Yong Woo Shin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yong Woo Shin has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Ki-Young Jung
Department of Neurology, Seoul National University Hospital, Seoul National University College of Medicine, Seoul 03080, Republic of Korea
4 shared publications - Han-Joon Kim
Department of Neurology, Seoul National University Hospital, College of Medicine, Seoul National University, Seoul, Republic of Korea
3 shared publications - Jun-Sang Sunwoo
Department of Neurology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, Korea
3 shared publications - Jung-Ick Byun
Department of Neurology, Kyung Hee University Hospital at Gangdong, Seoul, Korea
3 shared publications - Dario Arnaldi
Department of Neuroscience (DINOGMI), University of Genoa, Italy
2 shared publications - El Jeong
Interdisciplinary Program in Bioengineering, College of Engineering, Seoul National University , Seoul , South Korea
2 shared publications
Latest Publications
- Open Access
- 1 August 2024
- Published by Korean Sleep Society in Journal of Sleep Medicine
- Vol. 21 (2) , 123-125
Localized Upper Back Pain: A Rare Variant of Restless Legs Syndrome
Restless legs syndrome (RLS) is a chronic sensory-motor neuron disorder characterized by an urge to move the legs, accompanied by abnormal sensations and pain that occur during sitting and resting periods but are relieved by movement. Although RLS typically affects the lower limbs, cases of localized sensation in the chest, lower back, abdomen, arm, and perineum have also been reported. To date, only one documented case of RLS localized to the upper back has been reported. In this report, we present a rare variant of RLS that manifests as symptoms localized in the upper back.
- 1 August 2024
- Published by Korean Sleep Society in Journal of Sleep Medicine
- Vol. 21 (2) , 123-125
Open AccessLocalized Upper Back Pain: A Rare Variant of Restless Legs Syndrome
Restless legs syndrome (RLS) is a chronic sensory-motor neuron disorder characterized by an urge to move the legs, accompanied by abnormal sensations and pain that occur during sitting and resting periods but are relieved by movement. Although RLS typically affects the lower limbs, cases of localized sensation in the chest, lower back, abdomen, arm, and perineum have also been reported. To date, only one documented case of RLS localized to the upper back has been reported. In this report, we present a rare variant of RLS that manifests as symptoms localized in the upper back.
- Open Access
FORECAST-RBD: Forecasting Phenoconversion Risks and Its Clinical Phenotype in Patients with Isolated RBD Using Machine Learning and Explainable AI
Background and Objectives: Isolated Rapid Eye Movement (REM) sleep behavior disorder (iRBD) is a sleep disorder associated with neurodegenerative diseases such as Parkinson’s disease and dementia with Lewy bodies. Predicting which iRBD patients will phenoconvert to neurodegenerative diseases is crucial for prognosis and management. The objective of this study is to develop a machine learning model using clinical markers to predict phenoconversion in patients with RBD. Methods: Analyzing a cohort of 178 iRBD patients over a median follow-up period of 3.6 years, during which 30 patients converted to neurodegenerative conditions, we leveraged an comprehensive dataset encompassing demographics, medication history, cognitive assessments, sleep quality, autonomic symptoms, and parkinsonian signs. We explored a variety of feature selection methods and survival models. Additionally, separate models to predict the subtype of photoconversion—whether motor-first or cognition-first—were developed. Results: The extreme gradient boosting survival embeddings-Kaplan neighbors (XGBSE-KN) model demonstrated the best performance, achieving a concordance index of 0.823 and integrated Brier score of 0.123 on 10-fold cross-validation. Explainable AI methods provided insights into prediction rationales and key risk factors including age, RBDQ-KR factor 2 (behavioral factors), weight, antidepressant, coffee use, and UPDRS III excluding tremor score. For subtype classification, the RandomForestClassifier utilizing three features (PSQI-TST, MoCA, and age), emerged as the most effective, achieving a Matthews Correlation Coefficient of 0.697 in 100 repeated 5-fold cross-validations. These models have been deployed on a server for physician access. Discussion: These models can aid prognosis and enable personalized management in RBD patients, potentially improving patient care and outcomes. While these findings are promising, further external validation of the models is necessary to confirm their efficacy and reliability in clinical settings. Future research should focus on incorporating additional biomarkers and exploring the models’ performance in larger, diverse cohorts.
Open AccessFORECAST-RBD: Forecasting Phenoconversion Risks and Its Clinical Phenotype in Patients with Isolated RBD Using Machine Learning and Explainable AI
Background and Objectives: Isolated Rapid Eye Movement (REM) sleep behavior disorder (iRBD) is a sleep disorder associated with neurodegenerative diseases such as Parkinson’s disease and dementia with Lewy bodies. Predicting which iRBD patients will phenoconvert to neurodegenerative diseases is crucial for prognosis and management. The objective of this study is to develop a machine learning model using clinical markers to predict phenoconversion in patients with RBD. Methods: Analyzing a cohort of 178 iRBD patients over a median follow-up period of 3.6 years, during which 30 patients converted to neurodegenerative conditions, we leveraged an comprehensive dataset encompassing demographics, medication history, cognitive assessments, sleep quality, autonomic symptoms, and parkinsonian signs. We explored a variety of feature selection methods and survival models. Additionally, separate models to predict the subtype of photoconversion—whether motor-first or cognition-first—were developed. Results: The extreme gradient boosting survival embeddings-Kaplan neighbors (XGBSE-KN) model demonstrated the best performance, achieving a concordance index of 0.823 and integrated Brier score of 0.123 on 10-fold cross-validation. Explainable AI methods provided insights into prediction rationales and key risk factors including age, RBDQ-KR factor 2 (behavioral factors), weight, antidepressant, coffee use, and UPDRS III excluding tremor score. For subtype classification, the RandomForestClassifier utilizing three features (PSQI-TST, MoCA, and age), emerged as the most effective, achieving a Matthews Correlation Coefficient of 0.697 in 100 repeated 5-fold cross-validations. These models have been deployed on a server for physician access. Discussion: These models can aid prognosis and enable personalized management in RBD patients, potentially improving patient care and outcomes. While these findings are promising, further external validation of the models is necessary to confirm their efficacy and reliability in clinical settings. Future research should focus on incorporating additional biomarkers and exploring the models’ performance in larger, diverse cohorts.
- 8 February 2024
- Published by Oxford University Press (OUP) in SLEEP
- Vol. 47 (5)
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.
- 8 February 2024
- Published by Oxford University Press (OUP) in SLEEP
- Vol. 47 (5)
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.
- Open Access
EEG-based Machine Learning Models for the Prediction of Phenoconversion Time and Subtype in iRBD
Background Idiopathic/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. Objectives 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 eight 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. EEG slowing 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.
Open AccessEEG-based Machine Learning Models for the Prediction of Phenoconversion Time and Subtype in iRBD
Background Idiopathic/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. Objectives 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 eight 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. EEG slowing 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.
- Open Access
- 30 June 2022
- Published by Korean Society of Neurosonology in Journal of Neurosonology and Neuroimaging
- Vol. 14 (1) , 67-69
Childhood Primary Angiitis of the Central Nervous System Presenting as Isolated Middle Cerebral Artery Dissection
Isolated middle cerebral artery dissection and primary angiitis of the central nervous system are two rare but serious causes of ischemic stroke in children. We report a case of a patient who presented with headache, left-sided hemiparesis, and left hemi-hypoesthesia with acute cerebral infarction in the right middle cerebral artery territory. Brain magnetic resonance imaging showed isolated right middle cerebral artery dissection with arterial wall contrast enhancement extending beyond the length of the dissection and diffuse narrowing with stenosis in the right posterior cerebral artery suggesting angiitis. After exclusion of other diagnoses the patient was treated with corticosteroids and dual antiplatelet therapy. Follow up magnetic resonance imaging performed 4 months later showed partially improved contrast enhancement in the right middle cerebral artery and persistent narrowing and focal stenosis of the right posterior cerebral artery. Although rare, primary angiitis of the central nervous system should be considered in the differential diagnosis of acute stroke in children. High-resolution vessel wall imaging magnetic resonance studies can provide important information in determining the etiology of stroke.
- 30 June 2022
- Published by Korean Society of Neurosonology in Journal of Neurosonology and Neuroimaging
- Vol. 14 (1) , 67-69
Open AccessChildhood Primary Angiitis of the Central Nervous System Presenting as Isolated Middle Cerebral Artery Dissection
Isolated middle cerebral artery dissection and primary angiitis of the central nervous system are two rare but serious causes of ischemic stroke in children. We report a case of a patient who presented with headache, left-sided hemiparesis, and left hemi-hypoesthesia with acute cerebral infarction in the right middle cerebral artery territory. Brain magnetic resonance imaging showed isolated right middle cerebral artery dissection with arterial wall contrast enhancement extending beyond the length of the dissection and diffuse narrowing with stenosis in the right posterior cerebral artery suggesting angiitis. After exclusion of other diagnoses the patient was treated with corticosteroids and dual antiplatelet therapy. Follow up magnetic resonance imaging performed 4 months later showed partially improved contrast enhancement in the right middle cerebral artery and persistent narrowing and focal stenosis of the right posterior cerebral artery. Although rare, primary angiitis of the central nervous system should be considered in the differential diagnosis of acute stroke in children. High-resolution vessel wall imaging magnetic resonance studies can provide important information in determining the etiology of stroke.
- Open Access
- 10 January 2022
- Published by Korean Encephalitis and Neuroinflammation Society in encephalitis
- Vol. 2 (1) , 1-8
Clinical significance of Epstein-Barr virus polymerase chain reaction in cerebrospinal fluid
Purpose: Epstein-Barr virus (EBV) is implicated in various neurological conditions. However, the relationship between EBV DNA in cerebrospinal fluid (CSF) and central nervous system (CNS) infection is unclear. We evaluated the clinical manifestation of patients with EBV DNA detected in CSF.Methods: We reviewed the medical records of patients admitted to Seoul National University Hospital from January 2000 to March 2021 who underwent EBV polymerase chain reaction (PCR) tests in CSF. The subjects were divided into positive and negative groups depending on the presence of EBV DNA, and further clinical information was obtained from positive patients.Results: CSF EBV PCR tests were performed in 807 patients, and 57 (7.1%) tested positive. Pleocytosis was common (81%) in CSF samples with EBV DNA detected, and the proportion was significantly higher than that in samples that were EBV PCR negative (44.5%, p < 0.0001). Among 57 patients with EBV DNA detected in CSF, 51 (89.5%) were diagnosed with CNS infection or inflammatory disorders. Of the 51 patients, 31 (60.8%) had possible etiologies other than EBV. Follow-up evaluation was conducted in 19 of 20 patients, and 63.2% showed a favorable outcome.Conclusion: Positive EBV PCR in CSF is mostly nonspecific and should be interpreted with caution. A comprehensive workup is needed to identify other etiologies before considering EBV as the sole culprit.
- 10 January 2022
- Published by Korean Encephalitis and Neuroinflammation Society in encephalitis
- Vol. 2 (1) , 1-8
Open AccessClinical significance of Epstein-Barr virus polymerase chain reaction in cerebrospinal fluid
Purpose: Epstein-Barr virus (EBV) is implicated in various neurological conditions. However, the relationship between EBV DNA in cerebrospinal fluid (CSF) and central nervous system (CNS) infection is unclear. We evaluated the clinical manifestation of patients with EBV DNA detected in CSF.Methods: We reviewed the medical records of patients admitted to Seoul National University Hospital from January 2000 to March 2021 who underwent EBV polymerase chain reaction (PCR) tests in CSF. The subjects were divided into positive and negative groups depending on the presence of EBV DNA, and further clinical information was obtained from positive patients.Results: CSF EBV PCR tests were performed in 807 patients, and 57 (7.1%) tested positive. Pleocytosis was common (81%) in CSF samples with EBV DNA detected, and the proportion was significantly higher than that in samples that were EBV PCR negative (44.5%, p < 0.0001). Among 57 patients with EBV DNA detected in CSF, 51 (89.5%) were diagnosed with CNS infection or inflammatory disorders. Of the 51 patients, 31 (60.8%) had possible etiologies other than EBV. Follow-up evaluation was conducted in 19 of 20 patients, and 63.2% showed a favorable outcome.Conclusion: Positive EBV PCR in CSF is mostly nonspecific and should be interpreted with caution. A comprehensive workup is needed to identify other etiologies before considering EBV as the sole culprit.
- Open Access
- 31 December 2021
- Published by Korean Society of Neurosonology in Journal of Neurosonology and Neuroimaging
- Vol. 13 (2) , 80-83
Vessel Wall Magnetic Resonance Imaging Findings of Bilateral Middle Cerebral Artery Stenosis Associated with Nilotinib
Nilotinib is a Bcr-Abl tyrosine kinase inhibitor used to treat chronic myelogenous leukemia. There have been case reports of nilotinib-related vasculopathy. However, most cases present peripheral artery disease, whilst reports of nilotinib-related cerebrovascular disease are quite uncommon. Herein, we report a case of nilotinib-induced intracranial stenosis in a patient with recurrent transient ischemic attacks and discuss the results of serial vessel wall magnetic resonance imaging.
- 31 December 2021
- Published by Korean Society of Neurosonology in Journal of Neurosonology and Neuroimaging
- Vol. 13 (2) , 80-83
Open AccessVessel Wall Magnetic Resonance Imaging Findings of Bilateral Middle Cerebral Artery Stenosis Associated with Nilotinib
Nilotinib is a Bcr-Abl tyrosine kinase inhibitor used to treat chronic myelogenous leukemia. There have been case reports of nilotinib-related vasculopathy. However, most cases present peripheral artery disease, whilst reports of nilotinib-related cerebrovascular disease are quite uncommon. Herein, we report a case of nilotinib-induced intracranial stenosis in a patient with recurrent transient ischemic attacks and discuss the results of serial vessel wall magnetic resonance imaging.
- Open Access
- 1 January 2021
- Published by Korean Neurological Association in Journal of Clinical Neurology
- Vol. 17 (1) , 131-133
Occult Growing Teratoma as the Cause of Protracted Symptoms in a Patient with Anti-NMDA-Receptor Encephalitis and Prior Ovarian Teratoma Removal: Implications for Continued Monitoring and Treatment
Hong SB, et al. J Clin Neurol. 2021 Jan;17(1):131-133. https://doi.org/10.3988/jcn.2021.17.1.131
- 1 January 2021
- Published by Korean Neurological Association in Journal of Clinical Neurology
- Vol. 17 (1) , 131-133
Open AccessOccult Growing Teratoma as the Cause of Protracted Symptoms in a Patient with Anti-NMDA-Receptor Encephalitis and Prior Ovarian Teratoma Removal: Implications for Continued Monitoring and Treatment
Hong SB, et al. J Clin Neurol. 2021 Jan;17(1):131-133. https://doi.org/10.3988/jcn.2021.17.1.131