Individualized Prediction and Clinical Staging of Bipolar Disorders Using Neuroanatomical Biomarkers

Abstract

Background Neuroanatomical abnormalities in Bipolar disorder (BD) have previously been reported. However, the utility of these abnormalities in distinguishing individual BD patients from Healthy controls and stratify patients based on overall illness burden has not been investigated in a large cohort. Methods In this study, we examined whether structural neuroimaging scans coupled with a machine learning algorithm are able to distinguish individual BD patients from Healthy controls in a large cohort of 256 subjects. Additionally, we investigated the relationship between machine learning predicted probability scores and subjects’ clinical characteristics such as illness duration and clinical stages. Neuroimaging scans were acquired from 128 BD patients and 128 Healthy controls. Gray and white matter density maps were obtained and used to ‘train’ a relevance vector machine (RVM) learning algorithm which was used to distinguish individual patients from Healthy controls. Results The RVM algorithm distinguished patients from Healthy controls with 70.3 % accuracy (74.2 % specificity, 66.4 % sensitivity, chi-square p<0.005) using white matter density data and 64.9 % accuracy (71.1 % specificity, 58.6 % sensitivity, chi-square p<0.005) with gray matter density. Multiple brain regions – largely covering the fronto – limbic system were identified as ‘most relevant’ in distinguishing both groups. Patients identified by the algorithm with high certainty (a high probability score) – belonged to a subgroup with more than ten total lifetime manic episodes including hospitalizations (late stage). Conclusions These results indicate the presence of widespread structural brain abnormalities in BD which are associated with higher illness burden – which points to neuroprogression.

Cortical thickness patterns as state biomarker of anorexia nervosa

“… is a vector representing weighting factors estimated during the RVM training process and used in making predictions when the algorithm is exposed to previously ‘unseen’ individual's data. RVM uses a sparse Bayesian learning framework to estimate optimal weighting factors and other parameters (Mwangi, Ebmeier, Matthews, & Steele, ; Mwangi et al, ; Tipping, ).…”

“…In this study, the RVM algorithm was implemented using a MATLAB (The MathWorks, Natick, MA) toolbox (Tipping, ) and in‐house custom routines as described elsewhere (Mwangi et al, ; Mwangi, Hasan, & Soares, ). To examine the generalization ability (high sensitivity/specificity) of the algorithm in identifying affiliation with a diagnostic group, a leave‐one‐out crossvalidation (LOOCV) approach was used.…”

“…Another is to establish how patterns of brain cortical thickness may relate to AN. For the latter, machine‐learning analytic approaches can utilize multiple neuroanatomical measurements to classify individual participants and groups and are thus well‐positioned to provide this kind of information (Lavagnino et al, ; Mwangi et al, ). Advantages of machine‐learning algorithms include the ability to analyze multiple (regional thickness) measurements simultaneously, and the use of robust crossvalidation methods to establish generalizability of the results by testing them on participants that were previously excluded from the analysis (Mwangi et al, ).…”

Staging in bipolar disorder: from theoretical framework to clinical utility

“…It appears that progressive structural changes develop as the disorder evolves. Among a cohort of individuals with a first episode of mania, ventricular size was comparable to controls, while individuals with recurrent illness had ventricular enlargement. Over time, there is also progressive loss of grey matter in those who have a recurrence compared with those who remain episode free.…”

Virginia Woolf, neuroprogression, and bipolar disorder

“…4 In this sense, reductions in the volume of the fronto-limbic system and cognitive impairment have been reported as a function of previous manic episodes and hospitalizations. [25][26][27][28] In addition, it has been proposed that trauma and number of mood episodes may show sensitization to themselves and cross-sensitization to one another, leading to residual vulnerability to further occurrences of mood episodes and faster illness progression. 29 The progression of Woolf's BD seems to fit the model proposed by the hypothesis of neuroprogression -this is supported by some of her final diary entries and the suicide note she left to Leonard:…”