Wang Jie, Wang Zhuo, Liu Ning, Liu Caiyan, Mao Chenhui, Dong Liling, Li Jie, Huang Xinying, Lei Dan, Chu Shanshan, Wang Jianyong, Gao Jing
Department of Neurology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, China.
Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China.
J Pers Med. 2022 Jan 4;12(1):37. doi: 10.3390/jpm12010037.
Mini-Mental State Examination (MMSE) is the most widely used tool in cognitive screening. Some individuals with normal MMSE scores have extensive cognitive impairment. Systematic neuropsychological assessment should be performed in these patients. This study aimed to optimize the systematic neuropsychological test battery (NTB) by machine learning and develop new classification models for distinguishing mild cognitive impairment (MCI) and dementia among individuals with MMSE ≥ 26. 375 participants with MMSE ≥ 26 were assigned a diagnosis of cognitively unimpaired (CU) ( = 67), MCI ( = 174), or dementia ( = 134). We compared the performance of five machine learning algorithms, including logistic regression, decision tree, SVM, XGBoost, and random forest (RF), in identifying MCI and dementia. RF performed best in identifying MCI and dementia. Six neuropsychological subtests with high-importance features were selected to form a simplified NTB, and the test time was cut in half. The AUC of the RF model was 0.89 for distinguishing MCI from CU, and 0.84 for distinguishing dementia from nondementia. This simplified cognitive assessment model can be useful for the diagnosis of MCI and dementia in patients with normal MMSE. It not only optimizes the content of cognitive evaluation, but also improves diagnosis and reduces missed diagnosis.
简易精神状态检查表（MMSE）是认知筛查中使用最广泛的工具。一些MMSE评分正常的个体存在广泛的认知障碍。应对这些患者进行系统的神经心理学评估。本研究旨在通过机器学习优化系统神经心理测试组合（NTB），并开发新的分类模型，以区分MMSE≥26的个体中的轻度认知障碍（MCI）和痴呆症。375名MMSE≥26的参与者被诊断为认知未受损（CU）（=67）、MCI（=174）或痴呆症（=134）。我们比较了逻辑回归、决策树、支持向量机、XGBoost和随机森林（RF）这五种机器学习算法在识别MCI和痴呆症方面的表现。RF在识别MCI和痴呆症方面表现最佳。选择六个具有高重要性特征的神经心理子测试来形成简化的NTB，测试时间缩短了一半。RF模型区分MCI与CU的曲线下面积（AUC）为0.89，区分痴呆症与非痴呆症的AUC为0.84。这种简化的认知评估模型可用于MMSE正常的患者中MCI和痴呆症的诊断。它不仅优化了认知评估的内容，还改善了诊断并减少了漏诊。
