Prediction of estimated risk for bipolar disorder using machine learning and structural MRI features

Abstract

Background Individuals with bipolar disorder are commonly correctly diagnosed a decade after symptom onset. Machine learning techniques may aid in early recognition and reduce the disease burden. As both individuals at risk and those with a manifest disease display structural brain markers, structural magnetic resonance imaging may provide relevant classification features. Methods Following a pre-registered protocol, we trained linear support vector machine (SVM) to classify individuals according to their estimated risk for bipolar disorder using regional cortical thickness of help-seeking individuals from seven study sites (N = 276). We estimated the risk using three state-of-the-art assessment instruments (BPSS-P, BARS, EPIbipolar). Results For BPSS-P, SVM achieved a fair performance of Cohen's κ of 0.235 (95% CI 0.11–0.361) and a balanced accuracy of 63.1% (95% CI 55.9–70.3) in the 10-fold cross-validation. In the leave-one-site-out cross-validation, the model performed with a Cohen's κ of 0.128 (95% CI −0.069 to 0.325) and a balanced accuracy of 56.2% (95% CI 44.6–67.8). BARS and EPIbipolar could not be predicted. In post hoc analyses, regional surface area, subcortical volumes as well as hyperparameter optimization did not improve the performance. Conclusions Individuals at risk for bipolar disorder, as assessed by BPSS-P, display brain structural alterations that can be detected using machine learning. The achieved performance is comparable to previous studies which attempted to classify patients with manifest disease and healthy controls. Unlike previous studies of bipolar risk, our multicenter design permitted a leave-one-site-out cross-validation. Whole-brain cortical thickness seems to be superior to other structural brain features.

Machine Learning Prediction of Estimated Risk for Bipolar Disorders Using Hippocampal Subfield and Amygdala Nuclei Volumes

“…Unlike null hypothesis testing, machine learning techniques might be more appropriate for identifying discrete, multivariate differences, which are more representative of psychiatric disorders [ 68 ]. The classification performance using hippocampal subfields and nuclei of the amygdala was similar to our previous study using regional cortical thickness, cortical surface areas and volumes of subcortical structures (63.1 and 56.2% 10-fold versus leave-one-site-out) (Mikolas et al, 2023) [ 35 ]. The classification of patients with manifest BD versus HC by the ENIGMA consortium performed similarly (65.23% and 58.67% k-fold versus leave-one-site-out) [ 62 ].…”

“…On the other hand, the benefit of these features should be evaluated separately in future studies using longitudinal data and models should be trained to recognize subjects who transitioned to BD. Whereas the SVM classification based on BPSS-P risk assessment was above chance, the predictions using EPIbipolar and BARS failed, which was a similar pattern to Mikolas et al (2023) [35]. There are several possible reasons for the better performance of BPSS-P. First, BPSS-P assigned noticeably fewer subjects to the risk group compared to both other instruments (22.3% for BPSS-P, 71.8% for BARS, 88.9% low-risk and high-risk pooled for EPIbipolar).…”

“…These should be included as outcomes in future investigations. Compared to our previous study using regional cortical thickness, cortical surface areas and volumes of unparcelled cortical structures (Mikolas et al, 2023) [35], balanced accuracies were not much different numerically when using hippocampal subfields and amygdala nuclei as features for the SVM. The latter approach even seems to be more prone to confounders.…”

“…On the other hand, multivariate machine learning (ML) approaches have a higher sensitivity and can potentially improve individual inferences required for clinical diagnostics and prognostics. We have already investigated the use of ML in combination with regional cortical thickness and surface area values as well as subcortical structural volumes (Mikolas et al, 2023) [ 35 ]. Here, we classified subjects at risk of developing BD according to the BPSS-P criteria and achieved a balanced accuracy of 63.1 % using a 10-fold cross-validation.…”