CAJ | 학술논문

目的：近年来多元模式分析（ multivariate pattern analysis ， MVPA）方法的出现被认为是可以对各种神经精神疾病进行自动化识别的很有前途的工具，支持向量机（ support vector machine ， SVM）则是一种最广泛使用的MVPA方法。文中采用SVM分类器对遗忘型轻度认知障碍（ amnestic mild cognitive impairment ， aMCI）患者和无记忆障碍及其他相关疾病者进行MVPA研究，旨在构建具有较高判别能力的个体诊断模型，并从多变量分析的角度来解析aMCI患者的灰质损伤模式。方法采用3．0T磁共振对51例aMCI患者和68例正常对照者进行高分辨率三维T1-weighted扫描，为每个受试者计算灰质体积图谱，该图谱用于之后的判别分析。使用特征选择方法去除冗余信息后训练SVM分类器，使用留一交叉验证估计分类器的性能，最后识别出最有判别能力的灰质模式。结果该方法的分类准确率为83．19％，敏感性为76．47％，特异性为88．24％，接收者操作特性曲线下的面积是0．8368。对分类贡献最大的灰质区域包括双侧海马旁回、双侧海马、双侧杏仁核、双侧丘脑、右侧扣带回、右侧楔前叶、左侧尾状核、左侧颞上回、左侧颞中回、左侧岛叶以及左侧眶额皮层。结论构建的分类模型对aMCI患者具有较好的识别能力，可显示aMCI患者全脑灰质萎缩情况，对临床早期诊断aMCI患者有重要意义。
목적：근년래다원모식분석（ multivariate pattern analysis ， MVPA）방법적출현피인위시가이대각충신경정신질병진행자동화식별적흔유전도적공구，지지향량궤（ support vector machine ， SVM）칙시일충최엄범사용적MVPA방법。문중채용SVM분류기대유망형경도인지장애（ amnestic mild cognitive impairment ， aMCI）환자화무기억장애급기타상관질병자진행MVPA연구，지재구건구유교고판별능력적개체진단모형，병종다변량분석적각도래해석aMCI환자적회질손상모식。방법채용3．0T자공진대51례aMCI환자화68례정상대조자진행고분변솔삼유T1-weighted소묘，위매개수시자계산회질체적도보，해도보용우지후적판별분석。사용특정선택방법거제용여신식후훈련SVM분류기，사용류일교차험증고계분류기적성능，최후식별출최유판별능력적회질모식。결과해방법적분류준학솔위83．19％，민감성위76．47％，특이성위88．24％，접수자조작특성곡선하적면적시0．8368。대분류공헌최대적회질구역포괄쌍측해마방회、쌍측해마、쌍측행인핵、쌍측구뇌、우측구대회、우측설전협、좌측미상핵、좌측섭상회、좌측섭중회、좌측도협이급좌측광액피층。결론구건적분류모형대aMCI환자구유교호적식별능력，가현시aMCI환자전뇌회질위축정황，대림상조기진단aMCI환자유중요의의。
Objective In recent years , multivariate pattern analysis ( MVPA) method was proposed and considered to be a promising tool for automated identification of various neuropsychiatric populations .Support vector machine ( SVM) is one of the most widely used methods of MVPA .Using SVM classifier for MVPA of amnestic mild cognitive impairment (aMCI) and normal control (NC) group, the present study aims to build an individual diagnostic model with significant discriminative power and investigate the gray matter abnor-malities of aMCI patients . Methods Fifty-one aMCI patients and 68 normal controls were scanned on the 3-Tesla magnetic resonance imaging (MRI) for high-resolution T1-weighted images.Gray matter volume map was calculated for each subject and used as features for subsequent discriminative analysis .We first applied feature selection to remove redundant information and reduce feature dimension , and then trained an SVM classifier . Leave-one-out cross validation ( LOOCV) was used to estimate the performance of the classifier , and finally the most discriminative features were identified . Results The proposed classifier achieved a classification accuracy of 83.19%with a sensitivity of 76.47%and a specificity of 88.24%.In ad-dition, the area under the receiver operating characteristic (ROC) curve was 0.8368.Further analysis revealed that the most discrimi-native features for classification included bilateral parahippocampal gyri , bilateral hippocampi , bilateral amygdala , bilateral thalamus , right cingulate , right precuneus , left caudate , left superior temporal gyrus , left middle temporal gyrus , left insula and left orbitofrontal cortex. Conclusion The proposed classification model has achieved significant accuracy for aMCI prediction , and it also displayed the whole brain gray matter atrophy pattern in aMCI patients .It suggests that the proposed method may have important implications for early clinical diagnosis of aMCI patients .