TY - JOUR
T1 - Data-Driven Phenotyping of Central Disorders of Hypersomnolence With Unsupervised Clustering
AU - Gool, Jari K.
AU - Zhang, Zhongxing
AU - Oei, Martijn S.S.L.
AU - Mathias, Stephanie
AU - Dauvilliers, Yves
AU - Mayer, Geert
AU - Plazzi, Giuseppe
AU - Del Rio-Villegas, Rafael
AU - Cano, Joan Santamaria
AU - Šonka, Karel
AU - Partinen, Markku
AU - Overeem, Sebastiaan
AU - Peraita-Adrados, Rosa
AU - Heinzer, Raphael
AU - Martins Da Silva, Antonio
AU - Högl, Birgit
AU - Wierzbicka, Aleksandra
AU - Heidbreder, Anna
AU - Feketeova, Eva
AU - Manconi, Mauro
AU - Bušková, Jitka
AU - Canellas, Francesca
AU - Bassetti, Claudio L.
AU - Barateau, Lucie
AU - Pizza, Fabio
AU - Schmidt, Markus H.
AU - Fronczek, Rolf
AU - Khatami, Ramin
AU - Lammers, Gert Jan
N1 - Funding Information: The Article Processing Charge was funded by UKB/VSNU (Vrije Universiteit). Publisher Copyright: © American Academy of Neurology.
PY - 2022/6/7
Y1 - 2022/6/7
N2 - Background and ObjectivesRecent 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.MethodsWe 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.ResultsWe 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.DiscussionUsing 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.
AB - Background and ObjectivesRecent 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.MethodsWe 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.ResultsWe 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.DiscussionUsing 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.
UR - http://www.scopus.com/inward/record.url?scp=85131544358&partnerID=8YFLogxK
U2 - https://doi.org/10.1212/WNL.0000000000200519
DO - https://doi.org/10.1212/WNL.0000000000200519
M3 - Article
C2 - 35437263
SN - 0028-3878
VL - 98
SP - E2387-E2400
JO - Neurology
JF - Neurology
IS - 23
ER -