Hotspots of Floating Plastic Particles across the North Pacific Ocean.

The pollution of the marine environment with plastic debris is expected to increase, where ocean currents and winds cause their accumulation in convergence zones like the North Pacific Subtropical Gyre (NPSG). Surface-floating plastic (>330 µm) was collected in the North Pacific Ocean between Vancouver (Canada) and Singapore using a neuston catamaran and identified by Fourier-transform infrared spectroscopy (FT-IR). Baseline concentrations of 41,600-102,700 items km-2 were found, dominated by polyethylene and polypropylene. Higher concentrations (factors 4-10) of plastic items occurred not only in the NPSG (452,800 items km-2) but also in a second area, the Papaha̅naumokua̅kea Marine National Monument (PMNM, 285,200 items km-2). This second maximum was neither reported previously nor predicted by the applied ocean current model. Visual observations of floating debris (>5 cm; 8-2565 items km-2 and 34-4941 items km-2 including smaller "white bits") yielded similar patterns of baseline pollution (34-3265 items km-2) and elevated concentrations of plastic debris in the NPSG (67-4941 items km-2) and the PMNM (295-3748 items km-2). These findings suggest that ocean currents are not the only factor provoking plastic debris accumulation in the ocean. Visual observations may be useful to increase our knowledge of large-scale (micro)plastic pollution in the global oceans.

Analysis of inflammatory markers and tau deposits in an autopsy series of nine patients with anti-IgLON5 disease.

Anti-IgLON5 disease is a rare neurological, probably autoimmune, disorder associated in many cases with a specific tauopathy. Only a few post-mortem neuropathological studies have been reported so far. Little is known about the pathogenic mechanisms that result in neurodegeneration. We investigated the neuropathology of anti-IgLON5 disease and characterized cellular and humoral inflammation. We included nine cases (six of them previously published). Median age of patients was 71 years (53-82 years), the median disease duration was 6 years (0.5-13 years), and the female to male ratio was 5:4. Six cases with a median disease duration of 9 years presented a prominent tauopathy. Five of them had a classical anti-IgLON5-related brainstem tauopathy and another presented a prominent neuronal and glial 4-repeat tauopathy, consistent with progressive supranuclear palsy (PSP). Three cases with short disease duration (median 1.25 years) only showed a primary age-related neurofibrillary pathology. Inflammatory infiltrates of T and B cells were mild to moderate and did not significantly differ between anti-IgLON5 disease cases with or without tauopathy. In contrast, we found an extensive neuropil deposition of IgG4 in the tegmentum of the brainstem, olivary nucleus, and cerebellar cortex that was most prominent in two patients with short disease duration without the typical IgLON5-related tauopathy. The IgG4 deposits were particularly prominent in the cerebellar cortex and in these regions accompanied by mild IgG1 deposits. Activated complement deposition (C9neo) was absent. Our study indicates that IgLON5-related tau pathology occurs in later disease stages and may also present a PSP-phenotype with exclusively 4-repeat neuronal and glial tau pathology. The prominent deposition of anti-IgLON5 IgG4 at predilection sites for tau pathology suggests that anti-IgLON5 antibodies precede the tau pathology. Early start of immunotherapy might prevent irreversible neuronal damage and progression of the disease, at least in a subgroup of patients.

Low Specificity of Rapid Eye Movement Sleep Behavior Disorder Questionnaires: Need for Better Screening Methods.

BACKGROUND: Correct diagnosis of rapid eye movement sleep behavior disorder (RBD) is critical due to its link to α-synucleinopathies and risk of injuries and requires video-polysomnography (V-PSG). Usefulness of screening questionnaires outside the context of validation studies is limited. OBJECTIVE: The aim was to assess the performance of three validated RBD screening questionnaires compared with gold-standard V-PSG. METHODS: In this bicentric prospective study, 400 consecutive subjects referred to a sleep center for the first time filled three RBD questionnaires (RBD Screening Questionnaire, RBD Single Question, and Innsbruck RBD Inventory) in random order before sleep experts' interview. Subjects positive for at least one questionnaire were invited to undergo V-PSG. Data from patients negative for all questionnaires undergoing V-PSG for other reasons were also evaluated. Questionnaire performances were compared to gold-standard V-PSG RBD diagnosis. RESULTS: Three hundred ninety-nine patients (median age: 51 [interquartile range: 37-64] years, 54.9% men) participated. Two hundred thirty-eight (59.6%) were positive for at least one questionnaire, and RBD was diagnosed using V-PSG in 30 patients (7.5%). Questionnaire specificity was 48.1% to 67.4%, sensitivity 80% to 92%, accuracy 51% to 68.3%, negative predictive value 94.2% to 98%, and positive predictive value 14.1% to 20.7%, with no relevant differences in performances among the evaluated questionnaires. CONCLUSIONS: RBD questionnaires have low specificity and low positive predictive value and should not be used as a standalone tool for the diagnosis of RBD. Further development of RBD screening methods is needed, particularly for upcoming neuroprotective trials. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

A 24% prevalence of excessive fragmentary myoclonus in 500 consecutive sleep laboratory patients.

Excessive fragmentary myoclonus (EFM) is a frequent finding during routine video-polysomnography (VPSG). We aimed to automatically measure the prevalence of EFM according to current American Academy of Sleep Medicine (AASM) criteria, and the fragmentary myoclonus index (FMI) in sleep stage N1, N2, N3, rapid eye movement (REM) sleep and wake in a large patient population. A total of 500 VPSG recordings of patients admitted to the Sleep Laboratory, Department of Neurology, Medical University of Innsbruck, Austria, between May 1, 2022 and February 28, 2023, were included. EFM according to AASM criteria and FMI were computed by applying a previously validated algorithm. EFM was automatically detected in 121 of the 500 Sleep Laboratory patients (24.2%, 95% confidence interval 20.1%-28.9%). FMI increased with age, male gender, apnea-hypopnea-index (AHI), oxygen desaturation index (ODI), and periodic leg movements of sleep (PLMS) index. FMI was highest in REM sleep behaviour disorder (RBD), followed by neurodegenerative and internal medicine diseases, but the increase in the FMI was not explained by the disease itself but rather by the age and sex of the patients. Almost a quarter of our patient population had EFM. However, the prevalence of EFM does not allow the drawing of any conclusions about the pathophysiology of EFM or even the determination of a pathological FMI cut-off value. Associations of the FMI with age, sex, AHI, ODI and PLMS are in line with previous studies, but the FMI needs to be evaluated in different disease entities to learn more about its pathophysiology.

A reliable automatic algorithm to score fragmentary myoclonus.

Excessive fragmentary myoclonus (EFM) is an incidental polysomnographic finding requiring documentation of ≥20 minutes of NREM sleep with ≥5 fragmentary myoclonus (FM) potentials per minute. Manual FM scoring is time-consuming and prone to inter-rater variability. This work aimed to validate an automatic algorithm to score FM in whole-night recordings. One expert scorer manually scored FM in the anterior tibialis muscles in 10 polysomnographies of as many subjects. The algorithm consisted of two steps. First, parameters of the automatic leg movement identification algorithm of the BrainRT software (OSG, Belgium) were modified to identify FM-like activity. Second, a post-processing algorithm was implemented to remove FM activity not meeting sufficient amplitude criteria. The parameter choice and the post-processing were optimised with leave-one-out cross-validation. Agreement with the human scorer was measured with Cohen's kappa (k) and correlation between manual and automatic FM indices in different sleep stages was evaluated. Agreement in identifying patients with EFM was computed. The algorithm showed substantial agreement (average k > 0.62) for all sleep stages, except for W, where a moderate agreement was observed (average k = 0.58). Nonetheless, the agreement between human scorer and the algorithm was similar to previously reported values of inter-rater variability for FM scoring. Correlation coefficients were over 0.96 for all sleep stages. Furthermore, the presence/absence of EFM was correctly identified in 80% of the subjects. In conclusion, this work presents a reliable algorithm for automatic scoring of FM and EFM. Future studies will apply it to objectively and consistently evaluate FM indices and the presence of EFM in large populations.

Improved automatic identification of isolated rapid eye movement sleep behavior disorder with a 3D time-of-flight camera.

BACKGROUND AND PURPOSE: Automatic 3D video analysis of the lower body during rapid eye movement (REM) sleep has been recently proposed as a novel tool for identifying people with isolated REM sleep behavior disorder (iRBD), but, so far, it has not been validated on unseen subjects. This study aims at validating this technology in a large cohort and at improving its performances by also including an analysis of movements in the head, hands and upper body. METHODS: Fifty-three people with iRBD and 128 people without RBD (of whom 89 had sleep disorders considered RBD differential diagnoses) were included in the study. An automatic algorithm identified movements from 3D videos during REM sleep in four regions of interest (ROIs): head, hands, upper body and lower body. The movements were divided into categories according to duration: short (0.1-2 s), medium (2-15 s) and long (15-300 s). For each ROI and duration range, features were obtained from the identified movements. Logistic regression models using as predictors the features from one single ROI or a combination of ROIs were trained and tested in a 10-runs 10-fold cross-validation scheme on the task of differentiating people with iRBD from people without RBD. RESULTS: The best differentiation was achieved using short movements in all four ROIs (test accuracy 0.866 ± 0.007, test F1 score = 0.783 ± 0.010). Single group analyses showed that people with iRBD were distinguished successfully from subjects with RBD differential diagnoses. CONCLUSIONS: Automatic 3D video analysis might be implemented in clinical routine as a supportive screening tool for identifying people with RBD.

High Levels of Microplastics in the Arctic Sea Ice Alga Melosira arctica, a Vector to Ice-Associated and Benthic Food Webs.

Plastic pollution has become ubiquitous with very high quantities detected even in ecosystems as remote as Arctic sea ice and deep-sea sediments. Ice algae growing underneath sea ice are released upon melting and can form fast-sinking aggregates. In this pilot study, we sampled and analyzed the ice algaeMelosira arcticaand ambient sea water from three locations in the Fram Strait to assess their microplastic content and potential as a temporary sink and pathway to the deep seafloor. Analysis by µ-Raman and fluorescence microscopy detected microplastics (≥2.2 µm) in all samples at concentrations ranging from 1.3 to 5.7 × 104 microplastics (MP) m-3 in ice algae and from 1.4 to 4.5 × 103 MP m-3 in sea water, indicating magnitude higher concentrations in algae. On average, 94% of the total microplastic particles were identified as 10 µm or smaller in size and comprised 16 polymer types without a clear dominance. The high concentrations of microplastics found in our pilot study suggest thatM. arctica could trap microplastics from melting ice and ambient sea water. The algae appear to be a temporary sink and could act as a key vector to food webs near the sea surface and on the deep seafloor, to which its fast-sinking aggregates could facilitate an important mechanism of transport.

Language analysis of spontaneous descriptions of restless legs syndrome: Gender differences?

Patients with restless legs syndrome (RLS) use various terms when describing their symptoms. Whether gender might influence this has not been investigated so far. The aim of this study was to evaluate possible gender differences in spontaneous descriptions of RLS symptoms. This prospective study, conducted in 100 consecutive German-speaking RLS patients, used a single standardized question. Answers were digitally recorded and transcribed. A content-related linguistic analysis of the transcripts was performed by two independent blinded raters. The lengths of the answers and content-related linguistic features were compared between women and men. Ninety-eight patients were included in the final analysis, 59 women (60.2%) and 39 men (39.8%), with a median age of 62 (23-94) and 63 (31-82) years, respectively (p = 0.602). Demographic and clinical features, including educational level and RLS treatment class, did not differ between genders (p > 0.05). Total word or sentence count showed no gender differences (p = 0.159 and 0.259, respectively), although men used more words per sentence than women (p = 0.018). More men than women described quiescegenic (i.e., triggered by rest or inactivity) symptoms (p = 0.006) and successful attempts at relief (p = 0.039). There was a non-significant trend toward a more frequent use of the first-person perspective in men (median times used = 5 [0-10.5] vs. 3.8 [0-17.5], p = 0.068). The more frequent mention of quiescegenic symptoms and successful attempts at relief in men could indicate differences in phenotypic presentation of RLS between genders, a more precise description of RLS symptoms or a higher experience of self-efficacy in men compared to women.

Rapid eye movement sleep behaviour disorder: Past, present, and future.

This manuscript presents an overview of REM sleep behaviour disorder (RBD) with a special focus on European contributions. After an introduction examining the history of the disorder, we address the pathophysiological and clinical aspects, as well as the diagnostic issues. Further, implications of RBD diagnosis and biomarkers are discussed. Contributions of European researchers to this field are highlighted.

Factors associated with augmentation in patients with restless legs syndrome.

BACKGROUND AND PURPOSE: Augmentation is a paradoxical reaction mainly to dopaminergic medication in patients with restless legs syndrome (RLS), but the exact pathomechanism remains unclear. The aim of this study was to identify factors associated with augmentation in RLS patients. METHODS: RLS patients with and without current or previous augmentation were recruited. Demographic characteristics, history of smoking, questionnaires for depression, alexithymia, and impulsivity, and RLS severity were obtained. RESULTS: We included 122 patients, of whom half had a history of augmentation. Patients with augmentation had a longer disease duration (p = 0.001), had higher RLS severity scores (p = 0.013), had higher levodopa equivalent doses (p < 0.001), had higher scores for alexithymia (p = 0.028), had higher prevalence of impulse control disorders (p < 0.001), more often had a history of smoking (p = 0.039), were more often currently smoking (p = 0.015), and had more average pack-years (p = 0.016). CONCLUSIONS: Here, we describe several factors commonly associated with augmentation in RLS. These may help clinicians to screen and treat patients carefully to avoid the challenging side effect of augmentation.

Tying up Loose Ends of Microplastic Pollution in the Arctic: Distribution from the Sea Surface through the Water Column to Deep-Sea Sediments at the HAUSGARTEN Observatory.

Recent studies have shown that despite its remoteness, the Arctic region harbors some of the highest microplastic (MP) concentrations worldwide. Here, we present the results of a sampling campaign to assess the vertical distribution of MP particles (>11 µm) at five stations of the HAUSGARTEN observatory. Water column samples were taken with large volume pumps by filtering 218-561 L of seawater at two to four depth strata (near-surface, ∼300 m, ∼1000 m, and above seafloor), and sediment samples were taken with a multiple corer. MP concentrations in the water column ranged between 0 and 1287 N m-3 and in the sediment from 239 to 13 331 N kg-1. Fourier transform infrared spectroscopy (FTIR) imaging with automated data analysis showed that polyamide (39%) and ethylene-propylene-diene rubber (23%) were the most abundant polymers within the water samples and polyethylene-chlorinated (31%) in sediments. MPs ≤ 25 µm accounted for more than half of the synthetic particles in every sample. The largest MP particle recorded was in the 200 µm size class. The concentrations of fibers were not reported, as fiber detection by FTIR imaging was not available at the time of analyses. Two- and three-dimensional simulations of particle transport trajectories suggest different pathways for certain polymer types. A positive correlation between MP size composition and particulate organic carbon indicates interactions with biological processes in the water column.

The role of cortisol in trust behavior: Results from an experimental study on healthy controls and patients with juvenile myoclonic epilepsy.

Trust is one of the foundations of human society and pervades all aspects of human live. Research on humans focused primarily on identifying the biological basis of trust behavior in healthy subjects, and this evidence hints to certain brain areas, hormones, and genetic factors to be fundamentally involved. The contribution of cortisol in trust has not yet elicited much attention in research, especially when specifically examined at basal cortisol levels. Trust has been previously studied in some neurological diseases but not in patients with epilepsy, and the influence of hormones on trust in these diseases remains yet unknown. Against this background, we designed an experimental study with a group of patients with juvenile myoclonic epilepsy and a group of healthy controls to compare trust behavior and plasma cortisol levels between the two groups. This economic game is frequently used in research to operationalize trust behavior. All participants further underwent neuropsychological assessment. Our results showed that there was no significant difference in trust behavior during the trust game, but a trend toward lower trust in patients. Furthermore, there was a significant difference in cortisol levels between groups with lower levels in patients. Interestingly, cortisol levels correlated with trust only in the patient group, but not in the control group. Future studies should specifically differentiate the effect of induced cortisol increases (e.g., acute stress) versus the effect of basal cortisol levels reflecting homeostasis or chronic stress on trust behavior and leverage the potential of comparison between patients and healthy controls.

Computer-based monitoring and evaluation of epilepsy-related health variables and their impact on treatment decision.

OBJECTIVE: This study aimed to determine the effectiveness of electronic patient-reported outcomes (ePROs) with focus on epilepsy-specific quality of life, psychiatric and psychosocial burden, drug side effects, and patient satisfaction via the Computer-based Health Evaluation System (CHES) and to evaluate their impact on treatment regimen. METHODS: Forty consecutive patients with drug-resistant focal epilepsy undergoing prolonged video-electroencephalography (EEG) monitoring at the Department of Neurology, Innsbruck Medical University were included and randomized to an intervention group (questionnaire results accessible to the physicians) and a control group (questionnaire results inaccessible to the physicians). Patients had to complete questionnaires on the day of admission (T0) and the day of discharge (T1). RESULTS: Overall, twenty-five patients (25/40, 62.5%) showed abnormal assessment results, twelve of them exclusively due to pathological scores on the Liverpool Adverse Events Profile (LAEP). Mean LAEP score was within the pathological range of 48.8 points (48.8 ±â€¯7.2). The psychosocial burden with respect to the Performance, Socio-Demographic Aspects, Subjective Evaluation (PESOS) scale "fear" (48.7 ±â€¯21.4) was also moderately affected. Moreover, mean anxiety (9.1 ±â€¯4.4) and depression (7.6 ±â€¯4.5) scores were both slightly abnormal. Quality of life (as measured using the Quality of Life Inventory in Epilepsy (QOLIE-31)) was moderately impaired (seizure worry: 46.5 ±â€¯21.3, overall quality of life: 52.6 ±â€¯18.6, well-being: 54.1 ±â€¯16.3, energy-fatigue: 39.4 ±â€¯14.7, cognitive functioning: 41.4 ±â€¯19.5, medication effects: 46.2 ±â€¯23.4, social functioning: 51.1 ±â€¯20.8, and total score: 47.2 ±â€¯12.3). Careful medical history-taking and patient-physician consultations alone failed to detect needs for psychological/psychiatric help in three out of 7 patients in the control group (42.8%). Changes over time in Hospital Anxiety and Depression Scale (HADS) and QOLIE-31 scores were not significant. CONCLUSION: The use of ePROs was feasible and well accepted in the clinical setting. Treatment-associated adverse effects were the most frequently reported health-related restrictions. In particular, psychometric evaluation by applying ePROs can detect health-related problems in patients with epilepsy.

High Quantities of Microplastic in Arctic Deep-Sea Sediments from the HAUSGARTEN Observatory.

Although mounting evidence suggests the ubiquity of microplastic in aquatic ecosystems worldwide, our knowledge of its distribution in remote environments such as Polar Regions and the deep sea is scarce. Here, we analyzed nine sediment samples taken at the HAUSGARTEN observatory in the Arctic at 2340-5570 m depth. Density separation by MicroPlastic Sediment Separator and treatment with Fenton's reagent enabled analysis via Attenuated Total Reflection FTIR and µFTIR spectroscopy. Our analyses indicate the wide spread of high numbers of microplastics (42-6595 microplastics kg-1). The northernmost stations harbored the highest quantities, indicating sea ice as a possible transport vehicle. A positive correlation between microplastic abundance and chlorophyll a content suggests vertical export via incorporation in sinking (ice-) algal aggregates. Overall, 18 different polymers were detected. Chlorinated polyethylene accounted for the largest proportion (38%), followed by polyamide (22%) and polypropylene (16%). Almost 80% of the microplastics were ≤25 µm. The microplastic quantities are among the highest recorded from benthic sediments. This corroborates the deep sea as a major sink for microplastics and the presence of accumulation areas in this remote part of the world, fed by plastics transported to the North via the Thermohaline Circulation.

Clinical neurophysiology of REM parasomnias: Diagnostic aspects and insights into pathophysiology.

Parasomnias are due to a transient unstable state dissociation during entry into sleep, within sleep, or during arousal from sleep, and manifest with abnormal sleep related behaviors, perceptions, emotions, dreams, and autonomic nervous system activity. Rapid eye movement (REM) parasomnias include REM sleep behavior disorder (RBD), isolated recurrent sleep paralysis and nightmare disorder. Neurophysiology is key for diagnosing these disorders and provides insights into their pathophysiology. RBD is very well characterized from a neurophysiological point of view, also thank to the fact that polysomnography is needed for the diagnosis. Diagnostic criteria are provided by the American Academy of Sleep Medicine and video-polysomnography guidelines for the diagnosis by the International REM Sleep Behavior Disorder Study Group. Differences between the two sets of criteria are presented and discussed. Availability of polysomnography in RBD provides data on sleep electroencephalography (EEG), electrooculography (EOG) and electromyography (EMG). Sleep EEG in RBD shows e.g. changes in delta and theta power, in sleep spindles and K complexes. EMG during REM sleep is essential for RBD diagnosis and is an important neurodegeneration biomarker. RBD patients present alterations also in wake EEG, autonomic function, evoked potentials, and transcranial magnetic stimulation. Clinical neurophysiological data on recurrent isolated sleep paralysis and nightmare disorder are scant. The few available data provide insights into the pathophysiology of these disorders, demonstrating a state dissociation in recurrent isolated sleep paralysis and suggesting alterations in sleep macro- and microstructure as well as autonomic changes in nightmare disorder.

Effect of positive airway pressure treatment on excessive fragmentary myoclonus in 100 sleep-related breathing disorder patients.

STUDY OBJECTIVES: Excessive fragmentary myoclonus (EFM) is a frequent finding in patients undergoing video-polysomnography (VPSG). We aimed to evaluate the potential effect of sleep-related breathing disorder's treatment with positive airway pressure (PAP) therapy on EFM. METHODS: One hundred consecutive patients with EFM and sleep-related breathing disorder subsequently treated with PAP at the sleep lab of the Medical University of Innsbruck, Department of Neurology, Austria, were included. Each patient underwent two nights of VPSG: the first night without and the second night with PAP therapy. Fragmentary myoclonus was automatically scored with validated software, and fragmentary myoclonus index (FMI) and minutes of non-rapid eye movement (NREM) sleep with EFM (minNREM+EFM) were calculated. RESULTS: Under PAP therapy there was a significant decrease in the minNREM+EFM - 60.5 (9.5-161.8) at baseline vs. 37.5 (6.3-168.8) minutes under PAP, p = 0.025. No significant differences were observed for FMI between the two nights. Sleep variables, sleep diagnoses, comorbidities, and medication did not influence FMI or the minNREM+EFM. CONCLUSIONS: The initiation of PAP treatment led to a significant reduction of minNREM+EFM, but not of FMI. The results suggest that PAP therapy might influence the distribution of FM potentials.

Genome-wide meta-analyses of restless legs syndrome yield insights into genetic architecture, disease biology and risk prediction.

Restless legs syndrome (RLS) affects up to 10% of older adults. Their healthcare is impeded by delayed diagnosis and insufficient treatment. To advance disease prediction and find new entry points for therapy, we performed meta-analyses of genome-wide association studies in 116,647 individuals with RLS (cases) and 1,546,466 controls of European ancestry. The pooled analysis increased the number of risk loci eightfold to 164, including three on chromosome X. Sex-specific meta-analyses revealed largely overlapping genetic predispositions of the sexes (rg = 0.96). Locus annotation prioritized druggable genes such as glutamate receptors 1 and 4, and Mendelian randomization indicated RLS as a causal risk factor for diabetes. Machine learning approaches combining genetic and nongenetic information performed best in risk prediction (area under the curve (AUC) = 0.82-0.91). In summary, we identified targets for drug development and repurposing, prioritized potential causal relationships between RLS and relevant comorbidities and risk factors for follow-up and provided evidence that nonlinear interactions are likely relevant to RLS risk prediction.

Differentiation of central disorders of hypersomnolence with manual and artificial-intelligence-derived polysomnographic measures.

Differentiation of central disorders of hypersomnolence (DOH) is challenging but important for patient care. This study aimed to investigate whether biomarkers derived from sleep structure evaluated both by manual scoring as well as with artificial intelligence (AI) algorithms allow distinction of patients with different DOH. We included video-polysomnography data of 40 narcolepsy type 1 (NT1), 26 narcolepsy type 2 (NT2), 23 patients with idiopathic hypersomnia (IH) and 54 participants with subjective excessive daytime sleepiness (sEDS). Sleep experts manually scored sleep stages. A previously validated AI algorithm was employed to obtain automatic hypnograms and hypnodensity graphs (where each epoch is represented as a mixture of sleep stage probabilities). One-thousand-three features describing sleep architecture and instability were extracted from manual/automatic hypnogram and hypnodensity graphs. After feature selection, random forest classifiers were trained and tested in a 5-fold-cross-validation scheme to distinguish groups pairwise (NT1-vs-NT2, NT1-vs-IH, …) and single groups from the pooled remaining ones (NT1-vs-rest, NT2-vs-rest,…). The accuracy/F1-score values obtained in the test sets were: 0.74 ± 0.04/0.79 ± 0.05 (NT1-vs-NT2), 0.89 ± 0.09/0.91 ± 0.08 (NT1-vs-IH), 0.93 ± 0.06/0.91 ± 0.07 (NT1-vs-sEDS), 0.88 ± 0.04/0.80 ± 0.07 (NT1-vs-rest), 0.65 ± 0.10/0.70 ± 0.09 (NT2-vs-IH), 0.72 ± 0.12/0.60 ± 0.10 (NT2-vs-sEDS), 0.54 ± 0.19/0.38 ± 0.13 (NT2-vs-rest), 0.57 ± 0.11/0.35 ± 0.18 (IH-vs-sEDS), 0.71 ± 0.08/0.35 ± 0.10 (IH-vs-rest) and 0.76 ± 0.08/0.71 ± 0.13 (sEDS-vs-rest). The results confirm previous findings on sleep instability in patients with NT1 and show that combining manual and automatic AI-based sleep analysis could be useful for better distinction of NT2 from IH, but no precise sleep biomarker of NT2 or IH could be identified. Validation in a larger and multi-centric cohort is needed to confirm these findings.