Deep learning assessment of child gross-motor

Suzuki, Satoshi; Amemiya, Yoshihito; Sato, Maiko

doi:10.1109/hsi49210.2020.9142684

Cited by 7 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several previous studies have attempted to predict pediatric development using digital phenotype data, such as detecting developmental disabilities using drag-and-drop data in games [ 41 ], identifying visual impairments using gaze patterns and facial feature data in response to visual stimuli on a smartphone, and measuring fine motor skills in children using sensor-augmented toys [ 42 ]. Suzuki et al [ 23 , 24 ] conducted studies that collected the behavioral videos of 4- to 5-year-old children and extracted skeletal data through OpenPose to evaluate behavioral performance on a per-video basis using a convolutional neural network and autoencoder model. Liu et al [ 22 ] proposed a method to evaluate the initial gross motor skills of children with autism with an average age of 5 years using velocities, trajectories, and angles of upper and lower limb joints based on skeleton data extracted through OpenPose.…”

Section: Discussionmentioning

confidence: 99%

“…For human pose estimation, we used HRNet and Faster-RCNN compared to the studies by Suzuki et al [ 23 , 24 ] and Liu et al [ 22 ], which used OpenPose [ 30 , 31 , 45 ]. In human pose estimation, there are 2 types of methods: the bottom-up method (eg, OpenPose), where each body part is detected first and subsequently the body parts are combined, and the top-down method (eg, HRNet + Faster-RCNN), where the person is detected and then each body part is searched within the detected bounding box [ 29 - 31 , 45 ].…”

Section: Discussionmentioning

confidence: 99%

“…However, this study did not use a previously validated metric such as the K-DST, which may limit the explainability and generalizability of the model. Liu et al [ 22 ] evaluated the gross motor skills of children with autism with an average age of 5 years, and Suzuki et al [ 23 , 24 ] assessed gross motor skills on a video-by-video basis using a deep learning model with behavioral videos of 4- to 5-year-old children. However, since these studies were conducted on children aged ≥4 years, there is a limitation in that they could not validate the model effectiveness in the <3 years age group, where early intervention is expected to be more effective.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Comprehensive Assessment and Early Prediction of Gross Motor Performance in Toddlers With Graph Convolutional Networks–Based Deep Learning: Development and Validation Study

Chun,

Jang,

Kim

et al. 2024

JMIR Form Res

View full text Add to dashboard Cite

Background Accurate and timely assessment of children’s developmental status is crucial for early diagnosis and intervention. More accurate and automated developmental assessments are essential due to the lack of trained health care providers and imprecise parental reporting. In various areas of development, gross motor development in toddlers is known to be predictive of subsequent childhood developments. Objective The purpose of this study was to develop a model to assess gross motor behavior and integrate the results to determine the overall gross motor status of toddlers. This study also aimed to identify behaviors that are important in the assessment of overall gross motor skills and detect critical moments and important body parts for the assessment of each behavior. Methods We used behavioral videos of toddlers aged 18-35 months. To assess gross motor development, we selected 4 behaviors (climb up the stairs, go down the stairs, throw the ball, and stand on 1 foot) that have been validated with the Korean Developmental Screening Test for Infants and Children. In the child behavior videos, we estimated each child’s position as a bounding box and extracted human keypoints within the box. In the first stage, the videos with the extracted human keypoints of each behavior were evaluated separately using a graph convolutional networks (GCN)–based algorithm. The probability values obtained for each label in the first-stage model were used as input for the second-stage model, the extreme gradient boosting (XGBoost) algorithm, to predict the overall gross motor status. For interpretability, we used gradient-weighted class activation mapping (Grad-CAM) to identify important moments and relevant body parts during the movements. The Shapley additive explanations method was used for the assessment of variable importance, to determine the movements that contributed the most to the overall developmental assessment. Results Behavioral videos of 4 gross motor skills were collected from 147 children, resulting in a total of 2395 videos. The stage-1 GCN model to evaluate each behavior had an area under the receiver operating characteristic curve (AUROC) of 0.79 to 0.90. Keypoint-mapping Grad-CAM visualization identified important moments in each behavior and differences in important body parts. The stage-2 XGBoost model to assess the overall gross motor status had an AUROC of 0.90. Among the 4 behaviors, “go down the stairs” contributed the most to the overall developmental assessment. Conclusions Using movement videos of toddlers aged 18-35 months, we developed objective and automated models to evaluate each behavior and assess each child’s overall gross motor performance. We identified the important behaviors for assessing gross motor performance and developed methods to recognize important moments and body parts while evaluating gross motor performance.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comprehensive Assessment and Early Prediction of Gross Motor Performance in Toddlers With Graph Convolutional Networks–Based Deep Learning: Development and Validation Study

Chun,

Jang,

Kim

et al. 2024

JMIR Form Res

View full text Add to dashboard Cite

show abstract

“…Deep learning has been successfully used to diagnose or monitor children’s movement patterns with respect to neurological disorders [ 20 , 21 , 30 , 31 ]. The primary aim of this paper is to demonstrate the feasibility of the in-home monitoring of children’s neurological development through 2D video recordings, 2D pose estimation and deep learning architectures [ 23 , 32 , 33 ].…”

Section: Introductionmentioning

confidence: 99%

The Classification of Movement in Infants for the Autonomous Monitoring of Neurological Development

Turner

Hayes

Sharkey

2023

Sensors

View full text Add to dashboard Cite

Neurodevelopmental delay following extremely preterm birth or birth asphyxia is common but diagnosis is often delayed as early milder signs are not recognised by parents or clinicians. Early interventions have been shown to improve outcomes. Automation of diagnosis and monitoring of neurological disorders using non-invasive, cost effective methods within a patient’s home could improve accessibility to testing. Furthermore, said testing could be conducted over a longer period, enabling greater confidence in diagnoses, due to increased data availability. This work proposes a new method to assess the movements in children. Twelve parent and infant participants were recruited (children aged between 3 and 12 months). Approximately 25 min 2D video recordings of the infants organically playing with toys were captured. A combination of deep learning and 2D pose estimation algorithms were used to classify the movements in relation to the children’s dexterity and position when interacting with a toy. The results demonstrate the possibility of capturing and classifying children’s complexity of movements when interacting with toys as well as their posture. Such classifications and the movement features could assist practitioners to accurately diagnose impaired or delayed movement development in a timely fashion as well as facilitating treatment monitoring.

show abstract

“…Concerning the use of artificial intelligence (AI), various studies have evaluated children's motor functions—evaluation of cognition with physical movements [ 15 , 16 ], detection of machine learning–based fine motor skills [ 17 ], and evaluation of deep learning–based children's gross motor skills [ 18 ]—but they were all AI-based, model-oriented studies. Contrastingly, this study focused on presenting a dataset of children's gross motor skills for each age group.…”

Section: Introductionmentioning

confidence: 99%

Multiview child motor development dataset for AI-driven assessment of child development

Kim

Jang

et al. 2022

GigaScience

View full text Add to dashboard Cite

Background Children's motor development is a crucial tool for assessing developmental levels, identifying developmental disorders early, and taking appropriate action. Although the Korean Developmental Screening Test for Infants and Children (K-DST) can accurately assess childhood development, its dependence on parental surveys rather than reliable, professional observation limits it. This study constructed a dataset based on a skeleton of recordings of K-DST behaviors in children aged between 20 and 71 months, with and without developmental disorders. The dataset was validated using a child behavior artificial intelligence (AI) learning model to highlight its possibilities. Results The 339 participating children were divided into 3 groups by age. We collected videos of 4 behaviors by age group from 3 different angles and extracted skeletons from them. The raw data were used to annotate labels for each image, denoting whether each child performed the behavior properly. Behaviors were selected from the K-DST's gross motor section. The number of images collected differed by age group. The original dataset underwent additional processing to improve its quality. Finally, we confirmed that our dataset can be used in the AI model with 93.94%, 87.50%, and 96.31% test accuracy for the 3 age groups in an action recognition model. Additionally, the models trained with data including multiple views showed the best performance. Conclusion Ours is the first publicly available dataset that constitutes skeleton-based action recognition in young children according to the standardized criteria (K-DST). This dataset will enable the development of various models for developmental tests and screenings.

show abstract

Deep learning assessment of child gross-motor

Cited by 7 publications

References 18 publications

Comprehensive Assessment and Early Prediction of Gross Motor Performance in Toddlers With Graph Convolutional Networks–Based Deep Learning: Development and Validation Study

Comprehensive Assessment and Early Prediction of Gross Motor Performance in Toddlers With Graph Convolutional Networks–Based Deep Learning: Development and Validation Study

The Classification of Movement in Infants for the Autonomous Monitoring of Neurological Development

Multiview child motor development dataset for AI-driven assessment of child development

Contact Info

Product

Resources

About