Machine learning techniques are increasingly being used in making relevant predictions and inferences on
individual
subjects neuroimaging scan data. Previous studies have mostly focused on ...categorical discrimination of patients and matched healthy controls and more recently, on prediction of
individual
continuous variables such as clinical scores or age. However, these studies are greatly hampered by the large number of predictor variables (voxels) and low observations (subjects) also known as the
curse-of-dimensionality
or
small-n-large-p
problem. As a result, feature reduction techniques such as feature subset selection and dimensionality reduction are used to remove redundant predictor variables and experimental noise, a process which mitigates the
curse-of-dimensionality
and
small-n-large-p
effects. Feature reduction is an essential step before training a machine learning model to avoid
overfitting
and therefore improving model prediction
accuracy
and generalization ability. In this review, we discuss feature reduction techniques used with machine learning in neuroimaging studies.
The ability to exercise appropriate inhibitory control is critical in the regulation of body weight, but the exact mechanisms are not known. In this systematic review, we identified 37 studies that ...used specific neuropsychological tasks relevant to inhibitory control performance in obese participants with and without binge eating disorder (BED). We performed a meta-analysis of the studies that used the stop signal task (N=8). We further examined studies on the delay discounting task, the go/no-go task and the Stroop task in a narrative review. We found that inhibitory control is significantly impaired in obese adults and children compared to individuals with body weight within a healthy range (Standardized Mean Difference (SMD): 0.30; CI=0.00, 0.59, p=0.007). The presence of BED in obese individuals did not impact on task performance (SMD: 0.05; CI: -0.22, 0.32, p=0.419). Neuroimaging studies in obesity suggest that lower prefrontal cortex activity affects inhibitory control and BMI. In summary, impairment in inhibitory control is a critical feature associated with obesity and a potential target for clinical interventions.
Diffusion tensor imaging has the potential to be used as a neuroimaging marker of natural ageing and assist in elucidating trajectories of cerebral maturation and ageing. In this study, we applied a ...multivariate technique relevance vector regression (RVR) to predict individual subject's age using whole brain fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD) and radial diffusivity (RD) from a cohort of 188 subjects aged 4–85years. High prediction accuracy as derived from Pearson correlation coefficient of actual versus predicted age (FA — r=0.870 p<0.0001; MD — r=0.896 p<0.0001; AD — r=0.895 p<0.0001; RD — r=0.899 p<0.0001) was achieved. Cerebral white-matter regions that contributed to these predictions include; corpus callosum, cingulum bundles, posterior longitudinal fasciculus and the cerebral peduncle. A post-hoc analysis of these regions showed that FA follows a nonlinear rational-quadratic trajectory across the lifespan peaking at approximately 21.8years. The MD, RD and AD volumes were particularly useful for making predictions using grey matter cerebral regions. These results suggest that diffusion tensor imaging measurements can reliably predict individual subject's age and demonstrate that FA cerebral maturation and ageing patterns follow a non-linear trajectory with a noteworthy peaking age. These data will contribute to the understanding of neurobiology of cerebral maturation and ageing. Most notably, from a neuropsychiatric perspective our results may allow differentiation of cerebral changes that may occur due to natural maturation and ageing, and those due to developmental or neuropsychiatric disorders.
•Machine-learning is used to predict age using whole-brain diffusion tensor images.•A cross-validation approach is used to separate training and testing datasets.•White matter follows a rational-quadratic trajectory peaking at 21.8years.•Diffusivity in grey-matter tissue increases with maturation and ageing.
•Interpheron-alpha treatment in patients with chronic medical illness was associated with a reduction in plasma tryptophan levels.•Interferon-alpha treatment was associated with an increase in plasma ...kynurenine levels and kynurenine/tryptophan ratio activity.•Interpheron-alpha treatment was associated with increase in depression symptoms over time.
Dysregulated kynurenine (KYN) pathway has been implicated in the pathophysiology of depression. In this systematic review, we examined the relationship between kynurenine pathway metabolites (KYN, kynurenic acid KYNA, tryptophan TRP, quinolinic acid QUIN, KYN/TRP ratio) and depression symptoms in the context of pro-inflammatory activation and immune response. Out of 5,082 articles, fifteen studies were suitable; ten studies (N = 315 medically ill patients treated with interferon-alpha IFN-α) reported baseline and post-intervention plasma KYN, TRP and KYN/TRP ratios which were included in quantitative meta-analysis. Data from five studies were summarized (IFN-α, interferon-beta IFN-β, and lipopolysaccharide LPS). We found that IFN-α treatment in patients with chronic illnesses was associated with decreased TRP, increased levels of KYN and KYN/TRP ratio and depression scores from baseline to follow-up at both 4 and 24 weeks. Our findings suggest that increased risk of depression observed after immune-activating agents in patients with chronic medical illnesses is likely mediated by the kynurenine pathway. Further prospective studies are required to investigate the exact pathophysiology of the KYN pathway in depression.
Somatic complaints are often the presenting symptoms of major depressive disorder (MDD) in the outpatient context, because this may go unrecognized. It is well understood that MDD carries an ...increased risk of suicide. This study aimed to identify the risk factors and association with both MDD and suicidality among Han Chinese outpatients.
A multicenter study was carried out in 5189 outpatient adults (≥18 years old) in four general hospitals in Guangzhou, China. The 1392 patients who had the Patient Health Questionnaire-9 (PHQ-9) score ≥ 5, indicating depressive symptoms were offered an interview with a psychiatrist by the Mini International Neuropsychiatric Interview (MINI); 819 patients consented and completed the MINI interview. MINI module B was used to assess suicidality. Stepwise binary logistic models were used to estimate the relationship between a significant risk factor and suicide or MDD. According to with or without MDD, the secondary analysis was performed using the logistic regression model for the risk of suicidility.
The current prevalence of MDD and the one month prevalence of suicidality were 3.7% and 2.3% respectively. The odds ratio of suicidality in women was more than twice that in men (OR = 2.62; 95% CI 1.45-4.76). Other risk factors which were significantly associated with suicidality were: living alone, higher education, self-reported depression, getting psychiatric diagnoses (MDD, anxiety disorders, and bipolar disorders). Significant risk factors for MDD were also noticed, such as comorbid anxiety disorders, self-reported anxiety, insomnia, suicidal ideation.
It's a cross-sectional study in outpatient clinics using self-report questionnaires.
This study provides valuable data about the risk factors and association of MDD and suicide risk in adult outpatients in Han Chinese. Those factors allow better the employment of preventative measures.
Bipolar disorder (BD) is a chronic, debilitating illness with a global prevalence of up to 4.8%. The importance of understanding how dysfunctional mitochondria and mitophagy contribute to cell ...survival and death in BD is becoming increasingly apparent. Therefore, the purpose of this study was to evaluate the mitophagic pathway and NLRP3 inflammasome activation in peripheral blood mononuclear cells (PBMCs) of patients with BD and healthy individuals. Since 18-kDa translocator protein (TSPO) plays an important role in regulating mitochondrial function and since TSPO itself impairs cellular mitophagy, we also investigated the changes in the TSPO-related pathway. Our results showed that patients with BD had lower levels of Parkin, p62/SQSTM1 and LC3A and an upregulation of TSPO pathway proteins (TSPO and VDAC), both in terms of mRNA and protein levels. Additionally, we found a negative correlation between mitophagy-related proteins and TSPO levels, while VDAC correlated negatively with p62/SQSTM1 and LC3 protein levels. Moreover, we found that the gene expression levels of the NLRP3-related proteins NLRP3, ASC, and pro-casp1 were upregulated in BD patients, followed by an increase in caspase-1 activity as well as IL-1β and IL-18 levels. As expected, there was a strong positive correlation between NLRP3-related inflammasome activation and TSPO-related proteins. The data reported here suggest that TSPO-VDAC complex upregulation in BD patients, the simultaneous downregulation of mitophagic proteins and NLRP3 inflammasome activation could lead to an accumulation of dysfunctional mitochondria, resulting in inflammation and apoptosis. In summary, the findings of this study provide novel evidence that mitochondrial dysfunction measured in peripheral blood is associated with BD.
The importance of tryptophan as a precursor for neuroactive compounds has long been acknowledged. The metabolism of tryptophan along the kynurenine pathway and its involvement in mental disorders is ...an emerging area in psychiatry. We performed a meta-analysis to examine the differences in kynurenine metabolites in major depressive disorder (MDD), bipolar disorder (BD), and schizophrenia (SZ). Electronic databases were searched for studies that assessed metabolites involved in the kynurenine pathway (tryptophan, kynurenine, kynurenic acid, quinolinic acid, 3-hydroxykynurenine, and their associate ratios) in people with MDD, SZ, or BD, compared to controls. We computed the difference in metabolite concentrations between people with MDD, BD, or SZ, and controls, presented as Hedges' g with 95% confidence intervals. A total of 101 studies with 10,912 participants were included. Tryptophan and kynurenine are decreased across MDD, BD, and SZ; kynurenic acid and the kynurenic acid to quinolinic acid ratio are decreased in mood disorders (i.e., MDD and BD), whereas kynurenic acid is not altered in SZ; kynurenic acid to 3-hydroxykynurenine ratio is decreased in MDD but not SZ. Kynurenic acid to kynurenine ratio is decreased in MDD and SZ, and the kynurenine to tryptophan ratio is increased in MDD and SZ. Our results suggest that there is a shift in the tryptophan metabolism from serotonin to the kynurenine pathway, across these psychiatric disorders. In addition, a differential pattern exists between mood disorders and SZ, with a preferential metabolism of kynurenine to the potentially neurotoxic quinolinic acid instead of the neuroprotective kynurenic acid in mood disorders but not in SZ.
Abstract Rationale The neurotrophin hypothesis of major depressive disorder (MDD) postulates that this illness results from aberrant neurogenesis in brain regions that regulates emotion and memory. ...Notwithstanding this theory has primarily implicated BDNF in the neurobiology of MDD. Recent evidence suggests that other trophic factors namely GDNF, VEGF and IGF-1 may also be involved. Purpose The present review aimed to critically summarize evidence regarding changes in GDNF, IGF-1 and VEGF in individuals with MDD compared to healthy controls. In addition, we also evaluated the role of these mediators as potential treatment response biomarkers for MDD. Methods: A comprehensive review of original studies studies measuring peripheral, central or mRNA levels of GDNF, IGF-1 or VEGF in patients with MDD was conducted. The PubMed/MEDLINE database was searched for peer-reviewed studies published in English through June 2nd , 2015. Results: Most studies reported a reduction in peripheral GDNF and its mRNA levels in MDD patients versus controls. In contrast, IGF-1 levels in MDD patients compared to controls were discrepant across studies. Finally, most studies reported high peripheral VEGF levels and mRNA expression in MDD patients compared to healthy controls. Conclusions: GDNF, IGF-1 and VEGF levels and their mRNA expression appear to be differentially altered in MDD patients compared to healthy individuals, indicating that these molecules might play an important role in the pathophysiology of depression and antidepressant action of therapeutic interventions.
Despite the important advances in the understanding of the pathophysiology of MDD, a large proportion of depressed patients do not respond well to currently available pharmacological agents. The ...present review focuses on new targets and future directions in the pharmacological treatment of MDD. Novel agents and their efficacy in the treatment of depression are discussed, with a focus on the respectively target pathophysiological pathways and the level of available evidence. Although it is expected that classic antidepressants will remain the cornerstone of MDD treatment, at least for the near future, a large number of novel compounds is currently under investigation as for their efficacy in the treatment of MDD, many of which with promising results.
•Many patients with depression do not respond well to currently available agents.•Most available antidepressants act by inhibiting the reuptake of monoamines.•Novel treatments have targeted mechanisms beyond the monoaminergic system.
Identifying biomarkers in schizophrenia during the first episode without the confounding effects of treatment has been challenging. Leveraging these biomarkers to establish diagnosis and make ...individualized predictions of future treatment responses to antipsychotics would be of great value, but there has been limited progress. In this study, by using machine learning algorithms and the functional connections of the superior temporal cortex, we successfully identified the first-episode drug-naive (FEDN) schizophrenia patients (accuracy 78.6%) and predict their responses to antipsychotic treatment (accuracy 82.5%) at an individual level. The functional connections (FC) were derived using the mutual information and the correlations, between the blood-oxygen-level dependent signals of the superior temporal cortex and other cortical regions acquired with the resting-state functional magnetic resonance imaging. We also found that the mutual information and correlation FC was informative in identifying individual FEDN schizophrenia and prediction of treatment response, respectively. The methods and findings in this paper could provide a critical step toward individualized identification and treatment response prediction in first-episode drug-naive schizophrenia, which could complement other biomarkers in the development of precision medicine approaches for this severe mental disorder.
PDF
