Taltirelin Hydrate in Patients with Ataxia Due to Spinocerebellar Degeneration.

Objective: We conducted this study to assess the efficacy and safety of taltirelin hydrate (TH) in spinocerebellar degeneration (SCD). Methods: Patients were randomly assigned to either the taltirelin group (5 mg orally, twice daily) or the control group. The primary endpoint was changes in the Korean version of Scale for the Assessment and Rating of Ataxia (K-SARA) scores at 24 weeks. The secondary endpoints include changes in the K-SARA scores at 4 and 12 weeks, the Clinical Global Impression, Five-level version of the EuroQol five-dimensional questionnaire, Tinetti balance test and gait analysis at 4, 12 and 24 weeks. Results: A total of 149 patients (hereditary:non-hereditary = 86:63) were enrolled. There were significant differences in changes in K-SARA scores at 24 weeks from baseline between the taltirelin group and the control group (-0.51 ± 2.79 versus 0.36 ± 2.62, respectively; p = 0.0321). Of the K-SARA items, both 'Stance' and 'Speech disturbance' had significantly lower subscores in the taltirelin group as compared with the control group (-0.04 ± 0.89 versus 0.23 ± 0.79 and -0.07 ± 0.74 versus 0.18 ± 0.67; p = 0.0270 and 0.0130, respectively). But there were no significant differences in changes in other secondary efficacy outcome measures at 24 weeks from baseline between the two treatment arms (p > 0.05). Conclusion: Clinicians might consider using TH in the treatment of ataxia due to SCD.

Clonal hematopoiesis with DNMT3A mutations is associated with multiple system atrophy.

BACKGROUND: Clonal hematopoiesis of indeterminate potential (CHIP) is associated with cardiovascular diseases and other disorders, possibly via inflammation. Recent research suggests a connection of CHIP with neurodegenerative disorders. OBJECTIVE: We aimed to investigate the association between multiple system atrophy (MSA) and CHIP. METHODS: We included 100 patients with MSA and 4457 controls. Targeted sequencing of peripheral blood DNA samples was performed, focusing on a panel of 25 genes commonly. LINKED TO CHIP: The prevalence of CHIP in patients with MSA was assessed against controls at variant allele frequency (VAF) thresholds of 1.5 % and 2.0 %. RESULTS: DNMT3A mutation rates were significantly higher in patients with MSA, with a VAF of 1.5 %, which remained significant after adjusting for age and sex (adjusted odds ratio, 1.848; 95 % CI, 1.024-3.335; p = 0.0416). CONCLUSION: Our results suggest an association between DNMT3A mutations and MSA.

Machine learning-based classification of Parkinson's disease using acoustic features: Insights from multilingual speech tasks.

This study advances the automation of Parkinson's disease (PD) diagnosis by analyzing speech characteristics, leveraging a comprehensive approach that integrates a voting-based machine learning model. Given the growing prevalence of PD, especially among the elderly population, continuous and efficient diagnosis is of paramount importance. Conventional monitoring methods suffer from limitations related to time, cost, and accessibility, underscoring the need for the development of automated diagnostic tools. In this paper, we present a robust model for classifying speech patterns in Korean PD patients, addressing a significant research gap. Our model employs straightforward preprocessing techniques and a voting-based machine learning approach, demonstrating superior performance, particularly when training data is limited. Furthermore, we emphasize the effectiveness of the eGeMAPSv2 feature set in PD analysis and introduce new features that substantially enhance classification accuracy. The proposed model, achieving an accuracy of 84.73 % and an area under the ROC (AUC) score of 92.18 % on a dataset comprising 100 Korean PD patients and 100 healthy controls, offers a practical solution for automated diagnosis applications, such as smartphone apps. Future research endeavors will concentrate on enhancing the model's performance and delving deeper into the relationship between high-importance features and PD.

Parkinson's disease is associated with clonal hematopoiesis with TET2 mutation.

Clonal hematopoiesis of indeterminate potential (CHIP), a premalignant expansion of mutated hematopoietic stem cells, is linked to immune alterations. Given the role of neuroinflammation and immune dysfunction in Parkinson's disease (PD), we hypothesized a connection between CHIP and PD. We analyzed peripheral blood DNA from 341 PD, 92 isolated REM sleep behavior disorder (iRBD) patients, and 5003 controls using targeted sequencing of 24 genes associated with hematologic neoplasms. PD cases were classified by clinical progression mode: fast, slow, and typical. Using multivariable logistic regression models, CHIP prevalence was assessed against controls with a 1.0% variant allele fraction threshold. CHIP with TET2 mutations was more prevalent in PD than controls (aOR 1.75, 95% CI 1.11-2.77, p = 0.017), particularly in the fast motor progression subgroup (aOR 3.19, p = 0.004). No distinct associations were observed with iRBD. PD is linked to increased odds of CHIP with TET2 mutations, suggesting immune dysregulation in PD pathophysiology.

Monoaminergic degeneration, cognition, and autonomic symptom trajectory in early Parkinson's disease.

INTRODUCTION: Parkinson's disease (PD) encompasses a range of non-motor symptoms attributed to deficits in various neurotransmitter systems. This study aimed to investigate the associations between cognitive and autonomic symptoms and the degeneration of brainstem monoaminergic nuclei, particularly the serotonergic and noradrenergic nuclei, in a prospective cohort of early PD patients. METHODS: Twenty-eight early PD patients (with an average disease duration of approximately three years) underwent baseline [18F]FP-CIT positron emission tomography (PET) scans, Montreal Cognitive Assessment (MoCA), and Composite Autonomic Symptom Scale-31 (COMPASS-31) evaluations, followed by repeat MoCA and COMPASS-31 assessments three years later. Regression models were utilized to analyze both cross-sectional and longitudinal changes in non-motor symptoms relative to baseline degeneration of the noradrenergic locus coeruleus (LC) and serotonergic raphe, normalized by striatal dopaminergic terminal loss. RESULTS: Baseline LC and raphe degeneration in early PD was cross-sectionally associated with poorer MoCA performances. Over the three-year follow-up, gastrointestinal symptoms exhibited progression, while cognitive scores remained stable. Profound baseline degeneration of the LC and raphe, relative to nigrostriatal terminal loss, were predictive of subsequent accelerated deterioration in gastrointestinal symptoms. CONCLUSION: Brainstem non-dopaminergic dysfunction in early PD is linked to cognitive dysfunction and predicts progression in gastrointestinal symptoms, offering potential indicators for worsening non-motor trajectories.

Clinical characteristics and phenoconversion in isolated REM sleep behavior disorder: a prospective single-center study in Korea, compared with Montreal cohort.

STUDY OBJECTIVES: Isolated rapid-eye movement behavior disorder (iRBD) is a prodromal synucleinopathy, but its conversion rate and subtypes can vary among different cohorts. We report the clinical characteristics and phenoconversion rate of the large single-center iRBD cohort in Korea and compared it to the Montreal cohort. METHODS: This prospective cohort study examined 238 patients with polysomnography confirmed iRBD from Seoul National University Hospital (SNUH) who completed at least one follow-up evaluation. We compared the baseline and phenoconversion data of the SNUH cohort to those of 242 iRBD patients in the Montreal cohort. RESULTS: In the SNUH cohort, age at RBD diagnosis was similar (66.4±7.8 vs 65.6±8.4, p=0.265), but the proportion of men was lower (63.0% vs. 74.0%, p=0.001), and the duration of follow-up was shorter than that in the Montreal cohort (3.7±2.0 vs. 4.8±3.6 years, p<0.001). During follow-up, 34 (11.8%) patients in the SNUH cohort converted to neurodegenerative disease: 18 (52.9%) to Parkinson's disease, 9 (26.5%) to dementia with Lewy bodies (DLB), and 7 (20.6%) to multiple system atrophy. The conversion rate in the SNUH cohort was 15% after 3 years, 22% after 5 years, and 32% after 7 years, which was significantly lower than that of the Montreal cohort (log-rank test, p=0.002). Among phenoconversion subtype, fewer subjects in the SNUH group than in the Montreal group converted to DLB (Gray's test p=0.001). CONCLUSIONS: Through a comparative analysis between the SNUH and Montreal cohorts, we identified a significant difference in phenoconversion rates, particularly for DLB patients. These findings underscore the importance of further research into the underlying factors, such as racial and geographical factors contributing to such disparities.

Diagnostic accuracy and predictors of alpha-synuclein accumulation in the gastrointestinal tract of Parkinson's disease.

The only characteristic of alpha-synuclein (AS) accumulation in the gastrointestinal (GI) tract of Parkinson's disease (PD) found in pathological studies is the "rostrocaudal gradient," which describes the more frequent presence of AS accumulation in the upper GI tract than in the lower GI tract. This study aimed to determine the diagnostic accuracy and identify predictors of AS accumulation in the GI tract of PD patients. The frequency of AS accumulation in the GI tract was compared between PD patients (N = 97) who underwent radical GI surgery for cancer and individually matched controls (N = 94). We evaluated AS accumulation in the neural structures using phosphorylated AS immunohistochemistry. A multivariable logistic regression analysis was conducted to determine the predictors of AS accumulation in the GI tract of PD patients. The frequency of AS accumulation was significantly higher in PD patients (75.3%) than in controls (8.5%, p-value < 0.001). The sensitivity and specificity of the full-layer evaluation were 75.3% and 91.5%, respectively. When the evaluation was confined to the mucosal/submucosal layer, the sensitivity and specificity were 46.9% and 94.7%, respectively. The rostrocaudal gradient of AS accumulation was found in PD patients. The duration from symptom onset to surgery was significantly longer in PD patients with AS accumulation (4.9 ± 4.9 years) than in PD patients without AS accumulation (1.8 ± 4.1 years, p-value = 0.005). Both disease duration and rostrocaudal gradient independently predicted the presence of AS accumulation in the GI tract of PD patients. Our study suggests PD-related AS accumulation in the GI tract follows a temporally increasing but spatially static progression pattern.

Prognostic Implication of Ventricular Volumetry in Early Brain Computed Tomography after Cardiac Arrest.

Brain swelling after cardiac arrest may affect brain ventricular volume. This study aimed to investigate the prognostic implications of ventricular volume on early thin-slice brain computed tomography (CT) after cardiac arrest. We measured the gray-to-white matter ratio (GWR) and the characteristics and volumes of the lateral, third, and fourth ventricles. The primary outcome was a poor 6-month neurological outcome. Of the 166 patients, 115 had a poor outcome. The fourth ventricle was significantly smaller in the poor outcome group (0.58 cm3 [95% CI, 0.43-0.80]) than in the good outcome group (0.74 cm3 [95% CI, 0.68-0.99], p < 0.001). Ventricular characteristics and other ventricular volumes did not differ between outcome groups. The area under the curve for the fourth ventricular volume was 0.68, comparable to 0.69 for GWR. Lower GWR (<1.09) and lower fourth ventricular volume (<0.41 cm3) predicted poor outcomes with 100% specificity and sensitivities of 8.7% (95% CI, 4.2-15.4) and 20.9% (95% CI, 13.9-29.4), respectively. Combining these measures improved the sensitivity to 25.2% (95% CI, 17.6-34.2). After adjusting for covariates, the fourth ventricular volume was independently associated with neurologic outcome. A marked decrease in fourth ventricular volume, with concomitant hypoattenuation on CT scans, more accurately predicted outcomes.

Exploring Spectrogram-Based Audio Classification for Parkinson's Disease: A Study on Speech Classification and Qualitative Reliability Verification.

Patients suffering from Parkinson's disease suffer from voice impairment. In this study, we introduce models to classify normal and Parkinson's patients using their speech. We used an AST (audio spectrogram transformer), a transformer-based speech classification model that has recently outperformed CNN-based models in many fields, and a CNN-based PSLA (pretraining, sampling, labeling, and aggregation), a high-performance model in the existing speech classification field, for the study. This study compares and analyzes the models from both quantitative and qualitative perspectives. First, qualitatively, PSLA outperformed AST by more than 4% in accuracy, and the AUC was also higher, with 94.16% for AST and 97.43% for PSLA. Furthermore, we qualitatively evaluated the ability of the models to capture the acoustic features of Parkinson's through various CAM (class activation map)-based XAI (eXplainable AI) models such as GradCAM and EigenCAM. Based on PSLA, we found that the model focuses well on the muffled frequency band of Parkinson's speech, and the heatmap analysis of false positives and false negatives shows that the speech features are also visually represented when the model actually makes incorrect predictions. The contribution of this paper is that we not only found a suitable model for diagnosing Parkinson's through speech using two different types of models but also validated the predictions of the model in practice.

Late-Onset Ataxia-Telangiectasia Presenting With Dystonia and Tremor: The Use of Nanopore Long-Read Sequencing Solving the Variant Phase.

Objectives: This study investigates atypical late-onset ataxia-telangiectasia (AT) cases in a Korean family, diagnosed via Nanopore long-read sequencing, diverging from the typical early childhood onset caused by biallelic pathogenic ATM variants. Methods: A 52-year-old Korean woman exhibiting dystonia and tremor, with a family history of similar symptoms in her older sister, underwent comprehensive tests including routine laboratory tests, neuropsychological assessments, and neuroimaging. Genetic analysis was conducted through targeted sequencing of 29 dystonia-associated genes and Nanopore long-read sequencing to assess the configuration of 2 ATM gene variants. Results: Routine blood tests and brain imaging studies returned normal results, except for elevated α-fetoprotein levels. Neurologic examination revealed dystonia in the face, hand, and trunk, along with cervical dystonia in the proband. Her sister exhibited similar symptoms without evident telangiectasia. Genetic testing revealed 2 heterozygous pathogenic ATM gene variants (p.Glu2014Ter and p.Glu2052Lys). Nanopore long-read sequencing confirmed these variants were in trans configuration, establishing a definite molecular diagnosis in the proband. Discussion: This report expands the known clinical spectrum of AT, highlighting a familial case of atypical AT. Moreover, it underscores the clinical utility of Nanopore long-read sequencing in phasing variant haplotypes, essential for diagnosing autosomal recessive disorders, especially beneficial for cases without parental samples.

Wireless sequential dual light delivery for programmed PDT in vivo.

Using photodynamic therapy (PDT) to treat deep-seated cancers is limited due to inefficient delivery of photosensitizers and low tissue penetration of light. Polymeric nanocarriers are widely used for photosensitizer delivery, while the self-quenching of the encapsulated photosensitizers would impair the PDT efficacy. Furthermore, the generated short-lived reactive oxygen spieces (ROS) can hardly diffuse out of nanocarriers, resulting in low PDT efficacy. Therefore, a smart nanocarrier system which can be degraded by light, followed by photosensitizer activation can potentially overcome these limitations and enhance the PDT efficacy. A light-sensitive polymer nanocarrier encapsulating photosensitizer (RB-M) was synthesized. An implantable wireless dual wavelength microLED device which delivers the two light wavelengths sequentially was developed to programmatically control the release and activation of the loaded photosensitizer. Two transmitter coils with matching resonant frequencies allow activation of the connected LEDs to emit different wavelengths independently. Optimal irradiation time, dose, and RB-M concentration were determined using an agent-based digital simulation method. In vitro and in vivo validation experiments in an orthotopic rat liver hepatocellular carcinoma disease model confirmed that the nanocarrier rupture and sequential low dose light irradiation strategy resulted in successful PDT at reduced photosensitizer and irradiation dose, which is a clinically significant event that enhances treatment safety.

Prevalence and Characterization of NOTCH2NLC GGC Repeat Expansions in Koreans: From a Hospital Cohort Analysis to a Population-Wide Study.

Background and Objectives: GGC repeat expansions in the NOTCH2NLC gene are associated with a broad spectrum of progressive neurologic disorders, notably, neuronal intranuclear inclusion disease (NIID). We aimed to investigate the population-wide prevalence and clinical manifestations of NOTCH2NLC-related disorders in Koreans. Methods: We conducted a study using 2 different cohorts from the Korean population. Patients with available brain MRI scans from Seoul National University Hospital (SNUH) were thoroughly reviewed, and NIID-suspected patients presenting the zigzag edging signs underwent genetic evaluation for NOTCH2NLC repeats by Cas9-mediated nanopore sequencing. In addition, we analyzed whole-genome sequencing data from 3,887 individuals in the Korea Biobank cohort to estimate the distribution of the repeat counts in Koreans and to identify putative patients with expanded alleles and neurologic phenotypes. Results: In the SNUH cohort, among 90 adult-onset leukoencephalopathy patients with unknown etiologies, we found 20 patients with zigzag edging signs. Except for 2 diagnosed with fragile X-associated tremor/ataxia syndrome and 2 with unavailable samples, all 16 patients (17.8%) were diagnosed with NIID (repeat range: 87-217). By analyzing the Korea Biobank cohort, we estimated the distribution of repeat counts and threshold (>64) for Koreans, identifying 6 potential patients with NIID. Furthermore, long-read sequencing enabled the elucidation of transmission and epigenetic patterns of NOTCH2NLC repeats within a family affected by pediatric-onset NIID. Discussion: This study presents the population-wide distribution of NOTCH2NLC repeats and the estimated prevalence of NIID in Koreans, providing valuable insights into the association between repeat counts and disease manifestations in diverse neurologic disorders.

Symmetric and Profound Monoaminergic Degeneration in Parkinson's Disease with Premotor REM Sleep Behavior Disorder.

Background: Rapid eye movement sleep behavior disorder (RBD) may precede or follow motor symptoms in Parkinson's disease (PD). While over 70% of idiopathic RBD cases phenoconvert within a decade, a small subset develops PD after a more extended period or remains nonconverted. These heterogeneous manifestations of RBD in PD prompt subtype investigations. Premotor RBD may signify "body-first" PD with bottom-up, symmetric synucleinopathy propagation. Objective: Explore brainstem and nigrostriatal monoaminergic degeneration pattern differences based on premotor RBD presence and duration in de novo PD patients. Methods: In a cross-sectional analysis of de novo PD patients (n = 150) undergoing FP-CIT PET and RBD Single-Question Screen, the cohort was categorized into groups with and without premotor RBD (PDRBD +/-), with further classification of PDRBD + based on a 10-year duration of premotor RBD. Analysis of FP-CIT binding in the striatum and pons, striatal asymmetry, and striatum-to-pons ratios compared patterns of nigrostriatal and brainstem monoaminergic degeneration. Results: PDRBD + exhibited more severe and symmetrical striatal dopaminergic denervation compared to PDRBD-, with the difference in severity accentuated in the least-affected hemisphere. The PDRBD +<10Y subgroup displayed the most prominent striatal symmetry, supporting a more homogeneous "body-first" subtype. Pontine uptakes remained lower in PDRBD + even after adjusting for striatal uptake, suggesting early degeneration of pontine monoaminergic nuclei. Conclusions: Premotor RBD in PD is associated with severe, symmetrical nigrostriatal and brainstem monoaminergic degeneration, especially in cases with PD onset within 10 years of RBD. This supports the concept of a "widespread, bottom-up" pathophysiological mechanism associated with premotor RBD in PD.

The prevalence of non-troublesome dyskinesia in Parkinson's disease.

INTRODUCTION: Levodopa-induced dyskinesia is a common complication of long-term treatment of Parkinson's disease (PD), but its impact on daily activities is somewhat controversial. This study investigated the prevalence and severity of dyskinesia, particularly non-troublesome dyskinesia, to provide insights into its significance for long-term PD management. METHODS: We reviewed electronic medical records of 2571 PD patients, who had been followed up at Seoul National University Hospital and were seen between January 2016 and June 2017. Dyskinesia severity had been assessed during follow-up and was recorded with the highest score by considering its impact on functioning (0 = no dyskinesia, 1 = minimal with patient unaware, 2 = mild disability, 3 = moderate disability, 4 = severe disability). RESULTS: The prevalence of dyskinesia increased progressively with longer PD duration; 8.2% in the group with disease duration of 0-5 years, 40.7% for 6-10 years, 66.0% for 11-15 years, 74.6% for 16-20 years, and 83.2% for 21 years or more. The prevalence of dyskinesia scores ≥2 also increased with disease duration, with rates of 6.3% for 0-5 years, 31.9% for 6-10 years, 54.8% for 11-15 years, 62.9% for 16-20 years and 73.7% for 21 or more years. CONCLUSION: Despite the increasing prevalence and severity of dyskinesia with longer PD duration, the study found that less than non-troublesome dyskinesia remained at approximately 26.3% even after more than 21 years of disease duration. These findings suggest that dyskinesia may not be troublesome for many PD patients even in long-term.

Evaluating the Validity and Reliability of the Korean Version of the Scales for Outcomes in Parkinson's Disease-Cognition.

OBJECTIVE: The Scales for Outcomes in Parkinson's Disease-Cognition (SCOPA-Cog) was developed to assess cognition in patients with Parkinson's disease (PD). In this study, we aimed to evaluate the validity and reliability of the Korean version of the SCOPACog (K-SCOPA-Cog). METHODS: We enrolled 129 PD patients with movement disorders from 31 clinics in South Korea. The original version of the SCOPA-Cog was translated into Korean using the translation-retranslation method. The test-retest method with an intraclass correlation coefficient (ICC) and Cronbach's alpha coefficient were used to assess reliability. Spearman's rank correlation analysis with the Montreal Cognitive Assessment-Korean version (MOCA-K) and the Korean Mini-Mental State Examination (K-MMSE) were used to assess concurrent validity. RESULTS: The Cronbach's alpha coefficient was 0.797, and the ICC was 0.887. Spearman's rank correlation analysis revealed a significant correlation with the K-MMSE and MOCA-K scores (r = 0.546 and r = 0.683, respectively). CONCLUSION: Our. RESULTS: demonstrate that the K-SCOPA-Cog has good reliability and validity.

Electroencephalographic spectro-spatial covariance patterns related to phenoconversion in isolated rapid eye movement sleep behavior disorder and their longitudinal trajectories in α-synucleinopathies.

STUDY OBJECTIVES: This study aimed to identify electroencephalographic (EEG) spectro-spatial covariance patterns associated with phenoconversion in isolated rapid eye movement sleep behavior disorder (iRBD) patients and explore their longitudinal trajectories within α-synucleinopathies. METHODS: We assessed 47 participants, including 35 patients with iRBD and 12 healthy controls (HC), through baseline eye-closed resting EEGs. Patients with iRBD underwent follow-up EEG assessments and 18 patients with iRBD converted (12 to Parkinson's disease (PD), 6 to dementia with Lewy bodies [DLB]) during follow-up. We derived EEG spectro-spatial covariance patterns for PD-RBD and DLB-RBD from converters and HC. Correlations with motor and cognitive function, baseline distinctions among iRBD converters and nonconverters, and longitudinal trajectories were examined. RESULTS: At baseline, converters exhibited higher PD-RBD and DLB-RBD beta2 pattern scores compared to nonconverters (each area under curve [AUC] = 0.7751). The delta and alpha spatial patterns effectively distinguished both PD and DLB converters from HC, with the alpha pattern showing high discriminative power (AUC = 0.9097 for PD-RBD, 0.9306 for DLB-RBD). Movement Disorder Society-Sponsored Revision of the Unified Parkinson's Disease Rating Scale part III scores correlated positively with PD-RBD and DLB-RBD delta patterns (Spearman's rho = 0.688, p = 0.00014; rho = 0.539, p = 0.0055, respectively), with age and sex as cofactors. Distinct trajectories emerged during follow-up among PD converters, DLB converters, and iRBD nonconverters. CONCLUSIONS: Unique EEG spectro-spatial patterns specific to PD-RBD and DLB-RBD offer potential as predictive markers for phenoconversion to α-synucleinopathies in iRBD.

EEG-based machine learning models for the prediction of phenoconversion time and subtype in isolated rapid eye movement sleep behavior disorder.

STUDY OBJECTIVES: Isolated rapid eye movement sleep behavior disorder (iRBD) is a prodromal stage of α-synucleinopathies and eventually phenoconverts to overt neurodegenerative diseases including Parkinson's disease (PD), dementia with Lewy bodies (DLB), and multiple system atrophy (MSA). Associations of baseline resting-state electroencephalography (EEG) with phenoconversion have been reported. In this study, we aimed to develop machine learning models to predict phenoconversion time and subtype using baseline EEG features in patients with iRBD. METHODS: At baseline, resting-state EEG and neurological assessments were performed on patients with iRBD. Calculated EEG features included spectral power, weighted phase lag index, and Shannon entropy. Three models were used for survival prediction, and four models were used for α-synucleinopathy subtype prediction. The models were externally validated using data from a different institution. RESULTS: A total of 236 iRBD patients were followed up for up to 8 years (mean 3.5 years), and 31 patients converted to α-synucleinopathies (16 PD, 9 DLB, 6 MSA). The best model for survival prediction was the random survival forest model with an integrated Brier score of 0.114 and a concordance index of 0.775. The K-nearest neighbor model was the best model for subtype prediction with an area under the receiver operating characteristic curve of 0.901. Slowing of the EEG was an important feature for both models. CONCLUSIONS: Machine learning models using baseline EEG features can be used to predict phenoconversion time and its subtype in patients with iRBD. Further research including large sample data from many countries is needed to make a more robust model.