Use of Neuroimaging Machine-Learning Analysis to Improve Hypersomnolence Disorders’ Diagnostic Criteria
Jari Gool is an MD-PhD student in (clinical) neuroscience at the department of Anatomy and Neurosciences, in the Amsterdam University Medical Center (UMC), the Netherlands, and a visiting PhD student in neuroscience in the Concordia University in Montreal, Quebec, Canada.
Jari is a board member and chairmen of the Young Scientists Committee on the Dutch Society for Sleep-Wake Research (NSWO) and a member of the European Sleep Research Society (ESRS).
Award-winning research on hypersomnolence disorders using machine-learning analysis
In his research he investigates central disorders of hypersomnolence (narcolepsy and idiopathic hypersomnia), diseases that severely disable daily functioning by increased susceptibility to sleep-wake transitions in an uncontrollable manner. He takes part in a study collaboration between Amsterdam UMC (location VUmc), Sleep-Wake Centre SEIN, Leiden University Medical Center and Concordia University. This group aims to unravel the neural correlates of narcolepsy and idiopathic hypersomnia and the origin of patients’ complaints, by multimodally investigating patients with combined (functional) MRI and EEG measurements. They have also developed and implemented unsupervised machine learning algorithms in a pan-European effort to better understand sleep disorder subtypes and improve current diagnostic criteria.
Following his research, he recently co-authored a paper (as lead author) entitled “Data-Driven Phenotyping of Central Disorders of Hypersomnolence With Unsupervised Clustering” (vide Gool et al., 2022), an award-winning article, which helped him win the 2022 Daytime Sleepiness Award – Young Investigator Award and the ESRS Early Career Research Award. This work was a close collaboration with Klinik Barmelweid AG, Switzerland, and made use of data from the European Narcolepsy Network.
In the following interview, Jari Gool discusses this paper and his latest research on hypersomnolence disorders with Dr. Jennifer Goldschmied from the ESRS’ Digital & Communications Committee. He describes how he uses neuroimaging techniques such as magnetic resonance imaging (MRI) and electroencephalography (EEG) to study sleep disorders like narcolepsy and idiopathic hypersomnia, and how combining these methods helps investigate brain activity patterns of wake and sleep in patients with these disorders. Additionally, he talks about using an unsupervised machine learning algorithm to differentiate subtypes of narcolepsy type 1 and identify more reliable subgrouping of those without cataplexy. By the end of the interview, Gool outlines recent efforts for large-scale collaborations to combine neuroimaging datasets across the globe to better understand what is happening in the brains of people with a hypersomnolence disorder.
Don’t miss this very interesting interview and watch it below for further details and insights on Gool’s work, study results and future research projects. You can also access his publication here.
Central Disorders of Hypersomnolence
Daytime sleepiness (i.e., the inability to stay awake and alert during the day, resulting in periods of incoercible sleep, or involuntary bouts of drowsiness or sleep) is the primary complaint in the disorders included in this group. In all cases, daytime sleepiness should not be caused by disturbed nocturnal sleep or disordered circadian rhythms and, when other sleep disorders are present, they need to be adequately treated before a diagnosis in this category can be established. The term hypersomnolence refers to the symptom of excessive sleepiness, whereas hypersomnia indicates specific disorders, such as idiopathic hypersomnia (“Central Disorders of Hypersomnolence”).
“Central Disorders of Hypersomnolence,” Zucconi and Ferri (2021)., B. Assessment of Sleep Disorders and Diagnostic Procedures 1. Classification of sleep disorders., McNicholas, W., Paunio, T. & Peigneux, P. (Eds.). Sleep Medicine Textbook (2nd ed., p. 155). Regensburg: European Sleep Research Society.
Recent publications from ESRS members
Stankeviciute et al. (2023). Differential effects of sleep on brain structure and metabolism at the preclinical stages of AD. Alzheimers Dement.
- Wagenhäuser et al. (2023). The relationship between mental health, sleep quality and the immunogenicity of COVID-19 vaccinations. J Sleep Res.
- Åkerstedt et al. (2023). The association of short and long sleep with mortality in men and women. J Sleep Res.
- Malhotra et al. (2023). Positive Airway Pressure Adherence and Health Care Resource Utilization in Patients With Obstructive Sleep Apnea and Heart Failure With Reduced Ejection Fraction. J Am Heart Assoc.
- Calafate et al. (2023). Early alterations in the MCH system link aberrant neuronal activity and sleep disturbances in a mouse model of Alzheimer’s disease. Nat Neurosci.
- Woelders et al. (2023). Machine learning estimation of human body time using metabolomic profiling. Proc Natl Acad Sci U S A.
- DelRosso et al. (2023). Frequency of antidepressant use and clinical characteristics of children and adolescents undergoing polysomnography: an observational study. Child Adolesc Psychiatry Ment Health.
- Godos et al. (2023). Mediterranean diet, mental health, cognitive status, quality of life, and successful aging in southern Italian older adults. Exp Gerontol.
- Seifinejad et al. (2023). Epigenetic silencing of selected hypothalamic neuropeptides in narcolepsy with cataplexy. Proc Natl Acad Sci U S A.
- Bergmann et al. (2023). A reliable automatic algorithm to score fragmentary myoclonus. J Sleep Res.