ABSTRACT
There is limited convergence in neuroimaging investigations into volumes of subcortical brain regions in social anxiety disorder (SAD). The inconsistent findings may arise from variations in methodological approaches across studies, including sample selection based on age and clinical characteristics. The ENIGMA-Anxiety Working Group initiated a global mega-analysis to determine whether differences in subcortical volumes can be detected in adults and adolescents with SAD relative to healthy controls. Volumetric data from 37 international samples with 1115 SAD patients and 2775 controls were obtained from ENIGMA-standardized protocols for image segmentation and quality assurance. Linear mixed-effects analyses were adjusted for comparisons across seven subcortical regions in each hemisphere using family-wise error (FWE)-correction. Mixed-effects d effect sizes were calculated. In the full sample, SAD patients showed smaller bilateral putamen volume than controls (left: d = -0.077, pFWE = 0.037; right: d = -0.104, pFWE = 0.001), and a significant interaction between SAD and age was found for the left putamen (r = -0.034, pFWE = 0.045). Smaller bilateral putamen volumes (left: d = -0.141, pFWE < 0.001; right: d = -0.158, pFWE < 0.001) and larger bilateral pallidum volumes (left: d = 0.129, pFWE = 0.006; right: d = 0.099, pFWE = 0.046) were detected in adult SAD patients relative to controls, but no volumetric differences were apparent in adolescent SAD patients relative to controls. Comorbid anxiety disorders and age of SAD onset were additional determinants of SAD-related volumetric differences in subcortical regions. To conclude, subtle volumetric alterations in subcortical regions in SAD were detected. Heterogeneity in age and clinical characteristics may partly explain inconsistencies in previous findings. The association between alterations in subcortical volumes and SAD illness progression deserves further investigation, especially from adolescence into adulthood.
Subject(s)
Phobia, Social , Adult , Adolescent , Humans , Magnetic Resonance Imaging/methods , Brain , Anxiety , Neuroimaging/methodsABSTRACT
OBJECTIVES: The Global Aging & Geriatric Experiments in Bipolar Disorder Database (GAGE-BD) project pools archival datasets on older age bipolar disorder (OABD). An initial Wave 1 (W1; n = 1369) analysis found both manic and depressive symptoms reduced among older patients. To replicate this finding, we gathered an independent Wave 2 (W2; n = 1232, mean ± standard deviation age 47.2 ± 13.5, 65% women, 49% aged over 50) dataset. DESIGN/METHODS: Using mixed models with random effects for cohort, we examined associations between BD symptoms, somatic burden and age and the contribution of these to functioning in W2 and the combined W1 + W2 sample (n = 2601). RESULTS: Compared to W1, the W2 sample was younger (p < 0.001), less educated (p < 0.001), more symptomatic (p < 0.001), lower functioning (p < 0.001) and had fewer somatic conditions (p < 0.001). In the full W2, older individuals had reduced manic symptom severity, but age was not associated with depression severity. Age was not associated with functioning in W2. More severe BD symptoms (mania p ≤ 0.001, depression p ≤ 0.001) were associated with worse functioning. Older age was significantly associated with higher somatic burden in the W2 and the W1 + W2 samples, but this burden was not associated with poorer functioning. CONCLUSIONS: In a large, independent sample, older age was associated with less severe mania and more somatic burden (consistent with previous findings), but there was no association of depression with age (different from previous findings). Similar to previous findings, worse BD symptom severity was associated with worse functioning, emphasizing the need for symptom relief in OABD to promote better functioning.
Subject(s)
Bipolar Disorder , Medically Unexplained Symptoms , Aged , Female , Humans , Male , Middle Aged , Aging , Bipolar Disorder/epidemiology , Bipolar Disorder/diagnosis , Databases, Factual , Mania , AdultABSTRACT
Identifying brain alterations associated with suicidal thoughts and behaviors (STBs) in young people is critical to understanding their development and improving early intervention and prevention. The ENIGMA Suicidal Thoughts and Behaviours (ENIGMA-STB) consortium analyzed neuroimaging data harmonized across sites to examine brain morphology associated with STBs in youth. We performed analyses in three separate stages, in samples ranging from most to least homogeneous in terms of suicide assessment instrument and mental disorder. First, in a sample of 577 young people with mood disorders, in which STBs were assessed with the Columbia Suicide Severity Rating Scale (C-SSRS). Second, in a sample of young people with mood disorders, in which STB were assessed using different instruments, MRI metrics were compared among healthy controls without STBs (HC; N = 519), clinical controls with a mood disorder but without STBs (CC; N = 246) and young people with current suicidal ideation (N = 223). In separate analyses, MRI metrics were compared among HCs (N = 253), CCs (N = 217), and suicide attempters (N = 64). Third, in a larger transdiagnostic sample with various assessment instruments (HC = 606; CC = 419; Ideation = 289; HC = 253; CC = 432; Attempt=91). In the homogeneous C-SSRS sample, surface area of the frontal pole was lower in young people with mood disorders and a history of actual suicide attempts (N = 163) than those without a lifetime suicide attempt (N = 323; FDR-p = 0.035, Cohen's d = 0.34). No associations with suicidal ideation were found. When examining more heterogeneous samples, we did not observe significant associations. Lower frontal pole surface area may represent a vulnerability for a (non-interrupted and non-aborted) suicide attempt; however, more research is needed to understand the nature of its relationship to suicide risk.
Subject(s)
Suicidal Ideation , Suicide, Attempted , Adolescent , Humans , Brain , Neuroimaging/methods , Mood DisordersABSTRACT
The ENIGMA group on Generalized Anxiety Disorder (ENIGMA-Anxiety/GAD) is part of a broader effort to investigate anxiety disorders using imaging and genetic data across multiple sites worldwide. The group is actively conducting a mega-analysis of a large number of brain structural scans. In this process, the group was confronted with many methodological challenges related to study planning and implementation, between-country transfer of subject-level data, quality control of a considerable amount of imaging data, and choices related to statistical methods and efficient use of resources. This report summarizes the background information and rationale for the various methodological decisions, as well as the approach taken to implement them. The goal is to document the approach and help guide other research groups working with large brain imaging data sets as they develop their own analytic pipelines for mega-analyses.
Subject(s)
Anxiety Disorders/diagnostic imaging , Cerebral Cortex/diagnostic imaging , Data Interpretation, Statistical , Meta-Analysis as Topic , Multicenter Studies as Topic , Neuroimaging , Humans , Multicenter Studies as Topic/methods , Multicenter Studies as Topic/standards , Neuroimaging/methods , Neuroimaging/standardsABSTRACT
BACKGROUND: There is still little knowledge of objective suicide risk stratification. METHODS: This study aims to develop models using machine-learning approaches to predict suicide attempt (1) among survey participants in a nationally representative sample and (2) among participants with lifetime major depressive episodes. We used a cohort called the National Epidemiologic Survey on Alcohol and Related Conditions (NESARC) that was conducted in two waves and included a nationally representative sample of the adult population in the United States. Wave 1 involved 43 093 respondents and wave 2 involved 34 653 completed face-to-face reinterviews with wave 1 participants. Predictor variables included clinical, stressful life events, and sociodemographic variables from wave 1; outcome included suicide attempt between wave 1 and wave 2. RESULTS: The model built with elastic net regularization distinguished individuals who had attempted suicide from those who had not with an area under the ROC curve (AUC) of 0.89, balanced accuracy 81.86%, specificity 89.22%, and sensitivity 74.51% for the general population. For participants with lifetime major depressive episodes, AUC was 0.89, balanced accuracy 81.64%, specificity 85.86%, and sensitivity 77.42%. The most important predictor variables were a diagnosis of borderline personality disorder, post-traumatic stress disorder, and being of Asian descent for the model in all participants; and previous suicide attempt, borderline personality disorder, and overnight stay in hospital because of depressive symptoms for the model in participants with lifetime major depressive episodes. Random forest and artificial neural networks had similar performance. CONCLUSIONS: Risk for suicide attempt can be estimated with high accuracy.
Subject(s)
Alcohol-Related Disorders , Depressive Disorder, Major , Stress Disorders, Post-Traumatic , Adult , Humans , United States/epidemiology , Suicide, Attempted , Depressive Disorder, Major/epidemiology , Depressive Disorder, Major/diagnosis , Prospective Studies , Alcohol-Related Disorders/epidemiology , Risk FactorsABSTRACT
Abnormalities within frontal lobe gray and white matter of bipolar disorder (BD) patients have been consistently reported in adult and pediatric studies, yet little is known about the neurochemistry of the anterior white matter (AWM) in pediatric BD and how medication status may affect it. The present cross-sectional 3T 1H MRS study is the first to use a multivoxel approach to study the AWM of BD youth. Absolute metabolite levels from four bilateral AWM voxels were collected from 49 subjects between the ages of 8 and 18 (25 healthy controls (HC); 24 BD) and quantified. Our study found BD subjects to have lower levels of N-acetylaspartate (NAA) and glycerophosphocholine plus phosphocholine (GPC + PC), metabolites that are markers of neuronal viability and phospholipid metabolism and have also been implicated in adult BD. Further analysis indicated that the observed patterns were mostly driven by BD subjects who were medicated at the time of scanning and had an ADHD diagnosis. Although limited by possible confounding effects of mood state, medication, and other mood comorbidities, these findings serve as evidence of altered neurochemistry in BD youth that is sensitive to medication status and ADHD comorbidity.
Subject(s)
Bipolar Disorder , Neurochemistry , White Matter , Adolescent , Adult , Child , Cross-Sectional Studies , Humans , Proton Magnetic Resonance Spectroscopy , White Matter/diagnostic imagingABSTRACT
Emerging evidence suggests that obesity impacts brain physiology at multiple levels. Here we aimed to clarify the relationship between obesity and brain structure using structural MRI (n = 6420) and genetic data (n = 3907) from the ENIGMA Major Depressive Disorder (MDD) working group. Obesity (BMI > 30) was significantly associated with cortical and subcortical abnormalities in both mass-univariate and multivariate pattern recognition analyses independent of MDD diagnosis. The most pronounced effects were found for associations between obesity and lower temporo-frontal cortical thickness (maximum Cohen´s d (left fusiform gyrus) = -0.33). The observed regional distribution and effect size of cortical thickness reductions in obesity revealed considerable similarities with corresponding patterns of lower cortical thickness in previously published studies of neuropsychiatric disorders. A higher polygenic risk score for obesity significantly correlated with lower occipital surface area. In addition, a significant age-by-obesity interaction on cortical thickness emerged driven by lower thickness in older participants. Our findings suggest a neurobiological interaction between obesity and brain structure under physiological and pathological brain conditions.
Subject(s)
Depressive Disorder, Major , Aged , Brain/diagnostic imaging , Cerebral Cortex , Depressive Disorder, Major/genetics , Humans , Magnetic Resonance Imaging , Obesity/genetics , Risk FactorsABSTRACT
BACKGROUND: The clinical effects of smartphone-based interventions for bipolar disorder (BD) have yet to be established. OBJECTIVES: To examine the efficacy of smartphone-based interventions in BD and how the included studies reported user-engagement indicators. METHODS: We conducted a systematic search on January 24, 2022, in PubMed, Scopus, Embase, APA PsycINFO, and Web of Science. We used random-effects meta-analysis to calculate the standardized difference (Hedges' g) in pre-post change scores between smartphone intervention and control conditions. The study was pre-registered with PROSPERO (CRD42021226668). RESULTS: The literature search identified 6034 studies. Thirteen articles fulfilled the selection criteria. We included seven RCTs and performed meta-analyses comparing the pre-post change in depressive and (hypo)manic symptom severity, functioning, quality of life, and perceived stress between smartphone interventions and control conditions. There was significant heterogeneity among studies and no meta-analysis reached statistical significance. Results were also inconclusive regarding affective relapses and psychiatric readmissions. All studies reported positive user-engagement indicators. CONCLUSION: We did not find evidence to support that smartphone interventions may reduce the severity of depressive or manic symptoms in BD. The high heterogeneity of studies supports the need for expert consensus to establish ideally how studies should be designed and the use of more sensitive outcomes, such as affective relapses and psychiatric hospitalizations, as well as the quantification of mood instability. The ISBD Big Data Task Force provides preliminary recommendations to reduce the heterogeneity and achieve more valid evidence in the field.
Subject(s)
Bipolar Disorder , Smartphone , Big Data , Bipolar Disorder/psychology , Humans , Quality of Life , RecurrenceABSTRACT
BACKGROUND: Altered peripheral immune/inflammatory system and brain volumetric changes have been implicated in the pathophysiology of bipolar disorder (BD). This study aimed to evaluate how peripheral levels of cytokines are related to volumetric brain changes in euthymic patients with BD. METHODS: Euthymic patients with BD (n = 21) and healthy controls (n = 22) were enrolled in this exploratory study. Blood samples were collected on the same day of clinical assessment and neuroimaging. Cytokines were measured through cytometric bead array method. Neuroimaging data were acquired using a sagittal three-dimensional magnetic resonance imaging T1-weighted fast field echo sequence and was processed using FreeSurfer. RESULTS: Compared to controls, BD patients had significantly lower volumes in the cingulate, medial-orbitofrontal (MOF) and parahippocampal regions. We found a negative correlation between right MOF volume and interferon-gamma levels (ß = -0.431, P = .049) and a positive correlation between interleukin-10 levels and left posterior cingulate volume (ß = 0.457, P = .048). CONCLUSION: Our results support the involvement of inflammatory pathways in structural brain changes in BD.
Subject(s)
Bipolar Disorder , Humans , Gray Matter/pathology , Interleukin-10 , Inflammation Mediators , Interferon-gamma , Magnetic Resonance Imaging/methods , BrainABSTRACT
BACKGROUND: Bipolar disorder (BD) is a severe psychiatric disorder associated with structural and functional brain abnormalities, some of which have been found in unaffected relatives as well. In this study, we examined the potential role of decreased fractional anisotropy (FA) as a BD endophenotype, in adolescents at high risk for BD. METHODS: We included 15 offspring of patients with BD, 16 pediatric BD patients, and 16 matched controls. Diffusion weighted scans were obtained on a 3T scanner using an echo-planar sequence. Scans were segmented using FreeSurfer. RESULTS: Our results showed significantly decreased FA in six brain areas of offspring group; left superior temporal gyrus (LSTG; P < .0001), left transverse temporal gyrus (LTTG; P = .002), left banks of the superior temporal sulcus (LBSTS; P = .002), left anterior cingulum (LAC; P = .003), right temporal pole (RTP; P = .004) and left frontal pole (LFP; P = .017). On analysis, LSTG, LAC, and RTP demonstrated a potential to be an endophenotype when comparing all three groups. FA values in three regions, LBSTS, LTTG, and LFP were increased only in controls. CONCLUSION: Our findings point at decreased FA as a possible endophenotype for BD, as they were found in children of patients with BD. Most of these areas were previously found to have morphological and functional changes in adult and pediatric BD, and are thought to play important roles in affected domains of functioning. Prospective follow up studies should be performed to detect reliability of decreased FA as an endophenotype and effects of treatment on FA.
Subject(s)
Bipolar Disorder , Adult , Adolescent , Humans , Child , Anisotropy , Bipolar Disorder/diagnosis , Endophenotypes , Diffusion Tensor Imaging/methods , Prospective Studies , Reproducibility of ResultsABSTRACT
Bipolar disorders (BDs) are among the leading causes of morbidity and disability. Objective biological markers, such as those based on brain imaging, could aid in clinical management of BD. Machine learning (ML) brings neuroimaging analyses to individual subject level and may potentially allow for their diagnostic use. However, fair and optimal application of ML requires large, multi-site datasets. We applied ML (support vector machines) to MRI data (regional cortical thickness, surface area, subcortical volumes) from 853 BD and 2167 control participants from 13 cohorts in the ENIGMA consortium. We attempted to differentiate BD from control participants, investigated different data handling strategies and studied the neuroimaging/clinical features most important for classification. Individual site accuracies ranged from 45.23% to 81.07%. Aggregate subject-level analyses yielded the highest accuracy (65.23%, 95% CI = 63.47-67.00, ROC-AUC = 71.49%, 95% CI = 69.39-73.59), followed by leave-one-site-out cross-validation (accuracy = 58.67%, 95% CI = 56.70-60.63). Meta-analysis of individual site accuracies did not provide above chance results. There was substantial agreement between the regions that contributed to identification of BD participants in the best performing site and in the aggregate dataset (Cohen's Kappa = 0.83, 95% CI = 0.829-0.831). Treatment with anticonvulsants and age were associated with greater odds of correct classification. Although short of the 80% clinically relevant accuracy threshold, the results are promising and provide a fair and realistic estimate of classification performance, which can be achieved in a large, ecologically valid, multi-site sample of BD participants based on regional neurostructural measures. Furthermore, the significant classification in different samples was based on plausible and similar neuroanatomical features. Future multi-site studies should move towards sharing of raw/voxelwise neuroimaging data.
Subject(s)
Bipolar Disorder , Bipolar Disorder/diagnostic imaging , Brain/diagnostic imaging , Humans , Machine Learning , Magnetic Resonance Imaging , NeuroimagingABSTRACT
No neuroanatomical substrates for distinguishing between depression of bipolar disorder (dBD) and major depressive disorder (dMDD) are currently known. The aim of the current multicenter study was to identify neuroanatomical patterns distinct to depressed patients with the two disorders. Further analysis was conducted on an independent sample to enable generalization of results. We directly compared MR images of these subjects using voxel-based morphometry (VBM) and a support vector machine (SVM) algorithm using 1531 participants. The VBM analysis showed significantly reduced gray matter volumes in the bilateral dorsolateral prefrontal (DLPFC) and anterior cingulate cortices (ACC) in patients with dBD compared with those with dMDD. Patients with the two disorders shared small gray matter volumes for the right ACC and left inferior frontal gyrus when compared with healthy subjects. Voxel signals in these regions during SVM analysis contributed to an accurate classification of the two diagnoses. The VBM and SVM results in the second cohort also supported these results. The current findings provide new evidence that gray matter volumes in the DLPFC and ACC are core regions in displaying shared and distinct neuroanatomical substrates and can shed light on elucidation of neural mechanism for depression within the bipolar/major depressive disorder continuum.
Subject(s)
Bipolar Disorder/diagnostic imaging , Depressive Disorder, Major/diagnostic imaging , Gyrus Cinguli/diagnostic imaging , Magnetic Resonance Imaging/methods , Prefrontal Cortex/diagnostic imaging , Adult , Bipolar Disorder/psychology , Cohort Studies , Depressive Disorder, Major/psychology , Female , Humans , Male , Middle AgedABSTRACT
OBJECTIVES: The International Society for Bipolar Disorders Big Data Task Force assembled leading researchers in the field of bipolar disorder (BD), machine learning, and big data with extensive experience to evaluate the rationale of machine learning and big data analytics strategies for BD. METHOD: A task force was convened to examine and integrate findings from the scientific literature related to machine learning and big data based studies to clarify terminology and to describe challenges and potential applications in the field of BD. We also systematically searched PubMed, Embase, and Web of Science for articles published up to January 2019 that used machine learning in BD. RESULTS: The results suggested that big data analytics has the potential to provide risk calculators to aid in treatment decisions and predict clinical prognosis, including suicidality, for individual patients. This approach can advance diagnosis by enabling discovery of more relevant data-driven phenotypes, as well as by predicting transition to the disorder in high-risk unaffected subjects. We also discuss the most frequent challenges that big data analytics applications can face, such as heterogeneity, lack of external validation and replication of some studies, cost and non-stationary distribution of the data, and lack of appropriate funding. CONCLUSION: Machine learning-based studies, including atheoretical data-driven big data approaches, provide an opportunity to more accurately detect those who are at risk, parse-relevant phenotypes as well as inform treatment selection and prognosis. However, several methodological challenges need to be addressed in order to translate research findings to clinical settings.
Subject(s)
Big Data , Bipolar Disorder/therapy , Clinical Decision-Making , Machine Learning , Suicidal Ideation , Advisory Committees , Bipolar Disorder/epidemiology , Data Science , Humans , Phenotype , Prognosis , Risk AssessmentABSTRACT
OBJECTIVES: The authors aim to investigate the association between white matter integrity and accelerated brain aging in late-life depression. METHODS: The authors measured senescence-associated secretory phenotype (SASP) index proteins, cognitive performance, and MRI diffusion tensor imaging (DTI) measures of fractional anisotropy and mean diffusivity-based indices of white matter microstructure measures in 56 older adults with remitted late-life depression. RESULTS: Higher SASP index was significantly correlated with older age (râ¯=â¯0.42, pâ¯=â¯0.001) and worse executive function performance (r = -0.27, pâ¯=â¯0.04). After controlling for the effect of age, overall cognitive performance, and white matter hyperintensities, the association between SASP and left and right cingulate bundle mean diffusivity remained statistically significant. CONCLUSIONS: Our data suggest that, in the context of late-life depression, SASP proteins are associated with microstructural abnormalities in white matter tracts in brain and worse executive function performance.
Subject(s)
Cellular Senescence , Cognition , Depressive Disorder, Major/diagnostic imaging , Executive Function , Gyrus Cinguli/diagnostic imaging , White Matter/diagnostic imaging , Age Factors , Aged , Depressive Disorder, Major/metabolism , Depressive Disorder, Major/psychology , Diffusion Magnetic Resonance Imaging , Female , Humans , MaleABSTRACT
BACKGROUND AND AIMS: Cognitive impairments are primary hallmarks symptoms of bipolar disorder (BD). Whether these deficits are markers of vulnerability or symptoms of the disease is still unclear. This study used a component-wise gradient (CGB) machine learning algorithm to identify cognitive measures that could accurately differentiate pediatric BD, unaffected offspring of BD parents, and healthy controls. METHODS: 59 healthy controls (HC; 11.19 ± 3.15 yo; 30 girls), 119 children and adolescents with BD (13.31 ± 3.02 yo, 52 girls) and 49 unaffected offspring of BD parents (UO; 9.36 ± 3.18 yo; 22 girls) completed the CANTAB cognitive battery. RESULTS: CGB achieved accuracy of 73.2% and an AUROC of 0.785 in classifying individuals as either BD or non-BD on a dataset held out for validation for testing. The strongest cognitive predictors of BD were measures of processing speed and affective processing. Measures of cognition did not differentiate between UO and HC. CONCLUSIONS: Alterations in processing speed and affective processing are markers of BD in pediatric populations. Longitudinal studies should determine whether UO with a cognitive profile similar to that of HC are at less or equal risk for mood disorders. Future studies should include relevant measures for BD such as verbal memory and genetic risk scores.
Subject(s)
Bipolar Disorder/diagnosis , Bipolar Disorder/psychology , Cognition Disorders/diagnosis , Cognition Disorders/psychology , Neuropsychological Tests , Adolescent , Child , Cognition/physiology , Female , Humans , Longitudinal Studies , Male , Memory/physiology , Parents/psychologyABSTRACT
OBJECTIVE: Only few studies have investigated cortical thickness in anorexia nervosa (AN), and it is unclear whether patterns of altered cortical thickness can be identified as biomarkers for AN. METHOD: Cortical thickness was measured in 19 adult women with restricting-type AN, 24 individuals recovered from restricting-type AN (REC-AN) and 24 healthy controls. Those individuals with current or recovered from AN had previously shown altered regional cortical volumes across orbitofrontal cortex and insula. A linear relevance vector machine-learning algorithm estimated patterns of regional thickness across 24 subdivisions of those regions. RESULTS: Region-based analysis showed higher cortical thickness in AN and REC-AN, compared to controls, in the right medial orbital (olfactory) sulcus, and greater cortical thickness for short insular gyri in REC-AN versus controls bilaterally. The machine-learning algorithm identified a pattern of relatively higher right orbital, right insular and left middle frontal cortical thickness, but lower left orbital, right middle and inferior frontal, and bilateral superior frontal cortical thickness specific to AN versus controls (74% specificity and 74% sensitivity, χ2 p < .004); predicted probabilities differed significantly between AN and controls (p < .023). No pattern significantly distinguished the REC-AN group from controls. CONCLUSIONS: Higher cortical thickness in medial orbitofrontal cortex and insula probably contributes to higher gray matter volume in AN in those regions. The machine-learning algorithm identified a mixed pattern of mostly higher orbital and insular, but relatively lower superior frontal cortical thickness in individuals with current AN. These novel results suggest that regional cortical thickness patterns could be state markers for AN.
Subject(s)
Anorexia Nervosa/diagnosis , Biomarkers/chemistry , Cerebral Cortex/abnormalities , Magnetic Resonance Imaging/methods , Adult , Female , Humans , Young AdultABSTRACT
Diagnosis, clinical management and research of psychiatric disorders remain subjective - largely guided by historically developed categories which may not effectively capture underlying pathophysiological mechanisms of dysfunction. Here, we report a novel approach of identifying and validating distinct and biologically meaningful clinical phenotypes of bipolar disorders using both unsupervised and supervised machine learning techniques. First, neurocognitive data were analyzed using an unsupervised machine learning approach and two distinct clinical phenotypes identified namely; phenotype I and phenotype II. Second, diffusion weighted imaging scans were pre-processed using the tract-based spatial statistics (TBSS) method and 'skeletonized' white matter fractional anisotropy (FA) and mean diffusivity (MD) maps extracted. The 'skeletonized' white matter FA and MD maps were entered into the Elastic Net machine learning algorithm to distinguish individual subjects' phenotypic labels (e.g. phenotype I vs. phenotype II). This calculation was performed to ascertain whether the identified clinical phenotypes were biologically distinct. Original neurocognitive measurements distinguished individual subjects' phenotypic labels with 94% accuracy (sensitivity=92%, specificity=97%). TBSS derived FA and MD measurements predicted individual subjects' phenotypic labels with 76% and 65% accuracy respectively. In addition, individual subjects belonging to phenotypes I and II were distinguished from healthy controls with 57% and 92% accuracy respectively. Neurocognitive task variables identified as most relevant in distinguishing phenotypic labels included; Affective Go/No-Go (AGN), Cambridge Gambling Task (CGT) coupled with inferior fronto-occipital fasciculus and callosal white matter pathways. These results suggest that there may exist two biologically distinct clinical phenotypes in bipolar disorders which can be identified from healthy controls with high accuracy and at an individual subject level. We suggest a strong clinical utility of the proposed approach in defining and validating biologically meaningful and less heterogeneous clinical sub-phenotypes of major psychiatric disorders.
Subject(s)
Bipolar Disorder/diagnosis , Diffusion Magnetic Resonance Imaging/methods , Machine Learning , Neuroimaging/methods , White Matter/diagnostic imaging , Adult , Bipolar Disorder/diagnostic imaging , Bipolar Disorder/physiopathology , Female , Humans , Male , Middle Aged , Phenotype , Sensitivity and SpecificitySubject(s)
Machine Learning , Schizophrenia , Brain , Humans , Randomized Controlled Trials as Topic , Treatment OutcomeABSTRACT
BACKGROUND: Major psychiatric disorders are increasingly being conceptualized as 'neurodevelopmental', because they are associated with aberrant brain maturation. Several studies have hypothesized that a brain maturation index integrating patterns of neuroanatomical measurements may reliably identify individual subjects deviating from a normative neurodevelopmental trajectory. However, while recent studies have shown great promise in developing accurate brain maturation indices using neuroimaging data and multivariate machine learning techniques, this approach has not been validated using a large sample of longitudinal data from children and adolescents. METHODS: T1-weighted scans from 303 healthy subjects aged 4.88 to 18.35years were acquired from the National Institute of Health (NIH) pediatric repository (http://www.pediatricmri.nih.gov). Out of the 303 subjects, 115 subjects were re-scanned after 2years. The least absolute shrinkage and selection operator algorithm (LASSO) was 'trained' to integrate neuroanatomical changes across chronological age and predict each individual's brain maturity. The resulting brain maturation index was developed using first-visit scans only, and was validated using second-visit scans. RESULTS: We report a high correlation between the first-visit chronological age and brain maturation index (r=0.82, mean absolute error or MAE=1.69years), and a high correlation between the second-visit chronological age and brain maturation index (r=0.83, MAE=1.71years). The brain maturation index captured neuroanatomical volume changes between the first and second visits with an MAE of 0.27years. CONCLUSIONS: The brain maturation index developed in this study accurately predicted individual subjects' brain maturation longitudinally. Due to its strong clinical potentials in identifying individuals with an abnormal brain maturation trajectory, the brain maturation index may allow timely clinical interventions for individuals at risk for psychiatric disorders.