Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jun;26(2):633-640.
doi: 10.1007/s11325-021-02434-9. Epub 2021 Jul 8.

Application of machine learning analysis based on diffusion tensor imaging to identify REM sleep behavior disorder

Dong Ah Lee #  1 , Ho-Joon Lee #  2 , Hyung Chan Kim  1 , Kang Min Park  3
Affiliations

Application of machine learning analysis based on diffusion tensor imaging to identify REM sleep behavior disorder

Dong Ah Lee et al. Sleep Breath. 2022 Jun.

Abstract

Purpose: We evaluated the feasibility of machine learning analysis using diffusion tensor imaging (DTI) parameters to identify patients with idiopathic rapid eye movement (REM) sleep behavior disorder (RBD). We hypothesized that patients with idiopathic RBD could be identified via machine learning analysis based on DTI.

Methods: We enrolled 20 patients with newly diagnosed idiopathic RBD at a tertiary hospital. We also included 20 healthy subjects as a control group. All of the subjects underwent DTI. We obtained the conventional DTI parameters and structural connectomic profiles from the DTI. We investigated the differences in conventional DTI measures and structural connectomic profiles between patients with idiopathic RBD and healthy controls. We then used machine learning analysis using a support vector machine (SVM) algorithm to identify patients with idiopathic RBD using conventional DTI and structural connectomic profiles.

Results: Several regions showed significant differences in conventional DTI measures and structural connectomic profiles between patients with idiopathic RBD and healthy controls. The SVM classifier based on conventional DTI measures revealed an accuracy of 87.5% and an area under the curve of 0.900 to identify patients with idiopathic RBD. Another SVM classifier based on structural connectomic profiles yielded an accuracy of 75.0% and an area under the curve of 0.833.

Conclusion: Our findings demonstrate the feasibility of machine learning analysis based on DTI to identify patients with idiopathic RBD. The conventional DTI parameters might be more important than the structural connectomic profiles in identifying patients with idiopathic RBD.

Keywords: Diffusion tensor imaging; Machine learning; REM sleep.

PubMed Disclaimer

References

    1. Dauvilliers Y, Schenck CH, Postuma RB, Iranzo A, Luppi PH, Plazzi G, Montplaisir J, Boeve B (2018) REM sleep behaviour disorder. Nat Rev Dis Primers 4(1):19. https://doi.org/10.1038/s41572-018-0016-5 - DOI - PubMed
    1. Kang SH, Yoon IY, Lee SD, Han JW, Kim TH, Kim KW (2013) REM sleep behavior disorder in the Korean elderly population: prevalence and clinical characteristics. Sleep 36(8):1147–1152. https://doi.org/10.5665/sleep.2874 - DOI - PubMed - PMC
    1. Unger MM, Belke M, Menzler K, Heverhagen JT, Keil B, Stiasny-Kolster K, Rosenow F, Diederich NJ, Mayer G, Moller JC, Oertel WH, Knake S (2010) Diffusion tensor imaging in idiopathic REM sleep behavior disorder reveals microstructural changes in the brainstem, substantia nigra, olfactory region, and other brain regions. Sleep 33(6):767–773. https://doi.org/10.1093/sleep/33.6.767 - DOI - PubMed - PMC
    1. Scherfler C, Frauscher B, Schocke M, Iranzo A, Gschliesser V, Seppi K, Santamaria J, Tolosa E, Hogl B, Poewe W, Group S (2011) White and gray matter abnormalities in idiopathic rapid eye movement sleep behavior disorder: a diffusion-tensor imaging and voxel-based morphometry study. Ann Neurol 69(2):400–407. https://doi.org/10.1002/ana.22245 - DOI
    1. Duncan JS (2008) Imaging the brain’s highways-diffusion tensor imaging in epilepsy. Epilepsy Curr 8(4):85–89. https://doi.org/10.1111/j.1535-7511.2008.00249.x - DOI - PubMed - PMC

LinkOut - more resources