Identification and individualized prediction of clinical phenotypes in bipolar disorders using neurocognitive data, neuroimaging scans and machine learning

Abstract

Diagnosis, clinical management and research of psychiatric disorders remains 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 heterogenous clinical sub-phenotypes of major psychiatric disorders.

e-PTSD: an overview on how new technologies can improve prediction and assessment of Posttraumatic Stress Disorder (PTSD)

“…These techniques can correctly classify a patient according to his mood state with an accuracy up to 92% (Wu et al, 2017). In the field of psychotic transition, these techniques predict with 84.2% accuracy the risk of transition from an at-risk mental state to schizophrenia (whereas a trained clinician have less than 50% accuracy) (Koutsouleris et al, 2012).…”

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

“…Another study explored distinct phenotypes in a BD population 86 . They first used an unsupervised ML algorithm (k‐means) that allowed them to identify 2 homogenous subgroups of BD based on neurocognitive data (Cambridge Neurocognitive Test Automated Battery) of 70 patients with BD.…”

Machine learning and big data analytics in bipolar disorder: A position paper from the International Society for Bipolar Disorders Big Data Task Force

“…Clustering can find hidden groups underlying the predictors’ variance and help users explain phenomena. This type of learning includes finding subgroups of patients that share underlying characteristics, such as suicidality or neurocognitive impairment in a proportion of patients with BD …”