Department of Neuropsychiatry, Seoul National University Hospital, Seoul, Republic of Korea.
Department of Psychiatry, Seoul National University College of Medicine, 101 Daehak-no, Chongno-gu, Seoul, 03080, Republic of Korea.
Sci Rep. 2024 Aug 6;14(1):18186. doi: 10.1038/s41598-024-68586-2.
Patients with mental illnesses, particularly psychosis and obsessive‒compulsive disorder (OCD), frequently exhibit deficits in executive function and visuospatial memory. Traditional assessments, such as the Rey‒Osterrieth Complex Figure Test (RCFT), performed in clinical settings require time and effort. This study aimed to develop a deep learning model using the RCFT and based on eye tracking to detect impaired executive function during visuospatial memory encoding in patients with mental illnesses. In 96 patients with first-episode psychosis, 49 with clinical high risk for psychosis, 104 with OCD, and 159 healthy controls, eye movements were recorded during a 3-min RCFT figure memorization task, and organization and immediate recall scores were obtained. These scores, along with the fixation points indicating eye-focused locations in the figure, were used to train a Long Short-Term Memory + Attention model for detecting impaired executive function and visuospatial memory. The model distinguished between normal and impaired executive function, with an F score of 83.5%, and identified visuospatial memory deficits, with an F score of 80.7%, regardless of psychiatric diagnosis. These findings suggest that this eye tracking-based deep learning model can directly and rapidly identify impaired executive function during visuospatial memory encoding, with potential applications in various psychiatric and neurological disorders.
患有精神疾病的患者，特别是精神病和强迫症（OCD）患者，通常表现出执行功能和视空间记忆方面的缺陷。传统的评估方法，如临床环境中进行的 Rey-Osterrieth 复杂图形测试（RCFT），需要时间和精力。本研究旨在开发一种基于深度学习的模型，该模型使用 RCFT 和基于眼动追踪的方法，来检测精神疾病患者在视空间记忆编码过程中执行功能受损的情况。在 96 名首发精神病患者、49 名精神病高危患者、104 名强迫症患者和 159 名健康对照组中，在 3 分钟的 RCFT 图形记忆任务期间记录了眼动，并且获得了组织和即时回忆得分。这些分数以及表示在图形中眼睛注视位置的注视点被用于训练用于检测执行功能和视空间记忆受损的长短期记忆+注意力模型。该模型能够区分正常和受损的执行功能，F 分数为 83.5%，并且能够识别视空间记忆缺陷，F 分数为 80.7%，无论精神诊断如何。这些发现表明，这种基于眼动追踪的深度学习模型可以直接快速地识别视空间记忆编码过程中的执行功能受损，可能在各种精神和神经疾病中具有应用前景。
