Using structural MRI to identify individuals at genetic risk for bipolar disorders: a 2-cohort, machine learning study

Abstract

IntroductionThe diagnostic system in psychiatry continues to be based on behavioural symptoms rather than biomarkers. This complicates clinical work and research as it introduces marked hetero geneity. Neuroimaging has the unique ability to noninvasively investigate brain structure and function. Yet, the diag nostic promise of neuroimaging in psychiatry has not been fully realized. Brain imaging studies have shown replicated evidence for neuroanatomical changes in groups of participants with psychiatric disorders relative to controls. However, these statistical group differences have low specificity and sensitivity and thus are of limited diagnostic use on the level of individual participants. 1-3The problem of low sensitivity and specificity may be overcome by novel methods of neuroimaging analyses, such as machine learning (ML).1,2 Traditional methods of MRI data analysis focus on relatively large, localized and spatially segregated patterns of between-group differences. 4 In contrast, the multivariate ML techniques target patterns of relatively minor alterations distributed throughout the whole brain, 1 which may better characterize the abnormalities found in individuals with psychiatric disorders.5 These techniques bring neuroimaging analyses to the level of individual participants and potentially allow for their diagnostic use.The use of neuroimaging for diagnostic purposes in psychiatry is further complicated by clinical heterogeneity.6,7 Not all neuroimaging findings in psychiatric patients are of diagnostic use. For example, brain changes in patients with bipolar disorders (BD) may represent biological markers of BD, but also the consequences of illness episodes, 8,9 exposure to medications 10-12 or comorbid conditions. 13,14 The changes Background: Brain imaging is of limited diagnostic use in psychiatry owing to clinical heterogeneity and low sensitivity/specificity of between-group neuroimaging differences. Machine learning (ML) may better translate neuroimaging to the level of individual participants. Studying unaffected offspring of parents with bipolar disorders (BD) decreases clinical heterogeneity and thus increases sensitivity for detection of biomarkers. The present study used ML to identify individuals at genetic high risk (HR) for BD based on brain structure. Methods:We studied unaffected and affected relatives of BD probands recruited from 2 sites (Halifax, Canada, and Prague, Czech Republic). Each participant was individually matched by age and sex to controls without personal or family history of psychiatric disorders. We applied support vector machines (SVM) and Gaussian process classifiers (GPC) to structural MRI. Results: We included 45 unaffected and 36 affected relatives of BD probands matched by age and sex on an individual basis to healthy controls. The SVM of white matter distinguished unaffected HR from control participants (accuracy = 68.9%, p = 0.001), with similar accuracy for the GPC (65.6%, p = 0.002) or when analyzing data from each site separately. Differentiation of the mo...

Distinguishing bipolar and major depressive disorders by brain structural morphometry: a pilot study

“…It is of note that, in our sample, six patients with BD were misclassified as MDD (sensitivity, 62.5 %) and three patients with MDD were misclassified as BD (specificity, 84.3 %). This pattern is in line with recent findings [ 57 , 58 ] and the clinical complexities in diagnosing BD from MDD. Patients with onset of depressive episodes are often diagnosed and treated as having MDD until a manic or hypomanic episode emerges.…”

Will machine learning applied to neuroimaging in bipolar disorder help the clinician? A critical review and methodological suggestions

“…Each study used a different design. Hajek et al 81 attempted to classify unaffected BD offspring vs HC with sMRI features as well as affected BD relatives vs HC and reached an ACC of 68.9% and 59.7% respectively. Lin et al 43 classified asymptomatic high‐genetic‐risk individuals (HR) vs clinical HR (CHR) individuals with risk‐relevant clinical subsyndromal symptoms (including hypomanic, depressive, psychotic and/or attention deficit hyperactivity disorder [ADHD] subsyndromes) with an ACC of 83.21% with sMRI features.…”

Using structural MRI to identify bipolar disorders – 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group

“…We decided to a priori fix the hyperparameter at C = 1, for the following reasons. First, this setting is a common choice in the existing literature [53][54][55][56]. Second, SVM performance is relatively robust to changes in C values [57].…”