Importance of immunometabolic markers for the classification of patients with major depressive disorder using machine learning.

BACKGROUND: Although there is scientific evidence of the presence of immunometabolic alterations in major depression, not all patients present them. Recent studies point to the association between an inflammatory phenotype and certain clinical symptoms in patients with depression. The objective of our study was to classify major depression disorder patients using supervised learning algorithms or machine learning, based on immunometabolic and oxidative stress biomarkers and lifestyle habits. METHODS: Taking into account a series of inflammatory and oxidative stress biomarkers (C-reactive protein (CRP), tumor necrosis factor (TNF), 4-hydroxynonenal (HNE) and glutathione), metabolic risk markers (blood pressure, waist circumference and glucose, triglyceride and cholesterol levels) and lifestyle habits of the participants (physical activity, smoking and alcohol consumption), a study was carried out using machine learning in a sample of 171 participants, 91 patients with depression (71.42% women, mean age = 50.64) and 80 healthy subjects (67.50% women, mean age = 49.12). The algorithm used was the support vector machine, performing cross validation, by which the subdivision of the sample in training (70%) and test (30%) was carried out in order to estimate the precision of the model. The prediction of belonging to the patient group (MDD patients versus control subjects), melancholic type (melancholic versus non-melancholic patients) or resistant depression group (treatment-resistant versus non-treatment-resistant) was based on the importance of each of the immunometabolic and lifestyle variables. RESULTS: With the application of the algorithm, controls versus patients, such as patients with melancholic symptoms versus non-melancholic symptoms, and resistant versus non-resistant symptoms in the test phase were optimally classified. The variables that showed greater importance, according to the results of the area under the ROC curve, for the discrimination between healthy subjects and patients with depression were current alcohol consumption (AUC = 0.62), TNF-α levels (AUC = 0.61), glutathione redox status (AUC = 0.60) and the performance of both moderate (AUC = 0.59) and vigorous physical exercise (AUC = 0.58). On the other hand, the most important variables for classifying melancholic patients in relation to lifestyle habits were past (AUC = 0.65) and current (AUC = 0.60) tobacco habit, as well as walking routinely (AUC = 0.59) and in relation to immunometabolic markers were the levels of CRP (AUC = 0.62) and glucose (AUC = 0.58). In the analysis of the importance of the variables for the classification of treatment-resistant patients versus non-resistant patients, the systolic blood pressure (SBP) variable was shown to be the most relevant (AUC = 0.67). Other immunometabolic variables were also among the most important such as TNF-α (AUC = 0.65) and waist circumference (AUC = 0.64). In this case, sex (AUC = 0.59) was also relevant along with alcohol (AUC = 0.58) and tobacco (AUC = 0.56) consumption. CONCLUSIONS: The results obtained in our study show that it is possible to predict the diagnosis of depression and its clinical typology from immunometabolic markers and lifestyle habits, using machine learning techniques. The use of this type of methodology could facilitate the identification of patients at risk of presenting depression and could be very useful for managing clinical heterogeneity.

Relationship between immunometabolic status and cognitive performance among major depression disorder patients.

BACKGROUND: Alterations in cognitive performance have been described in patients with major depressive disorder (MDD). However, the specific risk factors of these changes are not yet known. This study aimed to explore whether inmunometabolic parameters are related to cognitive performance in MDD in comparison to healthy controls (HC) METHODS: Sample consisted of 84 MDD patients and 78 HC. Both groups were compared on the results of cognitive performance measured with the Cambridge Neuropsychological Test Automated Battery (CANTAB), the presence of metabolic syndrome (MetS) and an inflammatory/oxidative index calculated by a principal component analysis of peripheral biomarkers (tumor necrosis factor, C-reactive protein and 4-hydroxynonenal). A multiple linear regression was carried out, to study the relationship between inmunometabolic variables and the global cognitive performance, being the latter the dependent variable. RESULTS: Significant differences were obtained in the inflammatory/oxidative index between both groups (F(1157)= 12.93; p < .001), also in cognitive performance (F(1157)= 56.75; p < .001). The inmunometabolic covariate regression model (i.e., condition (HC/MDD), sex, age and medication loading, MetS, inflammatory/oxidative index and the interaction between MetS and inflammatory/oxidative index) was statistically significant (F(7157)= 11.24; p < .01) and explained 31% of variance. The condition, being either MDD or HD, (B=-0.97; p < .001), age (B=-0.28; p < .001) and the interaction between inflammatory/oxidative index and MetS (B=-0.38; p = .02) were factors associated to cognitive performance. LIMITATIONS: Sample size was relatively small. The cross-sectional design of the study limits the possibilities of analysis. CONCLUSIONS: Our results provide evidence on the conjoint influence of metabolic and inflammatory dysregulation on cognitive dysfunction in MDD patients. In this way, our study opens a line of research in immunometabolic agents to deal with cognitive decline associated with MDD.

Sex differences in the association between obsessive-compulsive symptom dimensions and diurnal cortisol patterns.

Previous studies in non-clinical populations suggest that obsessive-compulsive symptoms are associated with hypothalamic-pituitary-adrenal (HPA) axis measures and that there are sex differences in these associations. We aimed to replicate these findings in a sample of 57 patients with obsessive-compulsive disorder (OCD) and 98 healthy subjects. Current and lifetime OCD symptom dimensions were assessed with the Dimensional Yale-Brown Obsessive Compulsive Scale (DY-BOCS). Depressive symptoms and state and trait anxiety were also assessed. The following HPA axis measures were analysed in saliva: the diurnal cortisol slope (calculated using two formulas: [1] awakening to 11 p.m. [AWE diurnal slope] and [2] considering fixed time points [FTP diurnal slope] from 10 a.m. to 11 p.m.) and the dexamethasone suppression test ratio (DSTR) after 0.25 mg of dexamethasone. Multiple linear regression analyses were conducted to explore the contribution of OCD symptom dimensions to each HPA axis measure while adjusting for age, sex, BMI, smoking, trait anxiety and depressive symptoms. A sex-specific association between current ordering/symmetry symptoms and AWE diurnal cortisol slope (positive association [flattened slope] in men, inverse association [stepper slope] in women) was found. Two similar sex by OCD dimensions interactions were found for lifetime aggressive and ordering/symmetry symptoms and both (FTP, AWE) diurnal cortisol slopes. Current and lifetime hoarding symptoms were associated to a more flattened FTP diurnal cortisol slope in women. The DSTR was not associated with OCD symptoms. The lifetime interference in functionality was associated with a more flattened AWE diurnal cortisol slope. In conclusion, our study suggests that there are sex differences in the association between OCD subtypes and specific HPA axis measures.