Prevalence and predictive nomogram of depression among hypertensive patients in primary care

Figures

• 

  Figure 1. The flow chart of recruiting the surveyed subjects including screening, eligibility and Included.

• 

  Figure 2. Predictor selection from demographic variables, socioeconomic status, health-related behaviors, and anthropometric measurements using the LASSO binary logistic regression model. Notes: (A) Optimal parameter (lambda) selection in the LASSO model used fivefold cross-validation via minimum criteria. The partial likelihood deviance (binomial deviance) curve was plotted versus log (lambda). Dotted vertical lines were drawn at the optimal values by using the minimum criteria and the 1 SE of the minimum criteria (the 1-SE criteria). (B)LASSO coefficient profiles of the 38 features. A coefficient profile plot was produced against the log (lambda) sequence. Vertical line was drawn at the value selected using fivefold cross-validation, where optimal lambda resulted in seven features with nonzero coefficients. Abbreviations: LASSO, least absolute shrinkage and selection operator; SE, standard error.

• 

  Figure 3. Proposed nomogram for depression in patients with hypertension. Nomogram predicting depression risk in hypertensive patients.

• 

  Figure 4. ROC curve of the nomogram. AUC: area under the curve.

• 

  Figure 5. Calibration curves of the depressive nomogram prediction in the study. Notes: (A) Calibration curve of the depressive nomogram prediction in the training set. (B) Calibration curve of the depressive nomogram prediction in the validation set. The x-axis represents the predicted depressive risk. The y-axis represents the actual identified patients with depression. The diagonal dotted line represents a perfect prediction by an ideal model. The solid line represents the performance of the nomogram, of which a closer fit to the diagonal dotted line represents a better prediction.

• 

  Figure 6. Decision curve analysis for the nomogram for predict depression. Notes: The y-axis measures the net benefit. The red line represents the depressive risk nomogram. The thin solid line represents the assumption that all patients are non-depression. Thin thick solid line represents the assumption that no patients are non-depression to medication. The decision curve showed that if the threshold probability of a patient and a doctor is ranged from 8% to 82%, using this nomogram for depression in the current study to predict depression risk adds more benefit than the intervention-all-patients scheme or the intervention-none scheme.

• 

  Figure 7. The clinical impact curves of the nomogram predicting risk stratification of 1,000 people and showing the loss-benefit ratio. The red line, number high risk: under each threshold probability, the number of people classified by the nomogram as positive (high risk). The blue line, number high risk with outcome: the number of people with true positive under each threshold probability. The x-axis represents the net benefit; the y-axis represents the high risk (out of 1000) of depression in hypertensive patients. For example, the dotted vertical line illustrates a tentative cut-off point (20% risk of depression) at which 340 of 1000 subjects (34%) would be filtered by the nomogram, with about 140 of these (41.2%) being true depression cases.