Mari J J, Williams P
Psychol Med. 1985 Aug;15(3):651-9. doi: 10.1017/s0033291700031500.
The General Health Questionnaire (GHQ-12) (Goldberg, 1972) and the Self Report Questionnaire (SRQ-20) (Harding et al. 1980) were simultaneously validated against the criterion of the Clinical Interview Schedule (CIS) (Goldberg et al. 1970) in three primary care clinics in the city of Sao Paulo, Brazil. A comparison between the two screening instruments was carried out. The product-moment correlation between the two sets of scores was +0.72, and the validation coefficients for the GHQ-12 and the SRQ-20 were respectively: sensitivity 85% and 83%; specificity 79% and 80%; overall misclassification rate 18% and 19%. The two screening instruments were further compared by the application of Relative Operating Characteristic (ROC) analysis and, again, were found to be very similar in performance. The area under the ROC curve was 0.87 for the GHQ and 0.90 for the SRQ-20 (Z = 0.92, NS). Both psychiatric screening instruments were therefore found to be acceptably valid when assessed against the CIS in three primary care settings in Brazil. The application of ROC analysis to studies of this kind was feasible and straightforward. It was found to be superior to the conventional method of presentation of validity data. It is recommended that the application of ROC analysis to psychiatric screening studies be further utilized and explored.
在巴西圣保罗市的三家初级保健诊所，针对临床访谈表（CIS）（戈德堡等人，1970年）这一标准，同时对一般健康问卷（GHQ - 12）（戈德堡，1972年）和自评问卷（SRQ - 20）（哈丁等人，1980年）进行了验证。对这两种筛查工具进行了比较。两组分数之间的积差相关为 +0.72，GHQ - 12和SRQ - 20的验证系数分别为：灵敏度85%和83%；特异度79%和80%；总体错误分类率18%和19%。通过应用相对操作特征（ROC）分析对这两种筛查工具进行了进一步比较，结果再次发现它们在性能上非常相似。GHQ的ROC曲线下面积为0.87，SRQ - 20为0.90（Z = 0.92，无显著性差异）。因此，在巴西的三个初级保健环境中，以CIS为对照评估时，这两种精神科筛查工具都被认为具有可接受的效度。将ROC分析应用于这类研究是可行且直接的。它被发现优于呈现效度数据的传统方法。建议进一步利用和探索将ROC分析应用于精神科筛查研究。
