Using a coloring activity to identify children’s development of visual–motor integration: an application of artificial intelligence

Visual–motor integration (VMI) is an important indicator in children with learning disabilities. We aimed to use performance in a coloring activity to identify children’s VMI developmental status. A sample of 505 preschool children (mean = 57.64, SD = 11.10) were recruited. Among them, data from 404 and 101 children were used as the training and testing data, respectively. The Beery–Buktenica Developmental Test of Visual–motor Integration, fourth Edition, (VMI-4) was used as an indicator for the model of artificial intelligence (AI). The total scores of the VMI-4 were calculated, and then based on the children’s age, the total scores were transferred into standard scores and the developmental status of visual–motor integration. The AI model comprised a regression model and classification model to predict the developmental status rated by the VMI-4. In the training data, we found that the AI model comprising the support vector machine (SVM) regression model and eXtreme Gradient Boostin (XGBoost) classification model exhibited the best performance (accuracy: 86.2%; sensitivity: 84.7%; and specificity, 85.4%). The results of the trained AI model on the testing data indicated good performance, with accuracy, sensitivity, and specificity of 80.20%, 73.68%, and 81.71%, respectively. Combining the coloring activity with the AI technique has great potential as a screening tool to identify children’s VMI developmental status.

视动整合能力（Visual–motor integration, VMI）是学习障碍儿童的重要评估指标。本研究旨在通过儿童涂色活动的表现，识别其视动整合发育状态。本研究共招募505名学龄前儿童，其平均年龄为57.64，标准差为11.10；其中404名儿童的数据用作训练集，剩余101名儿童的数据用作测试集。本研究采用第四版毕-布视动整合发育测验（Beery–Buktenica Developmental Test of Visual–motor Integration, fourth Edition, VMI-4）作为人工智能（Artificial Intelligence, AI）模型的金标准评估指标：研究人员首先计算VMI-4的总得分，随后结合儿童年龄将总得分转换为标准得分，并据此确定其视动整合发育状态。本研究所用的AI模型包含回归模型与分类模型，用于预测VMI-4评定的视动整合发育状态。在训练集上，本研究发现结合支持向量机（Support Vector Machine, SVM）回归模型与极端梯度提升（eXtreme Gradient Boosting, XGBoost）分类模型的AI模型表现最优，其准确率达86.2%、灵敏度为84.7%、特异度为85.4%。经训练的AI模型在测试集上同样表现良好，准确率、灵敏度与特异度分别为80.20%、73.68%与81.71%。将涂色活动与AI技术相结合，有望成为识别儿童视动整合发育状态的有效筛查工具。