Department of Physical Medicine and Rehabilitation, Ton-Yen General Hospital, Hsinchu, Taiwan.
Department of Early Childhood Education and Care, College of Human Ecology, Minghsin University of Science and Technology, Hsinchu, Taiwan.
J Neurodev Disord. 2024 Nov 11;16(1):62. doi: 10.1186/s11689-024-09578-1.
A multi-method, multi-informant approach is crucial for evaluating attention-deficit/hyperactivity disorders (ADHD) in preschool children due to the diagnostic complexities and challenges at this developmental stage. However, most artificial intelligence (AI) studies on the automated detection of ADHD have relied on using a single datatype. This study aims to develop a reliable multimodal AI-detection system to facilitate the diagnosis of ADHD in young children.
78 young children were recruited, including 43 diagnosed with ADHD (mean age: 68.07 ± 6.19 months) and 35 with typical development (mean age: 67.40 ± 5.44 months). Machine learning and deep learning methods were adopted to develop three individual predictive models using electroencephalography (EEG) data recorded with a wearable wireless device, scores from the computerized attention assessment via Conners' Kiddie Continuous Performance Test Second Edition (K-CPT-2), and ratings from ADHD-related symptom scales. Finally, these models were combined to form a single ensemble model.
The ensemble model achieved an accuracy of 0.974. While individual modality provided the optimal classification with an accuracy rate of 0.909, 0.922, and 0.950 using the ADHD-related symptom rating scale, the K-CPT-2 score, and the EEG measure, respectively. Moreover, the findings suggest that teacher ratings, K-CPT-2 reaction time, and occipital high-frequency EEG band power values are significant features in identifying young children with ADHD.
This study addresses three common issues in ADHD-related AI research: the utility of wearable technologies, integrating databases from diverse ADHD diagnostic instruments, and appropriately interpreting the models. This established multimodal system is potentially reliable and practical for distinguishing ADHD from TD, thus further facilitating the clinical diagnosis of ADHD in preschool young children.
由于学龄前儿童的诊断复杂性和挑战，多方法、多信息源方法对于评估注意力缺陷/多动障碍（ADHD）至关重要。然而，大多数关于 ADHD 自动检测的人工智能 (AI) 研究都依赖于使用单一数据类型。本研究旨在开发一种可靠的多模态 AI 检测系统，以促进对幼儿 ADHD 的诊断。
招募了 78 名幼儿，包括 43 名被诊断为 ADHD（平均年龄：68.07±6.19 个月）和 35 名具有典型发育的幼儿（平均年龄：67.40±5.44 个月）。采用机器学习和深度学习方法，使用可穿戴无线设备记录的脑电图 (EEG) 数据、康纳斯儿童连续操作测试第二版 (K-CPT-2) 的计算机注意力评估得分以及 ADHD 相关症状量表的评分，开发了三个独立的预测模型。最后，将这些模型组合形成一个单一的集成模型。
集成模型的准确率为 0.974。虽然个别模态通过 ADHD 相关症状评分量表、K-CPT-2 得分和 EEG 测量提供了最佳分类，准确率分别为 0.909、0.922 和 0.950，但个体模式提供了最佳分类。此外，研究结果表明，教师评分、K-CPT-2 反应时间和枕部高频 EEG 波段功率值是识别患有 ADHD 的幼儿的重要特征。
本研究解决了 ADHD 相关 AI 研究中的三个常见问题：可穿戴技术的实用性、整合来自不同 ADHD 诊断工具的数据库以及适当解释模型。该多模态系统具有潜在的可靠性和实用性，可用于区分 ADHD 与 TD，从而进一步促进幼儿 ADHD 的临床诊断。
