A predictive model for diagnosing bipolar disorder based on the clinical characteristics of major depressive episodes in Chinese population.

BACKGROUND: A correct timely diagnosis of bipolar depression remains a big challenge for clinicians. This study aimed to develop a clinical characteristic based model to predict the diagnosis of bipolar disorder among patients with current major depressive episodes.
METHODS: A prospective study was carried out on 344 patients with current major depressive episodes, with 268 completing 1-year follow-up. Data were collected through structured interviews. Univariate binary logistic regression was conducted to select potential predictive variables among 19 initial variables, and then multivariate binary logistic regression was performed to analyze the combination of risk factors and build a predictive model. Receiver operating characteristic (ROC) curve was plotted.
RESULTS: Of 19 initial variables, 13 variables were preliminarily selected, and then forward stepwise exercise produced a final model consisting of 6 variables: age at first onset, maximum duration of depressive episodes, somatalgia, hypersomnia, diurnal variation of mood, irritability. The correct prediction rate of this model was 78% (95%CI: 75%-86%) and the area under the ROC curve was 0.85 (95%CI: 0.80-0.90). The cut-off point for age at first onset was 28.5 years old, while the cut-off point for maximum duration of depressive episode was 7.5 months. LIMITATIONS: The limitations of this study include small sample size, relatively short follow-up period and lack of treatment information.
CONCLUSION: Our predictive models based on six clinical characteristics of major depressive episodes prove to be robust and can help differentiate bipolar depression from unipolar depression.