Early identification of bipolar disorder among young adults – a 22‐year community birth cohort

Abstract

Objective We set forth to build a prediction model of individuals who would develop bipolar disorder (BD) using machine learning techniques in a large birth cohort. Methods A total of 3748 subjects were studied at birth, 11, 15, 18, and 22 years of age in a community birth cohort. We used the elastic net algorithm with 10‐fold cross‐validation to predict which individuals would develop BD at endpoint (22 years) at each follow‐up visit before diagnosis (from birth up to 18 years). Afterward, we used the best model to calculate the subgroups of subjects at higher and lower risk of developing BD and analyzed the clinical differences among them. Results A total of 107 (2.8%) individuals within the cohort presented with BD type I, 26 (0.6%) with BD type II, and 87 (2.3%) with BD not otherwise specified. Frequency of female individuals was 58.82% (n = 150) in the BD sample and 53.02% (n = 1868) among the unaffected population. The model with variables assessed at the 18‐year follow‐up visit achieved the best performance: AUC 0.82 (CI 0.75–0.88), balanced accuracy 0.75, sensitivity 0.72, and specificity 0.77. The most important variables to detect BD at the 18‐year follow‐up visit were suicide risk, generalized anxiety disorder, parental physical abuse, and financial problems. Additionally, the high‐risk subgroup of BD showed a high frequency of drug use and depressive symptoms. Conclusions We developed a risk calculator for BD incorporating both demographic and clinical variables from a 22‐year birth cohort. Our findings support previous studies in high‐risk samples showing the significance of suicide risk and generalized anxiety disorder prior to the onset of BD, and highlight the role of social factors and adverse life events.

Development and Multi-Site External Validation of a Generalizable Risk Prediction Model for Bipolar Disorder

“…Prior studies have largely focused on individuals with a history of depression and/or have included relatively small samples. 27,28 Here, we All rights reserved. No reuse allowed without permission.…”

“…Prior studies have largely focused on individuals with a history of depression and/or have included relatively small samples. 27,28 Here, we validated multiple algorithmic approaches across multiple well-powered longitudinal EHR sites in the absence of a common data model to generate a novel suite of prediction algorithms for BD. These models performed well across diverse geography and broad, heterogeneous patient populations.…”

Correlates of suicidality in young people with depressive disorders: A systematic review

“…First, nine studies explicitly excluded participants with bipolar disorders, thus reducing the number of comparisons that could be made between unipolar and bipolar disorders in our synthesis. Difficulties in accurately diagnosing bipolar disorders, particularly in young people, are also an important factor (Rabelo-da-Ponte et al, 2020). Bipolar disorders are frequently misdiagnosed as MDD and other unipolar depressive conditions (Bowden, 2001; Phillips and Kupfer, 2013; Zhang et al, 2017).…”

Can neurological soft signs and neurocognitive deficits serve as a combined endophenotype for Han Chinese with bipolar disorder?

“…However, this study found that motor coordination, IPS, VL, and WM as predictors can accurately identify patients and first-degree relatives from the healthy population. This result can be applied to screening high-risk groups of bipolar disorder, so as to identify and intervene early (Rabelo-da-Ponte et al, 2020), prevent disease occurrence and improve disease prognosis (Correll et al, 2020).…”