{"title":"通过手绘形状图像自动评估儿童精细运动的发展。","authors":"Nai-Hsuan Hwang, Sheng-Shan Chen, Tun-Wen Pai, Mary Hsin-Ju Ko, Ya-Lan Yu, Hui-Ju Chen","doi":"10.1016/j.pedneo.2025.04.001","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Fine motor skills are closely related to neurological maturity among children and serve as critical indicators of developmental status. However, clinical assessments require significant human and material resources. This study proposes an automated evaluation mechanism designed to assess the development of children's fine motor skills, offering a streamlined and resource-efficient approach to developmental assessment.</p><p><strong>Methods: </strong>The designed system evaluated the fine motor skills of 82 children aged 36-72 months. The children were asked to replicate five geometric shapes designed by the system: circles, crosses, squares, triangles, and rhombuses. The system automatically assessed 23 distinct features across the geometric shapes using an artificial intelligence-based model. A tailored scoring system then assigned a score that reflected the child's level of fine motor skill maturity.</p><p><strong>Results: </strong>A total of 81 replicated drawings from the children in the test group were collected and automatically assessed using the assessment mechanism developed in this study. The results demonstrated a strong positive correlation between fine motor skill maturity and practical age. Additionally, the scores identified children with delayed fine motor development. The macro F1-score and accuracy of the automatic classification models for the five different geometric shapes in the validation dataset were 0.9236 and 0.9268, respectively. These evaluation outcomes can effectively support early intervention and treatment efforts.</p><p><strong>Conclusion: </strong>The system's structured drawing tasks for varying geometric shapes have substantial practical value for the automatic assessment of children's fine motor maturity. The scoring method developed in this study provides a clear distinction between the different developmental stages of children's fine motor skills. This system offers an effective online tool for assessing fine motor development among children, thereby providing essential preliminary reference information for physicians in subsequent clinical evaluations and significantly reducing the burden on healthcare professionals.</p>","PeriodicalId":56095,"journal":{"name":"Pediatrics and Neonatology","volume":" ","pages":""},"PeriodicalIF":2.3000,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Automatic assessment of fine motor development in children through hand-drawn shape images.\",\"authors\":\"Nai-Hsuan Hwang, Sheng-Shan Chen, Tun-Wen Pai, Mary Hsin-Ju Ko, Ya-Lan Yu, Hui-Ju Chen\",\"doi\":\"10.1016/j.pedneo.2025.04.001\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Fine motor skills are closely related to neurological maturity among children and serve as critical indicators of developmental status. However, clinical assessments require significant human and material resources. This study proposes an automated evaluation mechanism designed to assess the development of children's fine motor skills, offering a streamlined and resource-efficient approach to developmental assessment.</p><p><strong>Methods: </strong>The designed system evaluated the fine motor skills of 82 children aged 36-72 months. The children were asked to replicate five geometric shapes designed by the system: circles, crosses, squares, triangles, and rhombuses. The system automatically assessed 23 distinct features across the geometric shapes using an artificial intelligence-based model. A tailored scoring system then assigned a score that reflected the child's level of fine motor skill maturity.</p><p><strong>Results: </strong>A total of 81 replicated drawings from the children in the test group were collected and automatically assessed using the assessment mechanism developed in this study. The results demonstrated a strong positive correlation between fine motor skill maturity and practical age. Additionally, the scores identified children with delayed fine motor development. The macro F1-score and accuracy of the automatic classification models for the five different geometric shapes in the validation dataset were 0.9236 and 0.9268, respectively. These evaluation outcomes can effectively support early intervention and treatment efforts.</p><p><strong>Conclusion: </strong>The system's structured drawing tasks for varying geometric shapes have substantial practical value for the automatic assessment of children's fine motor maturity. The scoring method developed in this study provides a clear distinction between the different developmental stages of children's fine motor skills. This system offers an effective online tool for assessing fine motor development among children, thereby providing essential preliminary reference information for physicians in subsequent clinical evaluations and significantly reducing the burden on healthcare professionals.</p>\",\"PeriodicalId\":56095,\"journal\":{\"name\":\"Pediatrics and Neonatology\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2025-05-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Pediatrics and Neonatology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1016/j.pedneo.2025.04.001\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"PEDIATRICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pediatrics and Neonatology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.pedneo.2025.04.001","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PEDIATRICS","Score":null,"Total":0}
Automatic assessment of fine motor development in children through hand-drawn shape images.
Background: Fine motor skills are closely related to neurological maturity among children and serve as critical indicators of developmental status. However, clinical assessments require significant human and material resources. This study proposes an automated evaluation mechanism designed to assess the development of children's fine motor skills, offering a streamlined and resource-efficient approach to developmental assessment.
Methods: The designed system evaluated the fine motor skills of 82 children aged 36-72 months. The children were asked to replicate five geometric shapes designed by the system: circles, crosses, squares, triangles, and rhombuses. The system automatically assessed 23 distinct features across the geometric shapes using an artificial intelligence-based model. A tailored scoring system then assigned a score that reflected the child's level of fine motor skill maturity.
Results: A total of 81 replicated drawings from the children in the test group were collected and automatically assessed using the assessment mechanism developed in this study. The results demonstrated a strong positive correlation between fine motor skill maturity and practical age. Additionally, the scores identified children with delayed fine motor development. The macro F1-score and accuracy of the automatic classification models for the five different geometric shapes in the validation dataset were 0.9236 and 0.9268, respectively. These evaluation outcomes can effectively support early intervention and treatment efforts.
Conclusion: The system's structured drawing tasks for varying geometric shapes have substantial practical value for the automatic assessment of children's fine motor maturity. The scoring method developed in this study provides a clear distinction between the different developmental stages of children's fine motor skills. This system offers an effective online tool for assessing fine motor development among children, thereby providing essential preliminary reference information for physicians in subsequent clinical evaluations and significantly reducing the burden on healthcare professionals.
期刊介绍:
Pediatrics and Neonatology is the official peer-reviewed publication of the Taiwan Pediatric Association and The Society of Neonatology ROC, and is indexed in EMBASE and SCOPUS. Articles on clinical and laboratory research in pediatrics and related fields are eligible for consideration.