Detecting recurrent major depressive disorder within primary care rapidly and reliably using short questionnaire measures

Leveraging Longitudinal Lifelog Data Using Survival Models for Predicting Risk of Relapse among Patients with Depression in Remission

Managing depression relapse is a challenge given factors such as inconsistent follow-up and cumbersome psychological distress evaluation methods which leaves patients with a high risk of relapse to leave their symptoms untreated. In an attempt to bridge this gap, we proposed an approach on the use of personal longitudinal lifelog activity data gathered from individual smartphones of patients in remission and maintenance therapy (N=87) to predict their risk of depression relapse. Through the use of survival models, we modeled the activity data as covariates to predict survival curves to determine if patients are at risk of relapse. We compared three models: CoxPH, Random Survival Forests, and DeepSurv, and found that DeepSurv performed the best in terms of Concordance Index and Brier Score. Our results show the possibility of utilizing lifelog data as a means of predicting the onset of relapse and towards building eventual tools for a more coherent patient evaluation and intervention system.

The Patient Health Questionnaire depression screener in spinal cord injury

CONTEXT

Although depression is not inevitable following spinal cord injury/dysfunction (SCI/D), it can have a negative impact on rehabilitation. Evidence-based assessment of depression utilizing self-report instruments, such as the Patient Health Questionnaire-9 (PHQ-9), is considered good clinical practice. Although the PHQ-9 has been studied in individuals with SCI/D, little is known about the clinical utility of the Patient Health Questionnaire-2 (PHQ-2). Traditional cutoff scores for the PHQ-2 were examined to explore their operating characteristics as related to PHQ-9 results.

METHODS

Archival data were collected for 116 Veterans with SCI/D who completed the PHQ-2 and PHQ-9 as one component of their routine, comprehensive SCI annual evaluation at a Veterans Affairs Medical Center. Logistic regressions were performed to determine the impact of different cutoff scores for the PHQ-2 on the likelihood that participants would endorse clinically significant levels of depressive symptoms on the PHQ-9 (≥10).

RESULTS

Using a cutoff score of 3 or greater correctly classified 94.8% of the cases, outperforming the other cutoff scores. A cutoff score of 3 or greater had a sensitivity of 83.3% and specificity of 97.8%, and yielded a positive predictive value of 90.9% and a negative predictive value of 95.7%.

CONCLUSION

The PHQ-2 shows promise as a clinically useful screener in the community-residing SCI/D population. Findings regarding the presence of suicidal ideation emphasize the importance of routine screening for depressive symptomatology in the SCI/D population. Future research should investigate the role of the PHQ-2 in clinical decision-making and treatment monitoring.

A case control series for the effect of photobiomodulation in patients with low back pain and concurrent depression

Background and aims

To present incidental findings in patients with low back pain (LBP) who received photobiomodulation (PBM) administered to the back and thighs as an adjunct to physical therapy (PT) and then experienced improvement in concurrent depression.

Materials and methods

Five outpatients with LBP and concurrent self-reported depression were treated for LBP over five weeks with PT (5-sessions) and concurrent PBM (final 3-sessions), and retrospectively matched to five control patients treated with PT alone (5-sessions). The PBM device emitted light at 850nm and 660 nm with an irradiance of 100 mW/cm² and fluence of 3 J/cm² on 12 symmetrical posterior sites (thoracic, lumbar and thighs) for 30 sec/site.

Results

Both groups had non-significant differences in all baseline scores, except for higher functional status (ARGS) in the PBM-group (33.6 ± 12.2 vs.18.6 ± 3.6, t(8) = 2.638, p = 0.030). After treatment, the mean decrease in depression scores (OMSQ-12 item #6) was significantly larger in the PBM-group (43.0 ± 22.0 vs. 8.0 ± 5.7, t(8) = 3.449, p = 0.009). Improvement in functional status (ARGS) in the PBM-group was similar to that in the controls (42.0 ± 13.5 vs. 43.4 ± 11.1, t(8) = 0.179, p = 0.862), suggesting group differences in antidepressant effect were independent of functional status improvement.

Conclusions

This preliminary investigation suggests that an antidepressant effect may result from PBM to the back and thighs in patients with LBP and concurrent depression.

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.

Identifying key parent-reported symptoms for detecting depression in high risk adolescents

Adolescent offspring of depressed parents are at particularly heightened risk of developing early onset Major Depressive Disorder (MDD) yet are unlikely to access services. We therefore aimed to identify a parsimonious combination of parent-reported symptoms that accurately detected offspring MDD. We used a multi-sample study comprising a development sample of 335 offspring of adults with recurrent MDD assessed on three occasions (mean age 12.4-14.8 years) and an independent validation sub-sample of 807 adolescents from a general population cohort (mean age 13.1 years). Parent ratings of psychiatric symptoms in adolescent offspring were assessed using established questionnaires. The best performing four-item combination of symptoms was identified. Accuracy in detecting concurrent DSM-IV MDD diagnosis, assessed by direct adolescent and parent interviews, was compared to the well-established 13-item short Moods and Feelings Questionnaire (sMFQ) using ROC curve analysis. The combination identified (concentration problems, anhedonia, worrying excessively and feeling unloved) performed equivalently to the sMFQ both in the development dataset and in the validation dataset. We concluded that a combination of four parent-reported mental health items performs equivalently to an established, longer depression questionnaire measure in detecting a diagnosis of adolescent major depressive disorder among offspring of parents with recurrent MDD and needs further evaluation.

Development and Application of a Genetic Algorithm for Variable Optimization and Predictive Modeling of Five-Year Mortality Using Questionnaire Data

The problem of selecting important variables for predictive modeling of a specific outcome of interest using questionnaire data has rarely been addressed in clinical settings. In this study, we implemented a genetic algorithm (GA) technique to select optimal variables from questionnaire data for predicting a five-year mortality. We examined 123 questions (variables) answered by 5,444 individuals in the National Health and Nutrition Examination Survey. The GA iterations selected the top 24 variables, including questions related to stroke, emphysema, and general health problems requiring the use of special equipment, for use in predictive modeling by various parametric and nonparametric machine learning techniques. Using these top 24 variables, gradient boosting yielded the nominally highest performance (area under curve [AUC] = 0.7654), although there were other techniques with lower but not significantly different AUC. This study shows how GA in conjunction with various machine learning techniques could be used to examine questionnaire data to predict a binary outcome.