Development and Internal Validation of a Novel Model to Identify Inflammatory Biomarkers of a Response to Escitalopram in Patients With Major Depressive Disorder

Advancing translational research in neuroscience through multi-task learning

Translational research in neuroscience is increasingly focusing on the analysis of multi-modal data, in order to account for the biological complexity of suspected disease mechanisms. Recent advances in machine learning have the potential to substantially advance such translational research through the simultaneous analysis of different data modalities. This review focuses on one of such approaches, the so-called "multi-task learning" (MTL), and describes its potential utility for multi-modal data analyses in neuroscience. We summarize the methodological development of MTL starting from conventional machine learning, and present several scenarios that appear particularly suitable for its application. For these scenarios, we highlight different types of MTL algorithms, discuss emerging technological adaptations, and provide a step-by-step guide for readers to apply the MTL approach in their own studies. With its ability to simultaneously analyze multiple data modalities, MTL may become an important element of the analytics repertoire used in future neuroscience research and beyond.

The associations between depressive symptoms, functional impairment, and quality of life, in patients with major depression: undirected and Bayesian network analyses

BACKGROUND

Depressive symptoms, functional impairment, and decreased quality of life (QOL) are three important domains of major depressive disorder (MDD). However, the possible causal relationship between these factors has yet to be elucidated. Moreover, it is not known whether certain symptoms of MDD are more impairing than others. The network approach is a promising solution to these shortfalls.

METHODS

The baseline data of a multicenter prospective project conducted in 11 governances of China were analyzed. In total, 1385 patients with MDD were included. Depressive symptoms, functioning disability, and QOL were evaluated by the 17-item Hamilton Depression Rating Scale (HAMD-17), the Sheehan Disability Scale (SDS), and the Quality of Life Enjoyment and Satisfaction Questionnaire-Short Form (Q-LES-Q-SF). The network was estimated through the graphical Least Absolute Shrinkage and Selection Operator (LASSO) technique in combination with the directed acyclic graph.

RESULTS

Three centrality metrics of the graphical LASSO showed that social life dysfunction, QOL, and late insomnia exhibited the highest strength centrality. The network accuracy and stability were estimated to be robust and stable. The Bayesian network indicated that some depressive symptoms were directly associated with QOL, while other depressive symptoms showed an indirect association with QOL mediated by impaired function. Depressed mood was positioned at the highest level in the model and predicted the activation of functional impairment and anxiety.

CONCLUSIONS

Functional disability mediated the relationship between depressive symptoms and QOL. Family functionality and suicidal symptoms were directly related to QOL. Depressed mood played the predominant role in activating both anxiety symptom and functional impairment.

Antenatal maternal depression, early life inflammation and neurodevelopment in a South African birth cohort

BACKGROUND

Antenatal exposure to maternal psychological adversity, including depression, increases the risk of impaired neurodevelopment in children. The underlying biological mechanisms remain unclear, especially in early life during critical windows of development and maturation. This study investigated the association of antenatal maternal depression, maternal and early life inflammatory markers and neurodevelopmental outcomes in children at 2 years of age.

METHODS

A subgroup of mothers and their children (n = 255) that were enrolled in a South African birth cohort study, the Drakenstein Child Health Study, were followed from the antenatal period through to 2 years of child age. Maternal depressive symptoms were measured by the Beck Depression Inventory (BDI-II) at 26 weeks gestation. Serum inflammatory markers [granulocyte-macrophage colony-stimulating factor (GM-CSF), interferon-γ (IFN-γ), interleukin IL-1β, IL-2, IL-4, IL-5, IL-6, IL-7, IL-8, IL-10, IL-12p70, IL-13, tumour necrosis factor-α (TNF-α), neutrophil gelatinase-associated lipocalin (NGAL) and metalloproteinase-9 (MMP-9)] were measured in mothers at enrolment and in their children at 6-10 weeks and at 2 years. Neurodevelopment was assessed at 2 years using the Bayley Scales of Infant and Toddler Development III.

RESULTS

Antenatal depressive symptoms (present in 25% of the mothers) were significantly associated with higher levels of IL-7 (p = 0.008), IL-8 (p = 0.019) and TNF-α (p = 0.031) in the mothers after correcting for sociodemographic and lifestyle factors. Serum IL-1β and NGAL levels were significantly elevated over time in children born to mothers with depressive symptoms compared to those without depression, after controlling for maternal and child health and sociodemographic factors. Elevated infant IL-1β at 6-10 weeks of age partially mediated the association of maternal depressive symptoms with poorer language scores at 2 years.

CONCLUSION

Alterations in early life immunity, as reflected by elevated IL-1β, is a potential pathway through which antenatal maternal depressive symptoms may impact language development in young children.

Development and validation of a nomogram based on lymphocyte subsets to distinguish bipolar depression from major depressive disorder

OBJECTIVE

Bipolar depression (BD) and major depressive disorder (MDD) are both common affective disorders. The common depression episodes make it difficult to distinguish between them, even for experienced clinicians. Failure to properly diagnose them in a timely manner leads to inappropriate treatment strategies. Therefore, it is important to distinguish between BD and MDD. The aim of this study was to develop and validate a nomogram model that distinguishes BD from MDD based on the characteristics of lymphocyte subsets.

MATERIALS AND METHODS

A prospective cross-sectional study was performed. Blood samples were obtained from participants who met the inclusion criteria. The least absolute shrinkage and selection operator (LASSO) regression model was used for factor selection. A differential diagnosis nomogram for BD and MDD was developed using multivariable logistic regression and the area under the curve (AUC) with 95% confidence interval (CI) was calculated, as well as the internal validation using a bootstrap algorithm with 1,000 repetitions. Calibration curve and decision curve analysis (DCA) were used to evaluate the calibration and clinical utility of the nomogram, respectively.

RESULTS

A total of 166 participants who were diagnosed with BD (83 cases) or MDD (83 cases), as well as 101 healthy controls (HCs) between June 2018 and January 2022 were enrolled in this study. CD19⁺ B cells, CD3⁺ T cells, CD3^-CD16/56⁺ NK cells, and total lymphocyte counts were strong predictors of the diagnosis of BD and MDD and were included in the differential diagnosis nomogram. The AUC of the nomogram and internal validation were 0.922 (95%; CI, 0.879-0.965), and 0.911 (95% CI, 0.838-0.844), respectively. The calibration curve used to discriminate BD from MDD showed optimal agreement between the nomogram and the actual diagnosis. The results of DCA showed that the net clinical benefit was significant.

CONCLUSION

This is an easy-to-use, repeatable, and economical nomogram for differential diagnosis that can help clinicians in the individual diagnosis of BD and MDD patients, reduce the risk of misdiagnosis, facilitate the formulation of appropriate treatment strategies and intervention plans.