Unveiling the Connection between Microbiota and Depressive Disorder through Machine Learning
Ontology highlight
ABSTRACT:
SUBMITTER:
PROVIDER: S-EPMC10671666 | biostudies-literature | 2023 Nov
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundThe development of optimal classification criteria for specific mental disorders which share similar symptoms is an important issue for precise diagnosis. We investigated whether P300 features in both sensor-level and source-level could be effectively used to classify post-traumatic stress disorder (PTSD) and major depressive disorder (MDD).MethodEEG signals were recorded from fifty-one PTSD patients, 67 MDD patients, and 39 healthy controls (HCs) while performing an auditory oddball task. Amplitude and latency of P300 were evaluated, and the current source analysis of P300 components was conducted using sLORETA. Finally, we classified two groups using machine-learning methods with both sensor- and source-level features. Moreover, we checked the comorbidity effects using the same approaches (PTSD-mono diagnosis (PTSDm, n = 28) and PTSD-comorbid diagnosis (PTSDc, n = 23)).ResultsPTSD showed significantly reduced P300 amplitudes and prolonged latency compared to HCs and MDD. Moreover, PTSD showed significantly reduced source activities, and the source activities were significantly correlated with symptoms of depression and anxiety. Also, the best classification accuracy at each pair was as follows: 80.00% (PTSD-HCs), 67.92% (MDD-HCs), 70.34% (PTSD-MDD), 82.09% (PTSDm-HCs), 71.58% (PTSDm-MDD), 82.56% (PTSDc-HCs), and 76.67% (PTSDc- MDD).ConclusionSince abnormal P300 reflects pathophysiological characteristics of PTSD, PTSD patients were well-discriminated from MDD and HCs when using P300 features. Thus, altered P300 characteristics in both sensor- and source-level may be useful biomarkers to diagnosis PTSD.
| S-EPMC6812119 | biostudies-literature
Project description:Depression in older adults is often underdiagnosed and has been linked to adverse outcomes, including motor vehicle crashes. With a growing population of older drivers in the United States, innovations in screening methods are needed to identify older adults at greatest risk of decline. This study used machine learning techniques to analyze real-world naturalistic driving data to identify depression status in older adults and examined whether specific demographics and medications improved model performance. We analyzed two years of GPS data from 157 older adults, including 81 with major depressive disorder, using XGBoost and logistic regression models. The top-performing model achieved an area under the curve of 0.86 with driving features combined with total medication use. These findings suggest that naturalistic driving data holds high potential as a functional digital neurobehavioral marker for AI identifying depression in older adults on a national scale, thereby ensuring equitable access to treatment.
| S-EPMC11828977 | biostudies-literature
Project description:BackgroundEnteric methane from cow burps, which results from microbial fermentation of high-fiber feed in the rumen, is a significant contributor to greenhouse gas emissions. A promising strategy to address this problem is microbiome-based precision feed, which involves identifying key microorganisms for methane production. While machine learning algorithms have shown success in associating human gut microbiome with various human diseases, there have been limited efforts to employ these algorithms to establish microbial biomarkers for methane emissions in ruminants.MethodsIn this study, we aim to identify potential methane biomarkers for methane emission from ruminants by employing regression algorithms commonly used in human microbiome studies, coupled with different feature selection methods. To achieve this, we analyzed the microbiome compositions and identified possible confounding metadata variables in two large public datasets of Holstein cows. Using both the microbiome features and identified metadata variables, we trained different regressors to predict methane emission. With the optimized models, permutation tests were used to determine feature importance to find informative microbial features.ResultsAmong the regression algorithms tested, random forest regression outperformed others and allowed the identification of several crucial microbial taxa for methane emission as members of the native rumen microbiome, including the genera Piromyces, Succinivibrionaceae UCG-002, and Acetobacter. Additionally, our results revealed that certain herd locations and feed composition markers, such as the lipid intake and neutral-detergent fiber intake, are also predictive features for methane emissions.ConclusionWe demonstrated that machine learning, particularly regression algorithms, can effectively predict cow methane emissions and identify relevant rumen microorganisms. Our findings offer valuable insights for the development of microbiome-based precision feed strategies aiming at reducing methane emissions.
| S-EPMC10749206 | biostudies-literature
Project description:Coronary artery disease (CAD) is a predominant cardiovascular condition influenced by risk factors, with an emphasis on major depressive disorder (MDD). However, the shared mechanisms and therapeutic targets for CAD and MDD remain incompletely comprehended. Functional enrichment analyses were conducted to investigate the pathways associated with the differentially expressed genes (DEGs) in the CAD and MDD datasets. Hub genes were identified utilizing the Protein-Protein Interaction network and Cytoscape software. The single sample gene set variation analysis was applied to assess immune cell infiltration in the CAD and MDD datasets. Weighted gene co-expression network analysis and molecular biological experiments were executed to evaluate these hub genes. Molecular docking was conducted to identify drug candidates targeting these hub genes. The overlapping DEGs between the CAD and MDD datasets were mainly enriched in the Herpes simplex virus 1 infection and the NF-kappa B signaling pathways. CDC42, NDUFB3, and TXN were validated within the eigengenes of the blue module, which exhibited a significant association with the CAD phenotype. The drug candidate GS-9620 was identified as a potential protective agent against both disorders. In conclusion, CDC42, NDUFB3, and TXN held potential as molecular biomarkers and therapeutic targets for the simultaneous treatment of CAD and MDD.
| S-EPMC11599718 | biostudies-literature
Project description:Background: The thalamus and habenula are thought to be key brain regions in the etiology of major depressive disorder (MDD); however, few studies have investigated the structural connection between them. We compared the number of white matter tracts between the thalamus and habenula between patient with MDD and normal controls (NCs). Methods: The habenula and thalamus region of interest masks were extracted from brain magnetic resonance imaging data and individual tractography analysis was performed. First, we compared the number of fiber connections from the habenula to the thalamus between the MDD (n = 34) and NC (n = 37) groups and also compared hemispherical differences to investigate possible asymmetries. Results: There was a significant difference in the number of tracts in the right habenula-left mediodorsal thalamus pair between the two groups. For hemispherical fiber connections, the waytotal ratio of the right ipsilateral tract between the thalamus and habenula was significantly higher than that of the left ipsilateral tract in both groups. Conclusion: The number of right habenula-left mediodorsal thalamus tracts was higher in patients with MDD than in NCs. These results indicate that MDD is related to the disintegration of the left thalamus-right habenula tract function with an increased number of tracts as a compensational mechanism.
| S-EPMC8440934 | biostudies-literature
Project description:Background: Psychiatric diagnosis is formulated by symptomatic classification; disease-specific neurophysiological phenotyping could help with its fundamental treatment. Here, we investigated brain phenotyping in patients with schizophrenia (SZ) and major depressive disorder (MDD) by using electroencephalography (EEG) and conducted machine-learning-based classification of the two diseases by using EEG components. Materials and Methods: We enrolled healthy controls (HCs) (n = 30) and patients with SZ (n = 34) and MDD (n = 33). An auditory P300 (AP300) task was performed, and the N1 and P3 components were extracted. Two-group classification was conducted using linear discriminant analysis (LDA) and support vector machine (SVM) classifiers. Positive and negative symptoms and depression and/or anxiety symptoms were evaluated. Results: Considering both the results of statistical comparisons and machine learning-based classifications, patients and HCs showed significant differences in AP300, with SZ and MDD showing lower N1 and P3 than HCs. In the sum of amplitudes and cortical sources, the findings for LDA with classification accuracy (SZ vs. HCs: 71.31%, MDD vs. HCs: 74.55%), sensitivity (SZ vs. HCs: 77.67%, MDD vs. HCs: 79.00%), and specificity (SZ vs. HCs: 64.00%, MDD vs. HCs: 69.67%) supported these results. The SVM classifier showed reasonable scores between SZ and HCs and/or MDD and HCs. The comparison between SZ and MDD showed low classification accuracy (59.71%), sensitivity (65.08%), and specificity (54.83%). Conclusions: Patients with SZ and MDD showed deficiencies in N1 and P3 components in the sum of amplitudes and cortical sources, indicating attentional dysfunction in both early and late sensory/cognitive gating input. The LDA and SVM classifiers in the AP300 are useful to distinguish patients with SZ and HCs and/or MDD and HCs.
| S-EPMC8549692 | biostudies-literature
Project description:Schizophrenia (SCZ), bipolar disorder (BP), and major depressive disorder (MDD) are the most common psychiatric disorders. Because there were lots of overlaps among these disorders from genetic epidemiology and molecular genetics, it is hard to realize the diagnoses of these psychiatric disorders. Currently, plenty of studies have been conducted for contributing to the diagnoses of these diseases. However, constructing a classification model with superior performance for differentiating SCZ, BP, and MDD samples is still a great challenge. In this study, the transcriptomic data was applied for discovering key genes and constructing a classification model. In this dataset, there were 268 samples including four groups (67 SCZ patients, 40 BP patients, 57 MDD patients, and 104 healthy controls), which were applied for constructing a classification model. First, 269 probes of differentially expressed genes (DEGs) among four sample groups were identified by the feature selection method. Second, these DEGs were validated by the literature review including disease relevance with the psychiatric disorders of these DEGs, the hub genes in the PPI (protein-protein interaction) network, and GO (gene ontology) terms and pathways. Third, a classification model was constructed using the identified DEGs by machine learning method to classify different groups. The ROC (receiver operator characteristic) curve and AUC (area under the curve) value were used to assess the classification capacity of the model. In summary, this classification model might provide clues for the diagnoses of these psychiatric disorders.
| S-EPMC9486057 | biostudies-literature
Project description:BackgroundDepressive disorder, particularly major depressive disorder (MDD), significantly impact individuals and society. Traditional analysis methods often suffer from subjectivity and may not capture complex, non-linear relationships between risk factors. Machine learning (ML) offers a data-driven approach to predict and diagnose depression more accurately by analyzing large and complex datasets.MethodsThis study utilized data from the National Health and Nutrition Examination Survey (NHANES) 2013-2014 to predict depression using six supervised ML models: Logistic Regression, Random Forest, Naive Bayes, Support Vector Machine (SVM), Extreme Gradient Boost (XGBoost), and Light Gradient Boosting Machine (LightGBM). Depression was assessed using the Patient Health Questionnaire (PHQ-9), with a score of 10 or higher indicating moderate to severe depression. The dataset was split into training and testing sets (80% and 20%, respectively), and model performance was evaluated using accuracy, sensitivity, specificity, precision, AUC, and F1 score. SHAP (SHapley Additive exPlanations) values were used to identify the critical risk factors and interpret the contributions of each feature to the prediction.ResultsXGBoost was identified as the best-performing model, achieving the highest accuracy, sensitivity, specificity, precision, AUC, and F1 score. SHAP analysis highlighted the most significant predictors of depression: the ratio family income to poverty (PIR), sex, hypertension, serum cotinine and hydroxycotine, BMI, education level, glucose levels, age, marital status, and renal function (eGFR).ConclusionWe developed ML models to predict depression and utilized SHAP for interpretation. This approach identifies key factors associated with depression, encompassing socioeconomic, demographic, and health-related aspects.
| S-EPMC11834192 | biostudies-literature
Project description:BackgroundMajor depressive disorder (MDD) is a global health challenge that impacts the quality of patients' lives severely. The disorder can manifest in many forms with different combinations of symptoms, which makes its clinical diagnosis difficult. Robust biomarkers are greatly needed to improve diagnosis and to understand the etiology of the disease. The main purpose of this study was to create a predictive model for MDD diagnosis based on peripheral blood transcriptomes.Materials and methodsWe collected nine RNA expression datasets for MDD patients and healthy samples from the Gene Expression Omnibus database. After a series of quality control and heterogeneity tests, 302 samples from six studies were deemed suitable for the study. R package "MetaOmics" was applied for systematic meta-analysis of genome-wide expression data. Receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic effectiveness of individual genes. To obtain a better diagnostic model, we also adopted the support vector machine (SVM), random forest (RF), k-nearest neighbors (kNN), and naive Bayesian (NB) tools for modeling, with the RF method being used for feature selection.ResultsOur analysis revealed six differentially expressed genes (AKR1C3, ARG1, KLRB1, MAFG, TPST1, and WWC3) with a false discovery rate (FDR) < 0.05 between MDD patients and control subjects. We then evaluated the diagnostic ability of these genes individually. With single gene prediction, we achieved a corresponding area under the curve (AUC) value of 0.63 ± 0.04, 0.67 ± 0.07, 0.70 ± 0.11, 0.64 ± 0.08, 0.68 ± 0.07, and 0.62 ± 0.09, respectively, for these genes. Next, we constructed the classifiers of SVM, RF, kNN, and NB with an AUC of 0.84 ± 0.09, 0.81 ± 0.10, 0.73 ± 0.11, and 0.83 ± 0.09, respectively, in validation datasets, suggesting that the SVM classifier might be superior for constructing an MDD diagnostic model. The final SVM classifier including 70 feature genes was capable of distinguishing MDD samples from healthy controls and yielded an AUC of 0.78 in an independent dataset.ConclusionThis study provides new insights into potential biomarkers through meta-analysis of GEO data. Constructing different machine learning models based on these biomarkers could be a valuable approach for diagnosing MDD in clinical practice.
| S-EPMC8249859 | biostudies-literature
Project description:IntroductionBrain dynamics offer a more direct insight into brain function than network structure, providing a profound understanding of dysregulation and control mechanisms within intricate brain systems. This study investigates the dynamics of functional brain networks in major depressive disorder (MDD) patients to decipher the mechanisms underlying brain dysfunction during depression and assess the impact of repetitive transcranial magnetic stimulation (rTMS) intervention.MethodsWe employed energy landscape analysis of functional magnetic resonance imaging (fMRI) data to examine the dynamics of functional brain networks in MDD patients. The analysis focused on key dynamical indicators of the default mode network (DMN), the salience network (SN), and the central execution network (CEN). The effects of rTMS intervention on these networks were also evaluated.ResultsOur findings revealed notable dynamical alterations in the pDMN, the vDMN, and the aSN, suggesting their potential as diagnostic and therapeutic markers. Particularly striking was the altered activity observed in the dDMN in the MDD group, indicative of patterns associated with depressive rumination. Notably, rTMS intervention partially reverses the identified dynamical alterations.DiscussionOur results shed light on the intrinsic dysfunction mechanisms of MDD from a dynamic standpoint and highlight the effects of rTMS intervention. The identified alterations in brain network dynamics provide promising analytical markers for the diagnosis and treatment of MDD. Future studies should further explore the clinical applications of these markers and the comprehensive dynamical effects of rTMS intervention.
| S-EPMC11920141 | biostudies-literature