Using the GHQ-12 to screen for mental health problems among primary care patients: psychometrics and practical considerations

Background This study explores the factor structure of the Indonesian version of the GHQ-12 based on several theoretical perspectives and determines the threshold for optimum sensitivity and specificity. Through a focus group discussion, we evaluate the practicality of the GHQ-12 as a screening tool for mental health problems among adult primary care patients in Indonesia. Methods This is a prospective study exploring the construct validity, criterion validity and reliability of the GHQ-12, conducted with 676 primary care patients attending 28 primary care clinics randomised for participation in the study. Participants' GHQ-12 scores were compared with their psychiatric diagnosis based on face-to-face clinical interviews with GPs using the CIS-R. Exploratory and Confirmatory Factor Analyses determined the construct validity of the GHQ-12 in this population. The appropriate threshold score of the GHQ-12 as a screening tool in primary care was determined using the receiver operating curve. Prior to data collection, a focus group discussion was held with research assistants who piloted the screening procedure, GPs, and a psychiatrist, to evaluate the practicality of embedding screening within the routine clinic procedures. Results Of all primary care patients attending the clinics during the recruitment period, 26.7% agreed to participate (676/2532 consecutive patients approached). Their median age was 46 (range 18-82 years); 67% were women. The median GHQ-12 score for our primary care sample was 2, with an interquartile range of 4. The internal consistency of the GHQ-12 was good (Cronbach's alpha = 0.76). Four factor structures were fitted on the data. The GHQ-12 was found to best fit a one-dimensional model, when response bias is taken into consideration. Results from the ROC curve indicated that the GHQ-12 is 'fairly accurate' when discriminating primary care patients with indication of mental disorders from those without, with average AUC of 0.78. The optimal threshold of the GHQ-12 was either 1/2 or 2/3 point depending on the intended utility, with a Positive Predictive Value of 0.68 to 0.73 respectively. The screening procedure was successfully embedded into routine patient flow in the 28 clinics. Conclusions The Indonesian version of the GHQ-12 could be used to screen primary care patients at high risk of mental disorders although with significant false positives if reasonable sensitivity is to be achieved. While it involves additional administrative burden, screening may help identify future users of mental health services in primary care that the country is currently expanding.