• Keywords
• hypnogram, spánkový deník, Epworthská škála spavosti,
• MeSH
• Medical History Taking MeSH
• Antidepressive Agents administration & dosage   MeSH
• Dementia complications   MeSH
• Diagnosis, Differential MeSH
• Humans MeSH
• Narcolepsy classification   pathology   MeSH
• Sleep Apnea, Obstructive diagnosis   pathology   therapy   MeSH
• REM Sleep Parasomnias diagnosis   MeSH
• Parasomnias diagnosis   drug therapy   classification   therapy   MeSH
• Sleep Disorders, Circadian Rhythm classification   MeSH
• Sleep Initiation and Maintenance Disorders diagnosis   etiology   drug therapy   pathology   therapy   MeSH
• Disorders of Excessive Somnolence classification   pathology   MeSH
• Mood Disorders complications   MeSH
• Sleep Wake Disorders * diagnosis   etiology   classification   complications   therapy   MeSH
• Sleep * MeSH
• Sleep Hygiene MeSH
• Sleep Stages MeSH
• Restless Legs Syndrome drug therapy   therapy   MeSH
• Sleep Apnea Syndromes diagnosis   pathology   therapy   MeSH
• Anxiety Disorders complications   MeSH
• Check Tag
• Humans MeSH
• Publication type
• Research Support, Non-U.S. Gov't MeSH
• Review MeSH

Narcolepsy is a rare life-long disease that exists in two forms, narcolepsy type-1 (NT1) or type-2 (NT2), but only NT1 is accepted as clearly defined entity. Both types of narcolepsies belong to the group of central hypersomnias (CH), a spectrum of poorly defined diseases with excessive daytime sleepiness as a core feature. Due to the considerable overlap of symptoms and the rarity of the diseases, it is difficult to identify distinct phenotypes of CH. Machine learning (ML) can help to identify phenotypes as it learns to recognize clinical features invisible for humans. Here we apply ML to data from the huge European Narcolepsy Network (EU-NN) that contains hundreds of mixed features of narcolepsy making it difficult to analyze with classical statistics. Stochastic gradient boosting, a supervised learning model with built-in feature selection, results in high performances in testing set. While cataplexy features are recognized as the most influential predictors, machine find additional features, e.g. mean rapid-eye-movement sleep latency of multiple sleep latency test contributes to classify NT1 and NT2 as confirmed by classical statistical analysis. Our results suggest ML can identify features of CH on machine scale from complex databases, thus providing 'ideas' and promising candidates for future diagnostic classifications.

• MeSH
• Models, Biological * MeSH
• Databases, Factual statistics & numerical data   MeSH
• Datasets as Topic MeSH
• Adult MeSH
• Data Interpretation, Statistical MeSH
• Humans MeSH
• Young Adult MeSH
• Narcolepsy classification   diagnosis   physiopathology   MeSH
• Polysomnography statistics & numerical data   MeSH
• Supervised Machine Learning * MeSH
• ROC Curve MeSH
• Sleep, REM physiology   MeSH
• Sleep Latency physiology   MeSH
• Stochastic Processes MeSH
• Rare Diseases classification   diagnosis   physiopathology   MeSH
• Check Tag
• Adult MeSH
• Humans MeSH
• Young Adult MeSH
• Male MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH

• MeSH
• Child MeSH
• Idiopathic Hypersomnia diagnostic imaging   drug therapy   genetics   MeSH
• Cataplexy diagnosis   drug therapy   MeSH
• Kleine-Levin Syndrome diagnostic imaging   drug therapy   MeSH
• Humans MeSH
• Adolescent MeSH
• Narcolepsy diagnosis   drug therapy   classification   MeSH
• Polysomnography methods   MeSH
• Disorders of Excessive Somnolence * diagnosis   classification   therapy   MeSH
• Sleep Disorders, Intrinsic diagnosis   drug therapy   MeSH
• Central Nervous System Stimulants administration & dosage   MeSH
• Check Tag
• Child MeSH
• Humans MeSH
• Adolescent MeSH

BACKGROUND: The successive editions of the International Classification of Sleep Disorders (ICSD) reflect the evolution of the concepts of various sleep disorders. This is particularly the case for central disorders of hypersomnolence, with continuous changes in terminology and divisions of narcolepsy, idiopathic hypersomnia, and recurrent hypersomnia. According to the ICSD 2nd Edition (ICSD-2), narcolepsy with cataplexy (NwithC), narcolepsy without cataplexy (Nw/oC), idiopathic hypersomnia with long sleep time (IHwithLST), and idiopathic hypersomnia without long sleep time (IHw/oLST) are four, well-defined hypersomnias of central origin. However, in the absence of biological markers, doubts have been raised as to the relevance of a division of idiopathic hypersomnia into two forms, and it is not yet clear whether Nw/oC and IHw/oLST are two distinct entities. With this in mind, it was decided to empirically review the ICSD-2 classification by using a hierarchical cluster analysis to see whether this division has some relevance, even though the terms "with long sleep time" and "without long sleep time" are inappropriate. RESULTS: The cluster analysis differentiated three main clusters: Cluster 1, "combined monosymptomatic hypersomnia/narcolepsy type 2" (people initially diagnosed with IHw/oLST and Nw/oC); Cluster 2 "polysymptomatic hypersomnia" (people initially diagnosed with IHwithLST); and Cluster 3, narcolepsy type 1 (people initially diagnosed with NwithC). CONCLUSIONS: Cluster analysis confirmed that narcolepsy type 1 and polysymptomatic hypersomnia are independent sleep disorders. People who were initially diagnosed with Nw/oC and IHw/oLST formed a single cluster, referred to as "combined monosymptomatic hypersomnia/narcolepsy type 2."

• MeSH
• Adult MeSH
• Middle Aged MeSH
• Humans MeSH
• Young Adult MeSH
• Narcolepsy classification   diagnosis   MeSH
• Polysomnography MeSH
• Disorders of Excessive Somnolence classification   diagnosis   MeSH
• Cluster Analysis MeSH
• Check Tag
• Adult MeSH
• Middle Aged MeSH
• Humans MeSH
• Young Adult MeSH
• Male MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH

• MeSH
• Medical History Taking MeSH
• Antiviral Agents adverse effects   MeSH
• Hypothyroidism MeSH
• Cataplexy diagnosis   etiology   classification   pathology   therapy   MeSH
• Humans MeSH
• Adolescent MeSH
• Narcolepsy * diagnosis   etiology   classification   pathology   therapy   MeSH
• Signs and Symptoms MeSH
• Treatment Outcome MeSH
• Check Tag
• Humans MeSH
• Adolescent MeSH
• Male MeSH
• Publication type
• Case Reports MeSH

• MeSH
• Benzhydryl Compounds therapeutic use   MeSH
• Adult MeSH
• Cataplexy diagnosis   physiopathology   MeSH
• Kleine-Levin Syndrome diagnosis   physiopathology   MeSH
• Drug Prescriptions economics   standards   MeSH
• Humans MeSH
• Methylphenidate therapeutic use   MeSH
• Adolescent MeSH
• Narcolepsy * diagnosis   drug therapy   classification   MeSH
• Disorders of Excessive Somnolence diagnosis   etiology   drug therapy   MeSH
• Check Tag
• Adult MeSH
• Humans MeSH
• Adolescent MeSH
• Publication type
• Review MeSH

• MeSH
• Antidepressive Agents, Tricyclic therapeutic use   MeSH
• Benzodiazepines therapeutic use   MeSH
• Narcolepsy diagnosis   classification   therapy   MeSH
• Sleep Apnea, Obstructive diagnosis   classification   therapy   MeSH
• Sleep Wake Disorders diagnosis   classification   therapy   MeSH
• Publication type
• Review MeSH

• MeSH
• Attention Deficit Disorder with Hyperactivity diagnosis   classification   MeSH
• Narcolepsy diagnosis   classification   MeSH
• Sleep Apnea, Obstructive diagnosis   classification   MeSH
• Sleep Wake Disorders classification   MeSH
• Restless Legs Syndrome diagnosis   classification   MeSH
• Publication type
• Congress MeSH
• Review MeSH

• MeSH
• Narcolepsy classification   MeSH
• Sleep Wake Disorders classification   MeSH

• MeSH
• Narcolepsy classification   MeSH
• Disorders of Excessive Somnolence classification   MeSH