Predictors of diagnostic transition from major depressive disorder to bipolar disorder: a retrospective observational network study

Anastasiya Nestsiarovich,Stephen R Pfohl,Nigam H Shah,Rae Woong Park,Matthew Spotnitz,Jenna M Reps,Michael E Matheny,Maura Beaton,Xinzhuo Jiang,Patrick B Ryan,Seng Chan You,Carmen Olga Torre,Dong Yun Lee,Christophe G Lambert,Scott L Duvall,Sang Joon Son,Kristine E Lynch,Christian G Reich

doi:10.1038/s41398-021-01760-6

Abstract

Many patients with bipolar disorder (BD) are initially misdiagnosed with major depressive disorder (MDD) and are treated with antidepressants, whose potential iatrogenic effects are widely discussed. It is unknown whether MDD is a comorbidity of BD or its earlier stage, and no consensus exists on individual conversion predictors, delaying BD’s timely recognition and treatment. We aimed to build a predictive model of MDD to BD conversion and to validate it across a multi-national network of patient databases using the standardization afforded by the Observational Medical Outcomes Partnership (OMOP) common data model. Five “training” US databases were retrospectively analyzed: IBM MarketScan CCAE, MDCR, MDCD, Optum EHR, and Optum Claims. Cyclops regularized logistic regression models were developed on one-year MDD-BD conversion with all standard covariates from the HADES PatientLevelPrediction package. Time-to-conversion Kaplan-Meier analysis was performed up to a decade after MDD, stratified by model-estimated risk. External validation of the final prediction model was performed across 9 patient record databases within the Observational Health Data Sciences and Informatics (OHDSI) network internationally. The model’s area under the curve (AUC) varied 0.633–0.745 (µ = 0.689) across the five US training databases. Nine variables predicted one-year MDD-BD transition. Factors that increased risk were: younger age, severe depression, psychosis, anxiety, substance misuse, self-harm thoughts/actions, and prior mental disorder. AUCs of the validation datasets ranged 0.570–0.785 (µ = 0.664). An assessment algorithm was built for MDD to BD conversion that allows distinguishing as much as 100-fold risk differences among patients and validates well across multiple international data sources.

Highlights

Mood disorders are one of the three leading causes of disability worldwide [1], with major depressive disorder (MDD) affecting more than 17 million Americans [2] and bipolar disorder (BD) affecting 7 million Americans annually [3]
We described the model’s performance by reporting the receiver operator characteristic area under the curve (AUC) across five training datasets
As a result of our integrative data analysis from different databases, we developed a simple, clinically meaningful algorithm to estimate the individual patient’s risk of MDD diagnosis transition to BD within one year after the index visit (Fig. 5)

Summary

Introduction

Mood disorders are one of the three leading causes of disability worldwide [1], with major depressive disorder (MDD) affecting more than 17 million Americans [2] and bipolar disorder (BD) affecting 7 million Americans annually [3] Both MDD and BD are chronic debilitating psychiatric conditions, with overlapping neurobiology and symptoms (recurrent depressive episodes), BD is diagnosed if at least one manic/hypomanic episode was present during the patient lifetime [4]. It is debatable whether MDD represents an earlier stage of BD or is part of the same illness [5,6,7], given high MDD to BD prospective conversion rates (20-year rate of 25% [8] and annual rate of 0.8–3.9% [9, 10]). It is suggested that the use of antidepressants by patients with unrecognized BD can contribute to their drug resistance, making them difficult to treat [11]

Objectives

Discussion

Conclusion