A peripheral inflammatory signature discriminates bipolar from unipolar depression: A machine learning approach.

Background: Mood disorders (major depressive disorder, MDD, and bipolar disorder, BD) are considered leading causes of life-long disability worldwide, where high rates of no response to treatment or relapse and delays in receiving a proper diagnosis (~60% of depressed BD patients are initially misdiagnosed as MDD) contribute to a growing personal and socio-economic burden. The immune system may represent a new target to develop novel diagnostic and therapeutic procedures but reliable biomarkers still need to be found.

Methods: In our study we predicted the differential diagnosis of mood disorders by considering the plasma levels of 54 cytokines, chemokines and growth factors of 81 BD and 127 MDD depressed patients. Clinical diagnoses were predicted also against 32 healthy controls. Elastic net models, including 5000 non-parametric bootstrapping procedure and inner and outer 10-fold nested cross-validation were performed in order to identify the signatures for the disorders.

Results: Results showed that the immune-inflammatory signature classifies the two disorders with a high accuracy (AUC = 97%), specifically 92% and 86% respectively for MDD and BD. MDD diagnosis was predicted by high levels of markers related to both pro-inflammatory (i.e. IL-1β, IL-6, IL-7, IL-16) and regulatory responses (IL-2, IL-4, and IL-10), whereas BD by high levels of inflammatory markers (CCL3, CCL4, CCL5, CCL11, CCL25, CCL27, CXCL11, IL-9 and TNF-α).

Conclusions: Our findings provide novel tools for early diagnosis of BD, strengthening the impact of biomarkers research into clinical practice, and new insights for the development of innovative therapeutic strategies for depressive disorders.