Classifying depression using blood biomarkers: A large population study

Graph convolutional network with attention mechanism improve major depressive depression diagnosis based on plasma biomarkers and neuroimaging data

BACKGROUND

The absence of clinically-validated biomarkers or objective protocols hinders effective major depressive disorder (MDD) diagnosis. Compared to healthy control (HC), MDD exhibits anomalies in plasma protein levels and neuroimaging presentations. Despite extensive machine learning studies in psychiatric diagnosis, a reliable tool integrating multi-modality data is still lacking.

METHODS

In this study, blood samples from 100 MDD and 100 HC were analyzed, along with MRI images from 46 MDD and 49 HC. Here, we devised a novel algorithm, integrating graph neural networks and attention modules, for MDD diagnosis based on inflammatory cytokines, neurotrophic factors, and Orexin A levels in the blood samples. Model performance was assessed via accuracy and F1 value in 3-fold cross-validation, comparing with 9 traditional algorithms. We then applied our algorithm to a dataset containing both the aforementioned protein quantifications and neuroimages, evaluating if integrating neuroimages into the model improves performance.

RESULTS

Compared to HC, MDD showed significant alterations in plasma protein levels and gray matter volume revealed by MRI. Our new algorithm exhibited superior performance, achieving an F1 value and accuracy of 0.9436 and 94.08 %, respectively. Integration of neuroimaging data enhanced our novel algorithm's performance, resulting in an improved F1 value and accuracy, reaching 0.9543 and 95.06 %.

LIMITATIONS

This single-center study with a small sample size requires future evaluations on a larger test set for improved reliability.

CONCLUSIONS

In comparison to traditional machine learning models, our newly developed MDD diagnostic model exhibited superior performance and showed promising potential for inclusion in routine clinical diagnosis for MDD.

Effectiveness of artificial intelligence in detecting and managing depressive disorders: Systematic review

OBJECTIVES

This study underscores the importance of exploring AI's creative applications in treating depressive disorders to revolutionize mental health care. Through innovative integration of AI technologies, the research confirms their positive effects on preventing, diagnosing, and treating depression. The systematic review establishes an evidence base for AI in depression management, offering directions for effective interventions.

METHODS

This systematic literature review investigates the effectiveness of AI in depression management by analyzing studies from January 1, 2017, to May 31, 2022. Utilizing search engines like IEEE Xplore, PubMed, and Web of Science, the review focused on keywords such as Depression/Mental Health, Machine Learning/Artificial Intelligence, and Prediction/Diagnosis. The analysis of 95 documents involved classification based on use, data type, and algorithm type.

RESULTS

The study revealed that AI in depression management excelled in accuracy, particularly in monitoring and prediction. Biomarker-derived data demonstrated the highest accuracy, with the CNN algorithm proving most effective. The findings affirm the therapeutic benefits of AI, including treatment, detection, and disease prediction, highlighting its potential in analyzing monitored data for depression management.

LIMITATIONS

This study exclusively examined the application of AI in individuals with depressive disorders. Interpretation should be cautious due to the limited scope of subjects to this specific population.

CONCLUSIONS

To introduce digital healthcare and therapies for ongoing depression management, it's crucial to present empirical evidence on the medical fee payment system, safety, and efficacy. These findings support enhanced medical accessibility through digital healthcare, offering personalized disease management for patients seeking non-face-to-face treatment.

Depression and cognition are associated with lipid dysregulation in both a multigenerational study of depression and the National Health and Nutrition Examination Survey

Chronic dysregulation of peripheral lipids has been found to be associated with depression and cognition, but their interaction has not been investigated. Growing evidence has highlighted the association between peripheral lipoprotein levels with depression and cognition with inconsistent results. We assessed the association between peripheral lipids, depression, and cognition while evaluating their potential interactions using robust clinically relevant predictors such as lipoprotein levels and chronic medical disorders that dysregulate lipoproteins. We report an association between peripheral lipids, depression, and cognition, suggesting a common underlying biological mechanism driven by lipid dysregulation in two independent studies. Analysis of a longitudinal study of a cohort at high or low familial risk for major depressive disorder (MDD) (n = 526) found metabolic diseases, including diabetes, hypertension, and other cardiovascular diseases, were associated with MDD and cognitive outcomes. Investigating a cross-sectional population survey of adults in the National Health and Nutrition Examination Survey 2011-2014 (NHANES) (n = 2377), depression was found to be associated with high density lipoprotein (HDL) and cognitive assessments. In the familial risk study, medical conditions were found to be associated with chronic lipid dysregulation and were significantly associated with MDD using the structural equation model. A positive association between chronic lipid dysregulation and cognitive scores was found in an exploratory analysis of the familial risk study. In a complementary study, analysis of NHANES revealed a positive association of HDL levels with cognition. Further analysis of the NHANES cohort indicated that depression status mediated the interaction between HDL levels and cognitive tests. Importantly, the protective effect of HDL on cognition was absent in those with depressive symptoms, which may ultimately result in worse outcomes leading to cognitive decline. These findings highlight the potential for the early predictive value of medical conditions with chronic lipid dyshomeostasis for the risk of depression and cognitive decline.

Different roles of microbiota and genetics in the prediction of treatment response in major depressive disorder

The roles of gut microbiota and susceptibility genes in patients with major depression disorder (MDD) are not well understood. Examining the microbiome and host genetics might be helpful for clinical decision-making. Patients with MDD were recruited in this study and subsequently treated for eight weeks. We identified the differences between the population with a response after two weeks and those with a response after eight weeks. The factors that were significantly correlated with efficacy were used to predict the treatment response. The differences in the importance of microbiota and genetics in prediction were analyzed. Our study identified rs58010457 as a potentially key locus affecting the treatment effect. Different microbiota and enriched pathways might play different roles in the response after two and eight weeks. We found that the area under the curve (AUC) value was greater than 0.8 for both random forest models. The contribution of different components to the AUC was evaluated by removing genetic information, microbiota abundance, and pathway data. The gut microbiome was an important predictor of the response after eight weeks, while genetics was an important predictor of the response after two weeks. These results suggested a dynamic effect of interaction among genetics and gut microbes on treatment. Furthermore, these results provide new guidance for clinical decisions: in cases of inadequate treatment effects after two weeks, the composition of the intestinal flora can be improved by diet therapy, which could ultimately affect the efficacy.

Machine learning-based predictive modeling of depression in hypertensive populations

We aimed to develop prediction models for depression among U.S. adults with hypertension using various machine learning (ML) approaches. Moreover, we analyzed the mechanisms of the developed models. This cross-sectional study included 8,628 adults with hypertension (11.3% with depression) from the National Health and Nutrition Examination Survey (2011–2020). We selected several significant features using feature selection methods to build the models. Data imbalance was managed with random down-sampling. Six different ML classification methods implemented in the R package caret—artificial neural network, random forest, AdaBoost, stochastic gradient boosting, XGBoost, and support vector machine—were employed with 10-fold cross-validation for predictions. Model performance was assessed by examining the area under the receiver operating characteristic curve (AUC), accuracy, precision, sensitivity, specificity, and F1-score. For an interpretable algorithm, we used the variable importance evaluation function in caret. Of all classification models, artificial neural network trained with selected features (n = 30) achieved the highest AUC (0.813) and specificity (0.780) in predicting depression. Support vector machine predicted depression with the highest accuracy (0.771), precision (0.969), sensitivity (0.774), and F1-score (0.860). The most frequent and important features contributing to the models included the ratio of family income to poverty, triglyceride level, white blood cell count, age, sleep disorder status, the presence of arthritis, hemoglobin level, marital status, and education level. In conclusion, ML algorithms performed comparably in predicting depression among hypertensive populations. Furthermore, the developed models shed light on variables’ relative importance, paving the way for further clinical research.