Interactive effects of systemic inflammation and life stressors on treatment response of depressive disorders

Identification of depression in patients with acute coronary syndrome using multiple serum biomarkers

BACKGROUND

Biomarkers for depression in patients with acute coronary syndrome (ACS) have not been identified.

METHODS

This study evaluated multiple serum biomarkers for depressive disorders after ACS. Thirteen serum biomarkers associated with seven functional systems, along with sociodemographic/clinical characteristics, were evaluated in 969 patients within 2 weeks after ACS onset (acute phase). In total, 711 patients were evaluated for depressive disorder using DSM-IV criteria 1 year later (chronic phase). Logistic regression was used for the analysis.

RESULTS

Depressive disorders were observed in 378 patients (39.0%) in the acute phase of ACS and 183 patients (25.7%) in the chronic phase. The weighted scores of five serum biomarkers (high-sensitivity C-reactive protein, interleukin-6, homocysteine, troponin I, and creatine kinase-MB) were significantly associated with depressive disorder diagnosis in the acute phase, and the weighted scores of three other biomarkers (tumor necrosis factor-alpha, interleukin-1 beta, and homocysteine) were significantly associated with depressive disorders in the chronic phase, in a dose-dependent manner after adjusting for relevant covariates (all P-values <0.001).

CONCLUSIONS

The combination of several serum biomarkers exhibited robust associations with depressive disorders in both the acute and chronic phases of ACS.

Predicting the Treatment Outcomes of Antidepressants Using a Deep Neural Network of Deep Learning in Drug-Naïve Major Depressive Patients

Predicting the treatment response to antidepressants by pretreatment features would be useful, as up to 70–90% of patients with major depressive disorder (MDD) do not respond to treatment as expected. Therefore, we aim to establish a deep neural network (DNN) model of deep learning to predict the treatment outcomes of antidepressants in drug-naïve and first-diagnosis MDD patients during severe depressive stage using different domains of signature profiles of clinical features, peripheral biochemistry, psychosocial factors, and genetic polymorphisms. The multilayer feedforward neural network containing two hidden layers was applied to build models with tenfold cross-validation. The areas under the curve (AUC) of the receiver operating characteristic curves were used to evaluate the performance of the models. The results demonstrated that the AUCs of the model ranged between 0.7 and 0.8 using a combination of different domains of categorical variables. Moreover, models using the extracted variables demonstrated better performance, and the best performing model was characterized by an AUC of 0.825, using the levels of cortisol and oxytocin, scales of social support and quality of life, and polymorphisms of the OXTR gene. A complex interactions model developed through DNN could be useful at the clinical level for predicting the individualized outcomes of antidepressants.