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
. 2024 Aug 28;14(9):871.
doi: 10.3390/brainsci14090871.

Machine Learning Predicts Phenoconversion from Polysomnography in Isolated REM Sleep Behavior Disorder

Matteo Cesari  1 , Andrea Portscher  1   2 , Ambra Stefani  1 , Raphael Angerbauer  1 , Abubaker Ibrahim  1 , Elisabeth Brandauer  1 , Simon Feuerstein  1   2 , Kristin Egger  1 , Birgit Högl  1 , Antonio Rodriguez-Sanchez  2
Affiliations

Machine Learning Predicts Phenoconversion from Polysomnography in Isolated REM Sleep Behavior Disorder

Matteo Cesari et al. Brain Sci. .

Abstract

Isolated rapid eye movement (REM) sleep behavior disorder (iRBD) is a prodromal stage of alpha-synucleinopathies. This study aimed at developing a fully-automated machine learning framework for the prediction of phenoconversion in patients with iRBD by using data recorded during polysomnography (PSG). A total of 66 patients with iRBD were included, of whom 18 converted to an overt alpha-synucleinopathy within 2.7 ± 1.0 years. For each patient, a baseline PSG was available. Sleep stages were scored automatically, and time and frequency domain features were derived from electromyography (EMG) and electroencephalography (EEG) signals in REM and non-REM sleep. Random survival forest was employed to predict the time to phenoconversion, using a four-fold cross-validation scheme and by testing several combinations of features. The best test performances were obtained when considering EEG features in REM sleep only (Harrel's C-index: 0.723 ± 0.113; Uno's C-index: 0.741 ± 0.11; integrated Brier score: 0.174 ± 0.06). Features describing EEG slowing had high importance for the machine learning model. This is the first study employing machine learning applied to PSG to predict phenoconversion in patients with iRBD. If confirmed in larger cohorts, these findings might contribute to improving the design of clinical trials for neuroprotective treatments.

Keywords: PSG; REM sleep; alpha-synucleinopathy; biomarker; iRBD; phenoconversion.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Schematic representation of the process of feature extraction. Based on the automatically scored sleep stages, features were derived from central and occipital EEG, and from chin and TA EMG channels. A detailed description is reported in Section 2.2 and Section 2.3, and the relative subsections.
Figure 2
Figure 2
Schematic representation of the process of machine learning model training and testing. A detailed description is reported in Section 2.4.
Figure 3
Figure 3
Weighted feature importance across the 40 test sets for the experiment considering 5 EEG features calculated in REM sleep. For each feature, the weighted feature importance was obtained by multiplying the average permutation-based feature importance across the test sets by the percentage of models in which the feature was selected. The unit of measure of the weighted feature importance is arbitrary.
See this image and copyright information in PMC

References

    1. Calabresi P., Mechelli A., Natale G., Volpicelli-Daley L., Di Lazzaro G., Ghiglieri V. Alpha-Synuclein in Parkinson’s Disease and Other Synucleinopathies: From Overt Neurodegeneration Back to Early Synaptic Dysfunction. Cell Death Dis. 2023;14:176. doi: 10.1038/s41419-023-05672-9. - DOI - PMC - PubMed
    1. Savica R., Boeve B.F., Mielke M.M. When Do α-Synucleinopathies Start? An Epidemiological Timeline: A Review. JAMA Neurol. 2018;75:503–509. doi: 10.1001/jamaneurol.2017.4243. - DOI - PubMed
    1. Mahlknecht P., Marini K., Werkmann M., Poewe W., Seppi K. Prodromal Parkinson’s Disease: Hype or Hope for Disease-Modification Trials? Transl. Neurodegener. 2022;11:11. doi: 10.1186/s40035-022-00286-1. - DOI - PMC - PubMed
    1. American Academy of Sleep Medicine . International Classification of Sleep Disorders. 3rd, text revision ed. American Academy of Sleep Medicine; Darien, IL, USA: 2023.
    1. Cesari M., Heidbreder A., St Louis E.K., Sixel-Döring F., Bliwise D.L., Baldelli L., Bes F., Fantini M.L., Iranzo A., Knudsen-Heier S., et al. Video-Polysomnography Procedures for Diagnosis of Rapid Eye Movement Sleep Behavior Disorder (RBD) and the Identification of Its Prodromal Stages: Guidelines from the International RBD Study Group. Sleep. 2022;45:zsab257. doi: 10.1093/sleep/zsab257. - DOI - PubMed

LinkOut - more resources