Dataset Information

Identifying neuroimaging biomarkers of major depressive disorder from cortical hemodynamic responses using machine learning approaches.

ABSTRACT:

Background

Early diagnosis of major depressive disorder (MDD) could enable timely interventions and effective management which subsequently improve clinical outcomes. However, quantitative and objective assessment tools for the suspected cases who present with depressive symptoms have not been fully established.

Methods

Based on a large-scale dataset (n = 363 subjects) collected with functional near-infrared spectroscopy (fNIRS) measurements during the verbal fluency task (VFT), this study proposed a data representation method for extracting spatiotemporal characteristics of NIRS signals, which emerged as candidate predictors in a two-phase machine learning framework to detect distinctive biomarkers for MDD. Supervised classifiers (e.g., support vector machine (SVM), k-nearest neighbors (KNN)) cooperated with cross-validation were implemented to evaluate the predictive capability of selected features in a training set. Another test set that was not involved in developing the algorithms enabled the independent assessment of the model's generalization.

Findings

For the classification with the optimal fusion features, the SVM classifier achieved the highest accuracy of 75.6% ± 4.7% in the nested cross-validation, and the correct prediction rate of 78.0% with a sensitivity of 75.0% and a specificity of 81.4% in the test set. Moreover, the multiway ANOVA test on clinical and demographic factors confirmed that twenty out of 39 optimal features were significantly correlated with the MDD-distinctive consequence.

Interpretation

The abnormal prefrontal activity of MDD may be quantified as diminished relative intensity and inappropriate activation timing of hemodynamic response, resulting in an objectively measurable biomarker for assessing cognitive deficits and screening MDD at the early stage.

Funding

This study was funded by NUS iHeathtech Other Operating Expenses (R-722-000-004-731).

SUBMITTER: Li Z

PROVIDER: S-EPMC9062667 | biostudies-literature | 2022 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identifying neuroimaging biomarkers of major depressive disorder from cortical hemodynamic responses using machine learning approaches.

Li Zhifei Z McIntyre Roger S RS Husain Syeda F SF Ho Roger R Tran Bach X BX Nguyen Hien Thu HT Soo Shuenn-Chiang SC Ho Cyrus S CS Chen Nanguang N

EBioMedicine 20220428

<h4>Background</h4>Early diagnosis of major depressive disorder (MDD) could enable timely interventions and effective management which subsequently improve clinical outcomes. However, quantitative and objective assessment tools for the suspected cases who present with depressive symptoms have not been fully established.<h4>Methods</h4>Based on a large-scale dataset (n = 363 subjects) collected with functional near-infrared spectroscopy (fNIRS) measurements during the verbal fluency task (VFT), t ...[more]

PMID: 35490557

Similar Datasets

Project description:Major depressive disorder emerges from the complex interactions of biological systems that span genes and molecules through cells, networks, and behavior. Establishing how neurobiological processes coalesce to contribute to depression requires a multiscale approach, encompassing measures of brain structure and function as well as genetic and cell-specific transcriptional data. Here, we examine anatomical (cortical thickness) and functional (functional variability, global brain connectivity) correlates of depression and negative affect across three population-imaging datasets: UK Biobank, Brain Genomics Superstruct Project, and Enhancing NeuroImaging through Meta Analysis (ENIGMA; combined n ≥ 23,723). Integrative analyses incorporate measures of cortical gene expression, postmortem patient transcriptional data, depression genome-wide association study (GWAS), and single-cell gene transcription. Neuroimaging correlates of depression and negative affect were consistent across three independent datasets. Linking ex vivo gene down-regulation with in vivo neuroimaging, we find that transcriptional correlates of depression imaging phenotypes track gene down-regulation in postmortem cortical samples of patients with depression. Integrated analysis of single-cell and Allen Human Brain Atlas expression data reveal somatostatin interneurons and astrocytes to be consistent cell associates of depression, through both in vivo imaging and ex vivo cortical gene dysregulation. Providing converging evidence for these observations, GWAS-derived polygenic risk for depression was enriched for genes expressed in interneurons, but not glia. Underscoring the translational potential of multiscale approaches, the transcriptional correlates of depression-linked brain function and structure were enriched for disorder-relevant molecular pathways. These findings bridge levels to connect specific genes, cell classes, and biological pathways to in vivo imaging correlates of depression.

Project description:BackgroundIt has been increasingly recognized that adults living alone have a higher likelihood of developing Major Depressive Disorder (MDD) than those living with others. However, there is still no prediction model for MDD specifically designed for adults who live alone.ObjectiveThis study aims to investigate the effectiveness of utilizing personal health data in combination with a stacked ensemble machine learning (SEML) technique to detect MDD among adults living alone, seeking to gain insights into the interaction between personal health data and MDD.MethodsOur data originated from the US National Health and Nutrition Examination Survey (NHANES) spanning 2007 to 2018. We finally selected a set of 30 easily accessible variables encompassing demographic profiles, lifestyle factors, and baseline health conditions. We constructed a SEML model for MDD detection, incorporating three conventional machine learning algorithms as base models and a Neural Network (NN) as the meta-model. Furthermore, SHapley Additive exPlanations (SHAP) analysis was used to explain the impact of each predictor on MDD.ResultsThe study included 2,642 adult participants who lived alone, of whom 10.6% (279 out of 2,642) had a PHQ-9 score of 10 or above, indicating the presence of MDD. The performance of our SEML model was robust, with an area under the curve (AUC) of 0.85. Further analysis using SHAP revealed positive correlations between the occurrence of MDD and factors such as sleep disorders, number of prescription medications, need for specific walking aids, leak urine during nonphysical activities, chronic bronchitis, and Healthy Eating Index (HEI) scores for sodium. Conversely, age, the Family Monthly Poverty Level Index (FMMPI), and HEI scores for added sugar showed negative correlations with MDD occurrence. Additionally, a U-shaped relationship was noted between the occurrence of MDD and both sleep duration and Body Mass Index (BMI), as well as HEI scores for dairy.ConclusionThe study has successfully developed a predictive model for MDD, specifically tailored for adults living alone using a stacked ensemble technique, enhancing the identification of MDD and its risk factors among adults living alone.

Project description:Background: Major Depressive Disorder (MDD) is a moderately heritable disorder with a high lifetime prevalence. At present, laboratory blood tests to support MDD diagnosis are not available. Methods: We used a classifier approach on blood gene expression profiles of a unique set of non-medicated subjects (MDD patients and controls) to select genes of which expression is predictive for disease status. To reveal blood gene expression changes related to MDD disease, we applied a powerful ex vivo stimulus to the blood, i.e. incubation with lipopolysaccharide (LPS; 10 ng/ml blood). Results: Based on LPS-stimulated blood gene expression using whole-genome microarrays in 42 subjects (primary cohort; 21 MDD patients (mean age 42.3 years), 21 healthy controls (mean age 41.9 years)), we identified a set of genes (CAPRIN1, CLEC4A, KRT23, MLC1, PLSCR1, PROK2, ZBTB16) that serves as a molecular signature of MDD. These findings were validated for the primary cohort using an independent quantitative PCR method (P = 0.007). The difference between depressive patients and controls was confirmed (P = 0.019) in a replication cohort of 13 patients with MDD (mean age 42.8 years) and 14 controls (mean age 45.6 years). The MDD-signature score comprised of expression levels of 7 genes could discriminate depressive patients from controls with sensitivity of 76.9% and specificity of 71.8%. Conclusions: We show for the first time that molecular analysis of stimulated blood cells can be used as an endophenotype for MDD diagnosis, which is a milestone in establishing biomarkers for neuropsychiatric disorders with moderate heritability in general. Our results may provide a new entry point for following and predicting treatment outcome, as well as prediction of severity and recurrence of MDD. In total, 33 MDD patients and 34 healthy controls were analyzed using basal gene expression in whole blood, and gene expression from whole blood that was stimulated with LPS for 5-6 h, using microarrays. Patients were arbitrarily selected from all patients to serve as primary cohort (nMDD = 21 (MDD01-MDD21); nControls = 21 (Con01-Con21)), or replication cohort (nMDD = 12 (MDD22-MDD35); nControls = 13 (Con22-Con37)) using microarrays. This submission does not include Samples CON21_LPS or CON30_LPS.

Project description:ImportanceCurrently, fewer than 40% of patients treated for major depressive disorder achieve remission with initial treatment. Identification of a biological marker that might improve these odds could have significant health and economic impact.ObjectiveTo identify a candidate neuroimaging "treatment-specific biomarker" that predicts differential outcome to either medication or psychotherapy.DesignBrain glucose metabolism was measured with positron emission tomography prior to treatment randomization to either escitalopram oxalate or cognitive behavior therapy for 12 weeks. Patients who did not remit on completion of their phase 1 treatment were offered enrollment in phase 2 comprising an additional 12 weeks of treatment with combination escitalopram and cognitive behavior therapy.SettingMood and anxiety disorders research program at an academic medical center.ParticipantsMen and women aged 18 to 60 years with currently untreated major depressive disorder.InterventionRandomized assignment to 12 weeks of treatment with either escitalopram oxalate (10-20 mg/d) or 16 sessions of manual-based cognitive behavior therapy.Main outcome and measureRemission, defined as a 17-item Hamilton depression rating scale score of 7 or less at both weeks 10 and 12, as assessed by raters blinded to treatment.ResultsPositive and negative predictors of remission were identified with a 2-way analysis of variance treatment (escitalopram or cognitive behavior therapy) × outcome (remission or nonresponse) interaction. Of 65 protocol completers, 38 patients with clear outcomes and usable positron emission tomography scans were included in the primary analysis: 12 remitters to cognitive behavior therapy, 11 remitters to escitalopram, 9 nonresponders to cognitive behavior therapy, and 6 nonresponders to escitalopram. Six limbic and cortical regions were identified, with the right anterior insula showing the most robust discriminant properties across groups (effect size = 1.43). Insula hypometabolism (relative to whole-brain mean) was associated with remission to cognitive behavior therapy and poor response to escitalopram, while insula hypermetabolism was associated with remission to escitalopram and poor response to cognitive behavior therapy.Conclusions and relevanceIf verified with prospective testing, the insula metabolism-based treatment-specific biomarker defined in this study provides the first objective marker, to our knowledge, to guide initial treatment selection for depression.Trial registrationRegistered at clinicaltrials.gov (NCT00367341).

Dataset Information

Identifying neuroimaging biomarkers of major depressive disorder from cortical hemodynamic responses using machine learning approaches.

Background

Methods

Findings

Interpretation

Funding

Publications

Identifying neuroimaging biomarkers of major depressive disorder from cortical hemodynamic responses using machine learning approaches.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets