Page 36 - 2022-31-中国全科医学
P. 36
http://www.chinagp.net E-mail:zgqkyx@chinagp.net.cn ·3873·
To explore the feasibility of the Computer-aided Language Assessment System(CLAS)in the measurement of cognitive-
linguistic impairment. Methods Random sampling method was used to recruit 73 participants,among them 55(75.3%)were
stroke/brain injury patients〔with a baseline score of 10-20 on the Mini-Mental State Examination(MMSE)〕hospitalized in
Department of Rehabilitation Medicine,the First Hospital of Jinan University from March 2018 to March 2020,and the other
18(24.7%)were healthy volunteers(consisting of undergraduate medicalinterns from Jinan University,family members and
accompanying caregivers of the patients). The CLAS,Montreal Cognitive Assessment Scale(MoCA),MMSE and Aphasia
Battery of Chinese(ABC)were used to evaluate the linguistic and cognition functions of the participants. The Spearman
correlation was used to assess the correlation of the score of CLAS with that of MoCA and MMSE. A receiver operating characteristic
curve(ROC)of CLAS was plotted to estimate its diagnostic value for cognitive-linguistic impairment,with sensitivity,
specificity and accuracy being calculated as well. A satisfaction survey was conducted in 18 healthy volunteers to understand
their satisfaction with the use of the CLAS. Results The total CLAS score was positively correlated with that of MMSE,and
MoCA(r s =0.910,0.884,P<0.05).Compared with MoCA(total MoCA score <26)in combination with ABC in diagnosing
cognitive impairment,the CLAS had an AUC of 0.733〔95%CI(0.632,0.834),P<0.001〕in identifying cognitive-linguistic
impairment when the optimal cut-off value was set as 85 points,and the maximum Youden index was obtained,with 1.000
sensitivity,0.703 specificity,and 0.931(68/73)accuracy. The average satisfaction score of 18 healthy volunteers was(4.07±0.48),
indicating an overall satisfaction level of "satisfactory". Conclusion High participant satisfaction with the CLAS was obtained in
this study. And as the CLAS has proven to have good validity and diagnostic accuracy,as well as good performance in identifying
cognitive-linguistic impairment,it could be applied to the screening and identification of cognitive-linguistic impairment.
【Key words】 Computer-aided Language Assessment System;Language disorders;Cognition disorders;Screening;
Diagnosis;Feasibility;Satisfaction;Validity
语言障碍、认知障碍是脑卒中、脑创伤常见的合并 能技术建立智能化认知评估系统奠定研究基础。
症,不仅对患者生活质量造成严重影响,还给家庭和社 1 对象与方法
会带来极大的经济负担 [1-2] 。目前,传统神经心理学测 1.1 研究对象 采用随机抽样法,于 2018 年 3 月至
验仍是语言认知障碍诊断的重要手段 [3] ,其可分为两 2020 年 3 月选取 55 例入住于暨南大学第一附属医院康
大类:一类是结构复杂的测验,包括 Halstead-Reitan 神 复医学科的脑卒中 / 脑损伤患者,以及 18 例健康受试
经心理成套测验、汉语失语成套测验(ABC)等,这类 者为研究对象,健康受试者来源于暨南大学本科实习
测验的内容涵括语言、认知功能的各个亚项,但对检测 生、患者家属及陪护人员。患者纳入标准:(1)经 CT
人员的技术要求较高,受试者对其耐受性较差,故这类 或 MRI 证实及专科医生确诊患脑卒中 / 脑损伤;(2)
测验临床应用较为受限 [4] ;另一类是结构较为简单的 MMSE 基线得分为 10~20 分;(3)意识清楚,能够配
筛查测验,包括简易精神状态检查量表(MMSE)、蒙 合语言、认知功能评估;(4)视力或矫正视力、双耳
特利尔认知评估量表(MoCA)、简易智力状态评估量 听力良好;(5)生命体征平稳,无严重心、肝、肺、
表(Mini-Cog)、简式 Token 测试等,这类测验对语言 肾等重要脏器疾病,无心血管疾病或其他合并症;(6)
认知障碍的识别与诊断具有一定特异度和灵敏度,临床 对本研究知情同意,并自愿参加本研究。患者排除标准:
应用广泛,多以总分反映受试者的语言或认知障碍的严 (1)存在精神障碍或先天精神发育迟缓;(2)服用对
重程度,但无法反映受试者语言、认知功能各维度的变 认知功能有影响的药物;(3)有酒精依赖等不良嗜好;(4)
化特点,仅能用于初筛 [5] 。 参与研究过程中,因不良反应、病情变化,无法完成测试。
考虑到两类测验各有其优势,同时也各自存在一定 健康受试者纳入标准:(1)年龄为 18~70 岁;(2)受
的不足之处,为了提高医务人员识别语言认知障碍患者 教育年限 >9 年;(3)基线 MMSE 得分≥ 27 分。所有受
的效率和准确度,本课题组基于文献回顾、专家咨询结 试者均已签署知情同意书。本研究已通过暨南大学附属
果,并通过设置基于数学模型的抽题规则、答题规则及 第一医院伦理委员会审批(审批号:KY-2020-087)。
赋分规则,开发了一个语言认知评估系统 [6] ,该系统 1.2 研究方法
可分维度、分层次快速识别出存在语言认知障碍的受试 1.2.1 评估工具 采用语言认知评估系统、MoCA、
者。在前期系统构建研究基础上,本研究通过对语言认 MMSE、ABC 评价受试者的语言、认知功能状况。
知评估系统的效度进行检验,并对使用者的满意度进行 1.2.1.1 语言认知评估系统 由暨南大学陈卓铭教授团
调查,旨在进一步分析该系统用于语言认知功能评估及 队自主研发,包含语言、认知两个维度。认知维度由注
语言认知障碍识别与诊断的可行性,为个体化语言、认 意力、记忆力、计算能力、定向力、推理能力 5 个一级
知康复治疗的实施和效果评价提供依据,为基于人工智 指标组成,其中一级指标“记忆力”下设 2 个二级指标,