View in EDS

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

Saved in:
Bibliographic Details
Title: Prediction of estimated risk for bipolar disorder using machine learning and structural MRI features.
Authors: Mikolas, Pavol, Marxen, Michael, Riedel, Philipp, Bröckel, Kyra, Martini, Julia, Huth, Fabian, Berndt, Christina, Vogelbacher, Christoph, Jansen, Andreas, Kircher, Tilo, Falkenberg, Irina, Lambert, Martin, Kraft, Vivien, Leicht, Gregor, Mulert, Christoph, Fallgatter, Andreas J., Ethofer, Thomas, Rau, Anne, Leopold, Karolina, Bechdolf, Andreas
Source: Psychological Medicine. Jan2024, Vol. 54 Issue 2, p278-288. 11p.
Subjects: Bipolar disorder, Risk assessment, Recognition (Psychology), Brain, Magnetic resonance imaging, Help-seeking behavior, Descriptive statistics, Support vector machines, Research, Machine learning, Brain cortical thickness, Comparative studies, Confidence intervals, Economic aspects of diseases, Brain mapping
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, EPI bipolar). 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 EPI bipolar 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. [ABSTRACT FROM AUTHOR]
Copyright of Psychological Medicine is the property of Cambridge University Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Psychology and Behavioral Sciences Collection
Description
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, EPI bipolar). 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 EPI bipolar 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. [ABSTRACT FROM AUTHOR]
ISSN:00332917
DOI:10.1017/S0033291723001319