Laura Manea

Optimal cut-off score for diagnosing depression with the Patient Health Questionnaire (PHQ-9): a meta-analysis

Background: The brief Patient Health Questionnaire (PHQ-9) is commonly used to screen for depression with 10 often recommended as the cut-off score. We summarized the psychometric properties of the PHQ-9 across a range of studies and cut-off scores to select the optimal cut-off for detecting depression. Methods: We searched Embase, MEDLINE and PsycINFO from 1999 to August 2010 for studies that reported the diagnostic accuracy of PHQ-9 to diagnose major depressive disorders. We calculated summary sensitivity, specificity, likelihood ratios and diagnostic odds ratios for detecting major depressive disorder at different cut-off scores and in different settings. We used random-effects bivariate meta-analysis at cutoff points between 7 and 15 to produce summary receiver operating characteristic curves. Results: We identified 18 validation studies (n = 7180) conducted in various clinical settings. Eleven studies provided details about the diagnostic properties of the questionnaire at more than one cut-off score (including 10), four studies reported a cut-off score of 10, and three studies reported cut-off scores other than 10. The pooled specificity results ranged from 0.73 (95% confidence interval [CI] 0.63–0.82) for a cut-off score of 7 to 0.96 (95% CI 0.94–0.97) for a cut-off score of 15. There was major variability in sensitivity for cut-off scores between 7 and 15. There were no substantial differences in the pooled sensitivity and specificity for a range of cut-off scores (8–11). Interpretation: The PHQ-9 was found to have acceptable diagnostic properties for detecting major depressive disorder for cut-off scores between 8 and 11. Authors of future validation studies should consistently report the outcomes for different cut-off scores.

A diagnostic meta-analysis of the Patient Health Questionnaire-9 (PHQ-9) algorithm scoring method as a screen for depression

BACKGROUND The depression module of the Patient Health Questionnaire-9 (PHQ-9) is a widely used depression screening instrument in nonpsychiatric settings. The PHQ-9 can be scored using different methods, including an algorithm based on Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition criteria and a cut-off based on summed-item scores. The algorithm was the originally proposed scoring method to screen for depression. We summarized the diagnostic test accuracy of the PHQ-9 using the algorithm scoring method across a range of validation studies and compared the diagnostic properties of the PHQ-9 using the algorithm and summed scoring method at the proposed cut-off point of 10. METHODS We performed a systematic review of diagnostic accuracy studies of the PHQ-9 using the algorithm scoring method to detect major depressive disorder (MDD). We used meta-analytic methods to calculate summary sensitivity, specificity, likelihood ratios and diagnostic odds ratios for diagnosing MDD of the PHQ-9 using algorithm scoring method. In studies that reported both scoring methods (algorithm and summed-item scoring at proposed cut-off point of ≥10), we compared the diagnostic properties of the PHQ-9 using these methods. RESULTS We found 27 validation studies that validated the algorithm scoring method of the PHQ-9 in various settings. There was substantial heterogeneity across studies, which makes the pooled results difficult to interpret. In general, sensitivity was low whereas specificity was good. Thirteen studies reported the diagnostic properties of the PHQ-9 for both scoring methods. Pooled sensitivity for algorithm scoring method was lower while specificities were good for both scoring methods. Heterogeneity was consistently high; therefore, caution should be used when interpreting these results. INTERPRETATION This review shows that, if the algorithm scoring method is used, the PHQ-9 has a low sensitivity for detecting MDD. This could be due to the rating scale categories of the measure, higher specificity or other factors that warrant further research. The summed-item score method at proposed cut-off point of ≥10 has better diagnostic performance for screening purposes or where a high sensitivity is needed.

Screening for anxiety disorders with the GAD-7 and GAD-2: a systematic review and diagnostic metaanalysis

OBJECTIVE To systematically review the accuracy of the GAD-7 and GAD-2 questionnaires for identifying anxiety disorders. METHODS A systematic review of the literature was conducted to identify studies that validated the GAD-7 or GAD-2 against a recognized gold standard diagnosis. Pooled estimates of diagnostic test accuracy were produced using random-effects bivariate metaanalysis. Heterogeneity was explored using the I(2) statistic. RESULTS A total of 12 samples were identified involving 5223 participants; 11 samples provided data on the accuracy of the GAD-7 for identifying generalized anxiety disorder (GAD). Pooled sensitivity and specificity values appeared acceptable at a cutoff point of 8 [sensitivity: 0.83 (95% CI 0.71-0.91), specificity: 0.84 (95% CI 0.70-0.92)] although cutoff scores 7-10 also had similar pooled estimates of sensitivity/specificity. Six samples provided data on the accuracy of the GAD-2 for identifying GAD. Pooled sensitivity and specificity values appeared acceptable at a cutoff of 3 [sensitivity: 0.76 (95% CI 0.55-0.89), specificity: 0.81 (95% CI 0.60-0.92)]. Four studies looked at the accuracy of the questionnaires for identifying any anxiety disorder. CONCLUSIONS The GAD-7 had acceptable properties for identifying GAD at cutoff scores 7-10. The GAD-2 had acceptable properties for identifying GAD at a cutoff score of 3. Further validation studies are needed.

Screening and case finding for major depressive disorder using the Patient Health Questionnaire (PHQ-9): a meta-analysis

OBJECTIVE The Patient Health Questionnaire (PHQ-9) is a widely used screening tool for major depressive disorder (MDD), although there is debate surrounding its diagnostic properties. For the PHQ-9, we aimed to: 1. Establish the diagnostic performance at the standard cutoff point (10). 2. Compare the diagnostic performance at the standard cutoff point in different clinical settings. 3. Assess whether there is selective reporting of cutoff points other than 10. METHODS We searched three databases - Embase, MEDLINE and PSYCHInfo - and performed a reverse citation search in Web of Science. We selected for inclusion studies of any design that assessed the PHQ-9 in adult populations against recognized gold-standard instruments for the diagnosis of either Diagnostic and Statistical Manual of Mental Disorders or International Classification of Diseases criteria for major depression. Included studies had to report sufficient information to calculate 2*2 contingency tables. Data extraction and synthesis were performed independently by two researchers. For the included studies, we calculated pooled sensitivity, pooled specificity, positive likelihood, negative likelihood ratio and diagnostic odds ratio for cutoff points 7 to 15. RESULTS Thirty-six studies (21,292 patients) met inclusion criteria. Pooled sensitivity for cutoff point 10 was 0.78 [95% confidence interval (CI), 0.70-0.84], and pooled specificity was 0.87 (95% CI, 0.84-0.90). At this cutoff, the PHQ-9 is a better screener in primary care than secondary care settings. No conclusions could be drawn at cutoff points other than 10 due to selective reporting of data. CONCLUSIONS For MDD, the PHQ-9 has acceptable diagnostic properties at cutoff point 10 in different settings. We recommend that future studies report the full range of cutoff points to allow exploration of optimal cutoff points in different settings.

The diagnostic accuracy of brief versions of the Geriatric Depression Scale: a systematic review and meta‐analysis

Depression in older adults is often under recognised despite it being the most common mental health illness in this age group. An increasing older adult population highlights the need for improved diagnostic rates. Brief versions (15 items or less) of the Geriatric Depression Scale (GDS), which are suitable for busy clinical practice, could improve detection rates.

Diagnostic accuracy of the Whooley questions for the identification of depression: a diagnostic meta-analysis

Objectives To determine the diagnostic accuracy of the Whooley questions in the identification of depression; and, to examine the effect of an additional ‘help’ question. Design Systematic review with random effects bivariate diagnostic meta-analysis. Search strategies included electronic databases, examination of reference lists, and forward citation searches. Inclusion criteria Studies were included that provided sufficient data to calculate the diagnostic accuracy of the Whooley questions against a gold standard diagnosis of major depression. Data extraction Descriptive information, methodological quality criteria, and 2×2 contingency tables were extracted. Results Ten studies met inclusion criteria. Pooled sensitivity was 0.95 (95% CI 0.88 to 0.97) and pooled specificity was 0.65 (95% CI 0.56 to 0.74). Heterogeneity was low (I2=24.1%). Primary care subgroup analysis gave broadly similar results. Four of the ten studies provided information on the effect of an additional help question. The addition of this question did not consistently improve specificity while retaining high sensitivity as reported in the original validation study. Conclusions The two-item Whooley questions have high sensitivity and modest specificity in the detection of depression. The current evidence for the use of an additional help question is not consistent and there is, as yet, insufficient data to recommend its use for screening or case finding. Trial registration number CRD42014009695.

Identifying depression with the PHQ-2: A diagnostic meta-analysis.

BACKGROUND There is interest in the use of very brief instruments to identify depression because of the advantages they offer in busy clinical settings. The PHQ-2, consisting of two questions relating to core symptoms of depression (low mood and loss of interest or pleasure), is one such instrument. METHOD A systematic review was conducted to identify studies that had assessed the diagnostic performance of the PHQ-2 to detect major depression. Embase, MEDLINE, PsychINFO and grey literature databases were searched. Reference lists of included studies and previous relevant reviews were also examined. Studies were included that used the standard scoring system of the PHQ-2, assessed its performance against a gold-standard diagnostic interview and reported data on its performance at the recommended (≥3) or an alternative cut-off point (≥2). After assessing heterogeneity, where appropriate, data from studies were combined using bivariate diagnostic meta-analysis to derive sensitivity, specificity, likelihood ratios and diagnostic odds ratios. RESULTS 21 studies met inclusion criteria totalling N=11,175 people out of which 1529 had major depressive disorder according to a gold standard. 19 of the 21 included studies reported data for a cut-off point of ≥3. Pooled sensitivity was 0.76 (95% CI =0.68-0.82), pooled specificity was 0.87 (95% CI =0.82-0.90). However there was substantial heterogeneity at this cut-off (I(2)=81.8%). 17 studies reported data on the performance of the measure at cut-off point ≥2. Heterogeneity was I(2)=43.2% pooled sensitivity at this cut-off point was 0.91 (95% CI =0.85-0.94), and pooled specificity was 0.70 (95% CI =0.64-0.76). CONCLUSION The generally lower sensitivity of the PHQ-2 at cut-off ≥3 than the original validation study (0.83) suggests that ≥2 may be preferable if clinicians want to ensure that few cases of depression are missed. However, in situations in which the prevalence of depression is low, this may result in an unacceptably high false-positive rate because of the associated modest specificity. These results, however, need to be interpreted with caution given the possibility of selectively reported cut-offs.

Screening for psychological and mental health difficulties in young people who offend: a systematic review and decision model

BACKGROUND There is policy interest in the screening and treatment of mental health problems in young people who offend, but the value of such screening is not yet known. OBJECTIVES To assess the diagnostic test accuracy of screening measures for mental health problems in young people who offend; to evaluate the clinical effectiveness and cost-effectiveness of screening and treatment; to model estimates of cost; to assess the evidence base for screening against UK National Screening Committee criteria; and to identify future research priorities. DATA SOURCES In total, 25 electronic databases including MEDLINE, PsycINFO, EMBASE and The Cochrane Library were searched from inception until April 2011. Reverse citation searches of included studies were undertaken and reference list of included studies were examined. REVIEW METHODS Two reviewers independently examined titles and abstracts and extracted data from included studies using a standardised form. The inclusion criteria for the review were (1) population - young offenders (aged 10-21 years); (2) intervention/instrument - screening instruments for mental health problems, implementation of a screening programme or a psychological or pharmacological intervention as part of a clinical trial; (3) comparator - for diagnostic test accuracy studies, any standardised diagnostic interview; for trials, any comparator; (4) outcomes - details of diagnostic test accuracy, mental health outcomes over the short or longer term or measurement of cost data; and (5) study design - for diagnostic test accuracy studies, any design; for screening programmes, randomised controlled trials or controlled trials; for clinical effectiveness studies, randomised controlled trials; for economic studies, economic evaluations of screening strategies or interventions. RESULTS Of 13,580 studies identified, nine, including eight independent samples, met the inclusion criteria for the diagnostic test accuracy and validity of screening measures review. Screening accuracy was typically modest. No studies examined the clinical effectiveness of screening, although 10 studies were identified that examined the clinical effectiveness of interventions for mental health problems. There were too few studies to make firm conclusions about the clinical effectiveness of treatments in this population. No studies met the inclusion criteria for the assessment of the cost-effectiveness of screening or treatment. An exemplar decision model was developed for depression, which identified a number of the likely key drivers of uncertainty, including the prevalence of unidentified mental health problems, the severity of mental health problems and their relationship to generic measures of outcome and the impact of treatment on recidivism. The information evaluated as part of the review was relevant to five of the UK National Screening Committee criteria. On the basis of the above results, none of the five criteria was met. LIMITATIONS The conclusions of the review are based on limited evidence. Conclusions are tentative and the decision model should be treated as an exemplar. CONCLUSIONS Evidence on the clinical effectiveness and cost-effectiveness of screening for mental health problems in young people who offend is currently lacking. Future research should consider feasibility trials of clinical interventions to establish important parameters ahead of conducting definitive trials. Future diagnostic studies should compare the diagnostic test accuracy of a range of screening instruments, including those recommended for use in the UK in this population. These studies should be designed to reduce the decision uncertainty identified by the exemplar decision model. REGISTRATION This study is registered as PROSPERO CRD42011001466. FUNDING The National Institute for Health Research Health Technology Assessment programme.

Are there researcher allegiance effects in diagnostic validation studies of the PHQ-9? A systematic review and meta-analysis

Objectives To investigate whether an authorship effect is found that leads to better performance in studies conducted by the original developers of the Patient Health Questionnaire (PHQ-9) (allegiant studies). Design Systematic review with random effects bivariate diagnostic meta-analysis. Search strategies included electronic databases, examination of reference lists and forward citation searches. Inclusion criteria Included studies provided sufficient data to calculate the diagnostic accuracy of the PHQ-9 against a gold standard diagnosis of major depression using the algorithm or the summed item scoring method at cut-off point 10. Data extraction Descriptive information, methodological quality criteria and 2×2 contingency tables. Results Seven allegiant and 20 independent studies reported the diagnostic performance of the PHQ-9 using the algorithm scoring method. Pooled diagnostic OR (DOR) for the allegiant group was 64.40, and 15.05 for non-allegiant studies group. The allegiance status was a significant predictor of DOR variation (p<0.0001). Five allegiant studies and 26 non-allegiant studies reported the performance of the PHQ-9 at recommended cut-off point of 10. Pooled DOR for the allegiant group was 49.31, and 24.96 for the non-allegiant studies. The allegiance status was a significant predictor of DOR variation (p=0.015). Some potential alternative explanations for the observed authorship effect including differences in study characteristics and quality were found, although it is not clear how some of them account for the observed differences. Conclusions Allegiant studies reported better performance of the PHQ-9. Allegiance status was predictive of variation in the DOR. Based on the observed differences between independent and non-independent studies, we were unable to conclude or exclude that allegiance effects are present in studies examining the diagnostic performance of the PHQ-9. This study highlights the need for future meta-analyses of diagnostic validation studies of psychological measures to evaluate the impact of researcher allegiance in the primary studies.

The Diagnostic Accuracy of Brief and Ultra-brief Versions of the Geriatric Depression Scale: a Meta-analysis

Introduction Depression in older adults is often under-diagnosed and consequently under-treated, despite association with higher rates of morbidity and mortality, increased healthcare utilisation and greater economic cost compared to younger populations. Better identification will be imperative in the future because of the estimated growth in the older adult population. Screening could improve identification; a well-known screening tool tis the Geriatric Depression Scale (GDS). Objective To evaluate the diagnostic accuracy of the brief GDS-15 and ultra-brief versions in the detection of major depression. Method Seven electronic databases and unpublished literature were searched, using predefined criteria, from 1982 to April 2014. Primary study quality was assessed using the QUADAS-2. Pooled diagnostic performance data was calculated using bivariate meta-analysis. Subgroup and sensitivity analyses were pre-planned. Heterogeneity was explored through meta-regression. Results Of 6635 records identified 32 studies were included. Meta-analyses were possible for the GDS-1, GDS-4 and GDS-15. For the GDS-15, at the recommended cut-off score of 5, the diagnostic odds ratio was highest in a community setting and for older adults aged ≤69 years. A cut-off score of 4, however, provided better diagnostic accuracy. Diagnostic data was less favourable when depression prevalence was ≥10%. Better diagnostic properties were found in non-Western countries. Meta-regression revealed country and language were predictive of diagnostic accuracy. Conclusions Further research is needed to explore diagnostic properties of ultra-brief GDS versions. GDS-15 findings suggest selective reporting of cut-off scores, which requires cautious interpretation and a need for greater methodological rigor in primary studies.