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.
Objectives:The objective of our study was to assess attention processes and executive function in patients with narcolepsy with cataplexy (NT1). To do so, we compared the results with those of a control group from the general population using an extensive neuropsychological test battery.Methods:We studied 28 patients with NT1 and 28 healthy control participants matched for age, gender, and educational level. They all completed questionnaires on sleepiness, anxiety, and depression symptoms. In addition, they underwent neuropsychological tests. The ability to maintain attention was assessed using three computer tasks with different levels of complexity.Results:Patients had significantly more daytime sleepiness than controls. A significant negative correlation between depression and disease duration was found in NT1 patients. The results of the anxiety questionnaire correlated with the presence of sleep paralysis. There were significant differences in information processing speed subtasks. Patients made significantly more omissions and generally reacted slower and more variably than controls in computerized tasks. As for executive function, patients performed worse in phonologic fluency tasks than controls. However, when the influence of processing speed on fluency tasks was statistically controlled, part of this significant difference disappeared.Conclusions:Our results indicate that the negative correlation between depression and disease duration probably reflects progressive adaptation to the functional burden of the disease. Information processing speed plays a fundamental role in the expression of cognitive deficits. We emphasized the need to control the influence of processing speed and sustained attention in the neuropsychological assessment of NT1 patients.
Summary Memory deficits in narcolepsy with cataplexy type 1 (NT1) have been poorly studied, and the results are controversial. Patients with NT1 usually report memory deficits, which are not seen in objective memory assessments. This study aimed to assess attention and memory processes in NT1 patients using standardised neuropsychological tests and to compare the results with a control group. Performance in memory and attention tests was studied in 12 NT1 patients (diagnosed according to ICSD‐3 criteria) and the results compared with those of 14 control subjects. All participants completed questionnaires on sleepiness and depression symptoms. Significant differences were found in the depression symptoms questionnaire. Regarding neuropsychological assessment, NT1 patients performed worse in attention than the control group in that they processed fewer stimuli and achieved fewer correct stimuli. However, no significant differences were found in the memory test results, and the performance was similar between both groups. After application of the Holm‐Bonferroni correction, the only differences that remained significant were those in the ESS and in BDI‐II scores. Our results showed that memory processes are preserved in NT1 patients and that memory complaints may not be associated with an objective memory deficit. In addition, the significant difference observed for patients in the depression questionnaire could explain the subjective memory complaints.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.