Data-Driven Phenotyping of Central Disorders of Hypersomnolence With Unsupervised Clustering.
Journal
Neurology
ISSN: 1526-632X
Titre abrégé: Neurology
Pays: United States
ID NLM: 0401060
Informations de publication
Date de publication:
07 06 2022
07 06 2022
Historique:
received:
30
10
2021
accepted:
28
02
2022
pubmed:
20
4
2022
medline:
9
6
2022
entrez:
19
4
2022
Statut:
ppublish
Résumé
Recent studies fueled doubts as to whether all currently defined central disorders of hypersomnolence are stable entities, especially narcolepsy type 2 and idiopathic hypersomnia. New reliable biomarkers are needed, and the question arises of whether current diagnostic criteria of hypersomnolence disorders should be reassessed. The main aim of this data-driven observational study was to see whether data-driven algorithms would segregate narcolepsy type 1 and identify more reliable subgrouping of individuals without cataplexy with new clinical biomarkers. We used agglomerative hierarchical clustering, an unsupervised machine learning algorithm, to identify distinct hypersomnolence clusters in the large-scale European Narcolepsy Network database. We included 97 variables, covering all aspects of central hypersomnolence disorders such as symptoms, demographics, objective and subjective sleep measures, and laboratory biomarkers. We specifically focused on subgrouping of patients without cataplexy. The number of clusters was chosen to be the minimal number for which patients without cataplexy were put in distinct groups. We included 1,078 unmedicated adolescents and adults. Seven clusters were identified, of which 4 clusters included predominantly individuals with cataplexy. The 2 most distinct clusters consisted of 158 and 157 patients, were dominated by those without cataplexy, and among other variables, significantly differed in presence of sleep drunkenness, subjective difficulty awakening, and weekend-week sleep length difference. Patients formally diagnosed as having narcolepsy type 2 and idiopathic hypersomnia were evenly mixed in these 2 clusters. Using a data-driven approach in the largest study on central disorders of hypersomnolence to date, our study identified distinct patient subgroups within the central disorders of hypersomnolence population. Our results contest inclusion of sleep-onset REM periods in diagnostic criteria for people without cataplexy and provide promising new variables for reliable diagnostic categories that better resemble different patient phenotypes. Cluster-guided classification will result in a more solid hypersomnolence classification system that is less vulnerable to instability of single features.
Sections du résumé
BACKGROUND AND OBJECTIVES
Recent studies fueled doubts as to whether all currently defined central disorders of hypersomnolence are stable entities, especially narcolepsy type 2 and idiopathic hypersomnia. New reliable biomarkers are needed, and the question arises of whether current diagnostic criteria of hypersomnolence disorders should be reassessed. The main aim of this data-driven observational study was to see whether data-driven algorithms would segregate narcolepsy type 1 and identify more reliable subgrouping of individuals without cataplexy with new clinical biomarkers.
METHODS
We used agglomerative hierarchical clustering, an unsupervised machine learning algorithm, to identify distinct hypersomnolence clusters in the large-scale European Narcolepsy Network database. We included 97 variables, covering all aspects of central hypersomnolence disorders such as symptoms, demographics, objective and subjective sleep measures, and laboratory biomarkers. We specifically focused on subgrouping of patients without cataplexy. The number of clusters was chosen to be the minimal number for which patients without cataplexy were put in distinct groups.
RESULTS
We included 1,078 unmedicated adolescents and adults. Seven clusters were identified, of which 4 clusters included predominantly individuals with cataplexy. The 2 most distinct clusters consisted of 158 and 157 patients, were dominated by those without cataplexy, and among other variables, significantly differed in presence of sleep drunkenness, subjective difficulty awakening, and weekend-week sleep length difference. Patients formally diagnosed as having narcolepsy type 2 and idiopathic hypersomnia were evenly mixed in these 2 clusters.
DISCUSSION
Using a data-driven approach in the largest study on central disorders of hypersomnolence to date, our study identified distinct patient subgroups within the central disorders of hypersomnolence population. Our results contest inclusion of sleep-onset REM periods in diagnostic criteria for people without cataplexy and provide promising new variables for reliable diagnostic categories that better resemble different patient phenotypes. Cluster-guided classification will result in a more solid hypersomnolence classification system that is less vulnerable to instability of single features.
Identifiants
pubmed: 35437263
pii: WNL.0000000000200519
doi: 10.1212/WNL.0000000000200519
pmc: PMC9202524
doi:
Types de publication
Journal Article
Observational Study
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
e2387-e2400Commentaires et corrections
Type : CommentIn
Type : ErratumIn
Informations de copyright
Copyright © 2022 The Author(s). Published by Wolters Kluwer Health, Inc. on behalf of the American Academy of Neurology.
Références
J Sleep Res. 2012 Aug;21(4):390-5
pubmed: 22098127
Sleep. 2020 Aug 12;43(8):
pubmed: 32193539
Sleep Med. 2015 Feb;16(2):225-31
pubmed: 25576137
Sleep Med. 2003 Jan;4(1):7-12
pubmed: 14592354
J Sleep Res. 2016 Jun;25(3):356-64
pubmed: 26809504
J Clin Sleep Med. 2014 Sep 15;10(9):1019-24
pubmed: 25142762
Sleep Med. 2019 Dec;64:71-76
pubmed: 31670163
Sleep Med. 2021 Apr;80:86-91
pubmed: 33588261
Sleep Med Rev. 2020 Aug;52:101327
pubmed: 32554241
Neurology. 2019 Apr 9;92(15):e1754-e1762
pubmed: 30867266
PLoS One. 2016 Jun 17;11(6):e0157318
pubmed: 27314230
Sleep. 2021 Feb 12;44(2):
pubmed: 32909046
Sci Rep. 2018 Jul 13;8(1):10628
pubmed: 30006563
Sleep Med Rev. 2017 Oct;35:76-84
pubmed: 27692973
Sleep Med. 2019 Mar;55:115-123
pubmed: 30785052
J Clin Sleep Med. 2014 Jan 15;10(1):89-95
pubmed: 24426826
Front Aging Neurosci. 2017 Sep 20;9:301
pubmed: 28979203
Sleep Med Rev. 2001 Oct;5(5):349-358
pubmed: 12530998
Sleep. 2017 Dec 1;40(12):
pubmed: 29099966
Sleep Med. 2021 Mar;79:6-10
pubmed: 33453460
Sleep. 2006 Feb;29(2):187-91
pubmed: 16494086
Sci Rep. 2018 Sep 20;8(1):14082
pubmed: 30237567
Sleep. 2007 Oct;30(10):1274-81
pubmed: 17969461
Sleep. 2021 May 14;44(5):
pubmed: 33249509
Sleep. 2009 Jun;32(6):753-9
pubmed: 19544751
Sleep Med Rev. 2016 Oct;29:23-33
pubmed: 26599679
J Sleep Res. 2003 Sep;12(3):189-206
pubmed: 12941058
J Am Acad Child Adolesc Psychiatry. 2000 Mar;39(3):346-52
pubmed: 10714055
Schweiz Arch Neurol Neurochir Psychiatr. 1981;129(2):209-22
pubmed: 7323773
Brain Sci. 2020 Jul 01;10(7):
pubmed: 32630358
Arch Gen Psychiatry. 1972 May;26(5):456-62
pubmed: 5019884
J Sleep Res. 2013 Oct;22(5):482-95
pubmed: 23496005
J Sleep Res. 2010 Dec;19(4):525-34
pubmed: 20408941
Sleep Med. 2004 Jan;5(1):37-41
pubmed: 14725825
J Clin Sleep Med. 2013 Aug 15;9(8):789-95
pubmed: 23946709
Sleep. 2014 Jun 01;37(6):1035-42
pubmed: 24882898
Ann Neurol. 2018 Feb;83(2):235-247
pubmed: 29323727
Behav Res Ther. 1999 Feb;37(2):113-25
pubmed: 9990743
Sleep Med Rev. 2020 Aug;52:101306
pubmed: 32311642
Cesk Neurol. 1956 Mar;19(1):48-58
pubmed: 13343296
Sleep. 2020 Sep 14;43(9):
pubmed: 32926158