Related Experiment Video
Updated: Apr 1, 2026
05:19
Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
Published on: July 7, 2023
3.7K
Predictive classification of pediatric bipolar disorder using atlas-based diffusion weighted imaging and support
Benson Mwangi1, Mon-Ju Wu1, Isabelle E Bauer1
1UT Center of Excellence on Mood Disorders, Department of Psychiatry and Behavioral Sciences, UT Houston Medical School, Houston, TX, USA.
Psychiatry Research
|October 14, 2015
Summary
Diffusion-weighted imaging can identify pediatric bipolar disorder in individuals. White matter abnormalities detected via this method show promise for distinguishing patients from healthy controls.
Area of Science:
- Neuroimaging
- Psychiatry
- Biomedical Engineering
Background:
- Pediatric bipolar disorder is associated with white matter diffusivity abnormalities.
- Previous studies have not confirmed if these abnormalities can reliably distinguish individuals.
Purpose of the Study:
- To determine if diffusion-weighted imaging (DWI) measurements can differentiate pediatric bipolar disorder patients from healthy controls.
- To assess the diagnostic accuracy of machine learning algorithms using DWI data.
Main Methods:
- Acquired DWI scans from 16 pediatric bipolar disorder patients and 16 healthy controls.
- Computed regional white matter microstructural measures (fractional anisotropy, axial diffusivity, radial diffusivity) using an atlas-based approach.
- Trained a support vector machine (SVM) algorithm to predict diagnostic labels based on DWI measurements.
Main Results:
- The SVM algorithm achieved 78.12% accuracy in distinguishing subjects.
- Specificity was 87.5% and sensitivity was 68.75%.
- Reduced fractional anisotropy in white matter was a key indicator in patients.
Conclusions:
- Atlas-based DWI measurements can distinguish individuals with pediatric bipolar disorder from healthy controls.
- These findings contribute to understanding the pathophysiology of pediatric bipolar disorder.
- DWI holds potential for clinical applications in diagnosing pediatric bipolar disorder.
