Department of Occupational Therapy, College of Medical Science, Soonchunhyang University, Room 1401, College of Medical Science, 22 Soonchunhyang-ro, Shinchang-myeon, Asan, Chungcheongnam-do, 31538, Republic of Korea.
BMC Psychiatry. 2024 Feb 27;24(1):166. doi: 10.1186/s12888-024-05622-5.
The Rey-Osterrieth Complex Figure Test (RCFT) is a tool to evaluate cognitive function. Despite its usefulness, its scoring criteria are as complicated as its figure, leading to a low reliability. Therefore, this study aimed to determine the feasibility of using the convolutional neural network (CNN) model based on the RCFT as a screening tool for mild cognitive impairment (MCI) and investigate the non-equivalence of sub-tasks of the RCFT.
A total of 354 RCFT images (copy and recall conditions) were obtained from 103 healthy controls (HCs) and 74 patients with amnestic MCI (a-MCI). The CNN model was trained to predict MCI based on the RCFT-copy and RCFT-recall images. To evaluate the CNN model's performance, accuracy, sensitivity, specificity, and F1-score were measured. To compare discriminative power, the area under the curve (AUC) was calculated by the receiver operating characteristic (ROC) curve analysis.
The CNN model based on the RCFT-recall was the most accurate in discriminating a-MCI (accuracy: RCFT-copy = 0.846, RCFT-recall = 0.872, MoCA-K = 0.818). Furthermore, the CNN model based on the RCFT could better discriminate MCI than the MoCA-K (AUC: RCFT-copy = 0.851, RCFT-recall = 0.88, MoCA-K = 0.848). The CNN model based on the RCFT-recall was superior to the RCFT-copy.
These findings suggest the feasibility of using the CNN model based on the RCFT as a surrogate for a conventional screening tool for a-MCI and demonstrate the superiority of the CNN model based on the RCFT-recall to the RCFT-copy.
瑞文氏渐进性智力测验（RCFT）是一种评估认知功能的工具。尽管它很有用，但它的评分标准和其图形一样复杂，导致可靠性较低。因此，本研究旨在确定基于 RCFT 的卷积神经网络（CNN）模型作为轻度认知障碍（MCI）筛查工具的可行性，并探讨 RCFT 子任务的非等效性。
共获得 103 名健康对照者（HCs）和 74 名遗忘型轻度认知障碍（a-MCI）患者的 354 张 RCFT 图像（复制和回忆条件）。基于 RCFT 复制和 RCFT 回忆图像训练 CNN 模型来预测 MCI。为了评估 CNN 模型的性能，测量了准确性、敏感性、特异性和 F1 分数。通过接收者操作特征（ROC）曲线分析计算曲线下面积（AUC）来比较判别能力。
RCFT 回忆的 CNN 模型在区分 a-MCI 方面最为准确（准确性：RCFT 复制=0.846，RCFT 回忆=0.872，MoCA-K=0.818）。此外，RCFT 基于的 CNN 模型比 MoCA-K 能更好地辨别 MCI（AUC：RCFT 复制=0.851，RCFT 回忆=0.88，MoCA-K=0.848）。RCFT 回忆的 CNN 模型优于 RCFT 复制。
这些发现表明，基于 RCFT 的 CNN 模型作为替代传统 a-MCI 筛查工具具有可行性，并证明了基于 RCFT 回忆的 CNN 模型优于 RCFT 复制。
