmith Motor Evaluation, we set motor skills assessments. The videos included 84 level 0, 106 level 1, and 80 level 3 recordings. We used whole-body pose estimation and three-dimensional transformation with a fuzzy-based approach to develop an AI model. The model was trained with two types of vectors: whole-body skeleton and key points with domain knowledge.

RESULTS

The average accuracies of the whole-body skeleton and key point models for level 0 were 77.667% and 88.062%, respectively. The Area Under the ROC curve (AUC) of the whole-body skeleton and key point models for level 3 were 96.049% and 94.333% respectively.

CONCLUSIONS

An AI model with minimal environmental restrictions can provide a family-centered developmental delay screen and enable the remote monitoring of infants requiring intervention.

2D Capsule Networks Detect Perceived Changes in Infant∼Environment Relationship Reflected in 3D Movement Dynamics

Can infant exploration and causal discovery be detected using Artificial Intelligence (AI)? A recent experiment probed how purposeful action emerges in early life by manipulating infants' functional connection to an object in the environment (i.e., tethering one foot to a colorful mobile). Vicon motion capture data from multiple infant joints were used here to create Histograms of Joint Displacements (HJDs) to generate pose-based descriptors for 3D infant spatial trajectories. Using HJDs as inputs, machine and deep learning systems were tasked with classifying the experimental state from which snippets of movement data were sampled. The architectures tested included k-Nearest Neighbour (kNN), Linear Discriminant Analysis (LDA), Fully connected network (FCNet), 1D-Convolutional Neural Network (1D-Conv), 1D-Capsule Network (1D-CapsNet), 2D-Conv and 2D-CapsNet. Sliding window scenarios were used for temporal analysis to search for topological changes in infant movement related to functional context. kNN and LDA achieved higher classification accuracy with single joint features, while deep learning approaches, particularly 2D-CapsNet, achieved higher accuracy on full-body features. For each AI architecture tested, measures of foot activity displayed the most distinct and coherent pattern alterations across different experimental stages (reflected in the highest classification accuracy rate), indicating that interaction with the world impacts the infant behaviour most at the site of organism∼world connection. Pairing theory-driven experimentation with AI tools thus opens a path to developing functionally-relevant assessments of infant behaviour that are likely to be useful in clinical settings.

Video-Based Behaviorally Coded Movement Assessment for Adolescents with Intellectual Disabilities: Application in Leg Dribbling Performance

Measuring motor performance in individuals with intellectual disabilities (ID) is quite challenging. The objective of this study was to compare the motor performances of individuals with ID and those with typical development (TD) during soccer dribbling through video-based behavior-coded movement assessment along with a wearable sensor. A cross-sectional research design was adopted. Adolescents with TD (N = 25) and ID (N = 29) participated in the straight-line and zigzag soccer dribbling tests. The dribbling performance was videotaped, and the footage was then analyzed with customized behavior-coding software. The coded parameters were the time for movement completion, the number of kicks, blocks, steps, the number of times the ball went out of bounds, the number of missed cones, and the trunk tilt angle. Participants with ID exhibited significantly poorer performance and demonstrated greater variances in many time and frequency domain parameters. It also revealed that participants with ID kicked with both feet while dribbling, whereas those with TD mainly used the dominant foot. The present findings demonstrated how the ID population differed from their peers in lower-extremity strategic control. The customized video-based behavior-coded approach provides an efficient and effective way to gather behavioral data and calculate performance parameter statistics in populations with intellectual disabilities.

Modeling gross motor developmental curves of extremely and very preterm infants using the AIMS home-video method

BACKGROUND

Motor development is one of the first signals to identify whether an infant is developing well. For very preterm (VPT) infants without severe perinatal complications, little is known about their motor developmental curves.

AIMS

Explore gross motor developmental curves from 3 until 18 months corrected age (CA) of VPT infants, and related factors. Explore whether separate profiles can be distinguished and compare these to profiles of Dutch term-born infants.

STUDY DESIGN

Prospective cohort study with parents repeatedly recording their infant, using the Alberta Infant Motor Scale (AIMS) home-video method, from 3 to 18 months CA.

SUBJECTS

Forty-two Dutch infants born ≤32.0 weeks gestational age and/or with a birthweight (BW) of <1500 g without severe perinatal complications.

OUTCOME MEASURES

Gross motor development measured with the AIMS.

RESULTS

In total 208 assessments were analyzed, with 27 infants ≥five assessments, 12 with <four, and three with one assessment. Sigmoid-shaped gross motor curves show unidirectional growth and variability. No infant or parental factors significantly influenced motor development, although a trend was seen for the model where lower BW, five-minute Apgar score <7, and Dutch native-speaking parents were associated with slower motor development. Three motor developmental profiles of VPT infants were identified, early developers, gradual developers, and late bloomers, which until 12 months CA are comparable in shape and speed to profiles of Dutch term-born infants.

CONCLUSIONS

VPT infants show great intra- and interindividual variability in gross motor development, with three motor profiles being distinguished. From 12 months CA onwards, VPT infants appear to develop at a slower pace. With some caution, classifying infants into motor developmental profiles may assist clinical decision-making.