1.Machine Learning Prediction of Attachment Type From Bio-Psychological Factors in Patients With Depression
Yoon Jae CHO ; Jin Sun RYU ; Jeong-Ho SEOK ; Eunjoo KIM ; Jooyoung OH ; Byung-Hoon KIM
Psychiatry Investigation 2025;22(4):412-423
Objective:
Adult attachment style is linked to how an individual responds to threats or stress and is known to be related to the onset of psychiatric symptoms such as depression. However, as the current assessment of attachment type mainly relies on self-report questionnaires and can be prone to bias, there is a need to incorporate physiological factors along with psychological symptoms and history in this process. We aimed to predict the measurement of two important types of adult attachment with heart rate variability (HRV), early life stress experience, and subjective psychiatric symptoms.
Methods:
Five hundred eighty-two subjects with depressive disorder were recruited retrospectively from January 2015 to June 2021. The experience of early life stress and psychiatric symptoms were collected, and HRV measures were obtained as input for an ensembled Voting Regressor model of machine learning-based regression models, including linear regression, ElasticNet, Support Vector Machine (SVM), Random Forest, and Extreme Gradient Boosting (XGBoost).
Results:
Model performances evaluated with R-squared score averaged across 30 seeds were 0.377 and 0.188 for anxious- and avoidant-attachment, respectively. Mean absolute error averaged to 13.251 and 12.083, respectively. Shapley value importance analysis indicated that for both attachment types, the most important feature was the trait-anxiety, followed by emotional abuse, state-anxiety or self-reported depressive symptoms, and fear or helplessness felt in the moment of an early life stressor.
Conclusion
Our results provide the evidence base that may be utilized in clinical settings to predict the degree of attachment type using bio-psychological factors.
2.Prevalence and characteristics of impacted teeth in Korean orthodontic patients at ten university dental hospitals
Youn-Kyung CHOI ; Sung-Hun KIM ; Yong-Il KIM ; Seong-Sik KIM ; Soo-Byung PARK ; Dong-Soon CHOI ; Ho-Jin KIM ; Kyung-A KIM ; Mo-Hyeon LEE ; Sung-Hwan CHOI ; Sung-Kwon CHOI ; Kyungmin Clara LEE ; Young-Mi JEON ; Sewoong OH ; Seorin JEONG
The Korean Journal of Orthodontics 2025;55(3):234-241
Objective:
This study aimed to investigate the prevalence and characteristics of impacted teeth (ITs) in orthodontic patients at university dental hospitals in Korea.
Methods:
This study included 14,774 patients who visited the Department of Orthodontics at 10 university dental hospitals in Korea between 2020 and 2022 and underwent orthodontic diagnosis. The prevalence and characteristics of ITs were investigated using orthodontic diagnostic records, radiographs, and diagnostic casts.
Results:
The prevalence of ITs, excluding third molar impaction, in Korean orthodontic patients was 13.6% (n = 2,014).The prevalence of ITs in pediatric orthodontic patients was 24.5% (n = 1,614).Of these patients, 68.2% had one IT, 27.5% had two ITs, 24.3% had bilateral IT, and 75.7% had unilateral IT. The most frequent IT was the maxillary canine (50.1%), followed by the mandibular second molar (11.7%), and maxillary second premolar (9.6%). An abnormal eruption path (46.5%) was the most frequent etiology. Orthodontic traction after surgical exposure (70.6%) was the most frequent treatment option. Among the patients with ITs, 29.8% had other dental anomalies, such as tooth agenesis (8.7%), microdontia (8.0%), and supernumerary teeth (5.1%). Furthermore, 50.8% had complications such as cystic lesions (18.3%), transposition (17.7%), and root resorption (14.8%).Among the patients with maxillary canine impaction, 62.2% had labial maxillary canine impaction and 21.1% had palatal maxillary canine impaction.
Conclusions
The prevalence of ITs in Korean orthodontic patients at university dental hospitals was high, particularly in pediatric orthodontic patients.
3.Machine Learning Prediction of Attachment Type From Bio-Psychological Factors in Patients With Depression
Yoon Jae CHO ; Jin Sun RYU ; Jeong-Ho SEOK ; Eunjoo KIM ; Jooyoung OH ; Byung-Hoon KIM
Psychiatry Investigation 2025;22(4):412-423
Objective:
Adult attachment style is linked to how an individual responds to threats or stress and is known to be related to the onset of psychiatric symptoms such as depression. However, as the current assessment of attachment type mainly relies on self-report questionnaires and can be prone to bias, there is a need to incorporate physiological factors along with psychological symptoms and history in this process. We aimed to predict the measurement of two important types of adult attachment with heart rate variability (HRV), early life stress experience, and subjective psychiatric symptoms.
Methods:
Five hundred eighty-two subjects with depressive disorder were recruited retrospectively from January 2015 to June 2021. The experience of early life stress and psychiatric symptoms were collected, and HRV measures were obtained as input for an ensembled Voting Regressor model of machine learning-based regression models, including linear regression, ElasticNet, Support Vector Machine (SVM), Random Forest, and Extreme Gradient Boosting (XGBoost).
Results:
Model performances evaluated with R-squared score averaged across 30 seeds were 0.377 and 0.188 for anxious- and avoidant-attachment, respectively. Mean absolute error averaged to 13.251 and 12.083, respectively. Shapley value importance analysis indicated that for both attachment types, the most important feature was the trait-anxiety, followed by emotional abuse, state-anxiety or self-reported depressive symptoms, and fear or helplessness felt in the moment of an early life stressor.
Conclusion
Our results provide the evidence base that may be utilized in clinical settings to predict the degree of attachment type using bio-psychological factors.
4.Prevalence and characteristics of impacted teeth in Korean orthodontic patients at ten university dental hospitals
Youn-Kyung CHOI ; Sung-Hun KIM ; Yong-Il KIM ; Seong-Sik KIM ; Soo-Byung PARK ; Dong-Soon CHOI ; Ho-Jin KIM ; Kyung-A KIM ; Mo-Hyeon LEE ; Sung-Hwan CHOI ; Sung-Kwon CHOI ; Kyungmin Clara LEE ; Young-Mi JEON ; Sewoong OH ; Seorin JEONG
The Korean Journal of Orthodontics 2025;55(3):234-241
Objective:
This study aimed to investigate the prevalence and characteristics of impacted teeth (ITs) in orthodontic patients at university dental hospitals in Korea.
Methods:
This study included 14,774 patients who visited the Department of Orthodontics at 10 university dental hospitals in Korea between 2020 and 2022 and underwent orthodontic diagnosis. The prevalence and characteristics of ITs were investigated using orthodontic diagnostic records, radiographs, and diagnostic casts.
Results:
The prevalence of ITs, excluding third molar impaction, in Korean orthodontic patients was 13.6% (n = 2,014).The prevalence of ITs in pediatric orthodontic patients was 24.5% (n = 1,614).Of these patients, 68.2% had one IT, 27.5% had two ITs, 24.3% had bilateral IT, and 75.7% had unilateral IT. The most frequent IT was the maxillary canine (50.1%), followed by the mandibular second molar (11.7%), and maxillary second premolar (9.6%). An abnormal eruption path (46.5%) was the most frequent etiology. Orthodontic traction after surgical exposure (70.6%) was the most frequent treatment option. Among the patients with ITs, 29.8% had other dental anomalies, such as tooth agenesis (8.7%), microdontia (8.0%), and supernumerary teeth (5.1%). Furthermore, 50.8% had complications such as cystic lesions (18.3%), transposition (17.7%), and root resorption (14.8%).Among the patients with maxillary canine impaction, 62.2% had labial maxillary canine impaction and 21.1% had palatal maxillary canine impaction.
Conclusions
The prevalence of ITs in Korean orthodontic patients at university dental hospitals was high, particularly in pediatric orthodontic patients.
5.Machine Learning Prediction of Attachment Type From Bio-Psychological Factors in Patients With Depression
Yoon Jae CHO ; Jin Sun RYU ; Jeong-Ho SEOK ; Eunjoo KIM ; Jooyoung OH ; Byung-Hoon KIM
Psychiatry Investigation 2025;22(4):412-423
Objective:
Adult attachment style is linked to how an individual responds to threats or stress and is known to be related to the onset of psychiatric symptoms such as depression. However, as the current assessment of attachment type mainly relies on self-report questionnaires and can be prone to bias, there is a need to incorporate physiological factors along with psychological symptoms and history in this process. We aimed to predict the measurement of two important types of adult attachment with heart rate variability (HRV), early life stress experience, and subjective psychiatric symptoms.
Methods:
Five hundred eighty-two subjects with depressive disorder were recruited retrospectively from January 2015 to June 2021. The experience of early life stress and psychiatric symptoms were collected, and HRV measures were obtained as input for an ensembled Voting Regressor model of machine learning-based regression models, including linear regression, ElasticNet, Support Vector Machine (SVM), Random Forest, and Extreme Gradient Boosting (XGBoost).
Results:
Model performances evaluated with R-squared score averaged across 30 seeds were 0.377 and 0.188 for anxious- and avoidant-attachment, respectively. Mean absolute error averaged to 13.251 and 12.083, respectively. Shapley value importance analysis indicated that for both attachment types, the most important feature was the trait-anxiety, followed by emotional abuse, state-anxiety or self-reported depressive symptoms, and fear or helplessness felt in the moment of an early life stressor.
Conclusion
Our results provide the evidence base that may be utilized in clinical settings to predict the degree of attachment type using bio-psychological factors.
6.Prevalence and characteristics of impacted teeth in Korean orthodontic patients at ten university dental hospitals
Youn-Kyung CHOI ; Sung-Hun KIM ; Yong-Il KIM ; Seong-Sik KIM ; Soo-Byung PARK ; Dong-Soon CHOI ; Ho-Jin KIM ; Kyung-A KIM ; Mo-Hyeon LEE ; Sung-Hwan CHOI ; Sung-Kwon CHOI ; Kyungmin Clara LEE ; Young-Mi JEON ; Sewoong OH ; Seorin JEONG
The Korean Journal of Orthodontics 2025;55(3):234-241
Objective:
This study aimed to investigate the prevalence and characteristics of impacted teeth (ITs) in orthodontic patients at university dental hospitals in Korea.
Methods:
This study included 14,774 patients who visited the Department of Orthodontics at 10 university dental hospitals in Korea between 2020 and 2022 and underwent orthodontic diagnosis. The prevalence and characteristics of ITs were investigated using orthodontic diagnostic records, radiographs, and diagnostic casts.
Results:
The prevalence of ITs, excluding third molar impaction, in Korean orthodontic patients was 13.6% (n = 2,014).The prevalence of ITs in pediatric orthodontic patients was 24.5% (n = 1,614).Of these patients, 68.2% had one IT, 27.5% had two ITs, 24.3% had bilateral IT, and 75.7% had unilateral IT. The most frequent IT was the maxillary canine (50.1%), followed by the mandibular second molar (11.7%), and maxillary second premolar (9.6%). An abnormal eruption path (46.5%) was the most frequent etiology. Orthodontic traction after surgical exposure (70.6%) was the most frequent treatment option. Among the patients with ITs, 29.8% had other dental anomalies, such as tooth agenesis (8.7%), microdontia (8.0%), and supernumerary teeth (5.1%). Furthermore, 50.8% had complications such as cystic lesions (18.3%), transposition (17.7%), and root resorption (14.8%).Among the patients with maxillary canine impaction, 62.2% had labial maxillary canine impaction and 21.1% had palatal maxillary canine impaction.
Conclusions
The prevalence of ITs in Korean orthodontic patients at university dental hospitals was high, particularly in pediatric orthodontic patients.
7.Pain Lateralization in Cluster Headache and Associated Clinical Factors
Soohyun CHO ; Mi Ji LEE ; Min Kyung CHU ; Jeong Wook PARK ; Heui-Soo MOON ; Pil-Wook CHUNG ; Jong-Hee SOHN ; Byung-Su KIM ; Daeyoung KIM ; Kyungmi OH ; Byung-Kun KIM ; Soo-Jin CHO
Journal of Clinical Neurology 2025;21(3):220-229
Background:
and Purpose The pain lateralization in cluster headache (CH) may be related to the asymmetry in the functions of the brain hemispheres. The right-sided dominance of pain in CH has been found inconsistently across studies, and so we aimed to characterize this and identify the factors influencing pain lateralization during current and previous bouts.
Methods:
This study enrolled 227 patients from the Korean Cluster Headache Registry between October 2018 and December 2020. We evaluated the side of pain during current and previous bouts, demographic features, and clinical characteristics, including handedness. Multivariable logistic regression analyses were performed to identify factors associated with the side of pain.
Results:
The 227 patients with CH included 131 (57.7%) with right-sided pain and 86 (37.9%) with left-sided pain during the current bout (p<0.001). The 189 patients with previous bouts of CH included 86.8% who consistently reported the same side of pain throughout multiple bouts (side-locked pain), with a higher prevalence of pain on the right than the left side (55.0% vs. 31.7%, p<0.001). Multivariable analyses revealed that higher age at diagnosis (odds ratio [OR]=1.045, p=0.031) and shorter CH attacks (OR=0.992, p=0.017) were associated with left-side-locked pain. However, handedness was not associated with the lateralization of leftside-locked pain.
Conclusions
This study has confirmed the predominance of right-sided pain throughout multiple CH bouts. We found that higher age at diagnosis and shorter CH attacks were associated with left-side-locked pain, suggesting that certain clinical factors are associated with the pain laterality. However, the underlying mechanisms linking these factors to lateralized pain remain unclear and therefore require further investigation.
8.Pain Lateralization in Cluster Headache and Associated Clinical Factors
Soohyun CHO ; Mi Ji LEE ; Min Kyung CHU ; Jeong Wook PARK ; Heui-Soo MOON ; Pil-Wook CHUNG ; Jong-Hee SOHN ; Byung-Su KIM ; Daeyoung KIM ; Kyungmi OH ; Byung-Kun KIM ; Soo-Jin CHO
Journal of Clinical Neurology 2025;21(3):220-229
Background:
and Purpose The pain lateralization in cluster headache (CH) may be related to the asymmetry in the functions of the brain hemispheres. The right-sided dominance of pain in CH has been found inconsistently across studies, and so we aimed to characterize this and identify the factors influencing pain lateralization during current and previous bouts.
Methods:
This study enrolled 227 patients from the Korean Cluster Headache Registry between October 2018 and December 2020. We evaluated the side of pain during current and previous bouts, demographic features, and clinical characteristics, including handedness. Multivariable logistic regression analyses were performed to identify factors associated with the side of pain.
Results:
The 227 patients with CH included 131 (57.7%) with right-sided pain and 86 (37.9%) with left-sided pain during the current bout (p<0.001). The 189 patients with previous bouts of CH included 86.8% who consistently reported the same side of pain throughout multiple bouts (side-locked pain), with a higher prevalence of pain on the right than the left side (55.0% vs. 31.7%, p<0.001). Multivariable analyses revealed that higher age at diagnosis (odds ratio [OR]=1.045, p=0.031) and shorter CH attacks (OR=0.992, p=0.017) were associated with left-side-locked pain. However, handedness was not associated with the lateralization of leftside-locked pain.
Conclusions
This study has confirmed the predominance of right-sided pain throughout multiple CH bouts. We found that higher age at diagnosis and shorter CH attacks were associated with left-side-locked pain, suggesting that certain clinical factors are associated with the pain laterality. However, the underlying mechanisms linking these factors to lateralized pain remain unclear and therefore require further investigation.
9.Machine Learning Prediction of Attachment Type From Bio-Psychological Factors in Patients With Depression
Yoon Jae CHO ; Jin Sun RYU ; Jeong-Ho SEOK ; Eunjoo KIM ; Jooyoung OH ; Byung-Hoon KIM
Psychiatry Investigation 2025;22(4):412-423
Objective:
Adult attachment style is linked to how an individual responds to threats or stress and is known to be related to the onset of psychiatric symptoms such as depression. However, as the current assessment of attachment type mainly relies on self-report questionnaires and can be prone to bias, there is a need to incorporate physiological factors along with psychological symptoms and history in this process. We aimed to predict the measurement of two important types of adult attachment with heart rate variability (HRV), early life stress experience, and subjective psychiatric symptoms.
Methods:
Five hundred eighty-two subjects with depressive disorder were recruited retrospectively from January 2015 to June 2021. The experience of early life stress and psychiatric symptoms were collected, and HRV measures were obtained as input for an ensembled Voting Regressor model of machine learning-based regression models, including linear regression, ElasticNet, Support Vector Machine (SVM), Random Forest, and Extreme Gradient Boosting (XGBoost).
Results:
Model performances evaluated with R-squared score averaged across 30 seeds were 0.377 and 0.188 for anxious- and avoidant-attachment, respectively. Mean absolute error averaged to 13.251 and 12.083, respectively. Shapley value importance analysis indicated that for both attachment types, the most important feature was the trait-anxiety, followed by emotional abuse, state-anxiety or self-reported depressive symptoms, and fear or helplessness felt in the moment of an early life stressor.
Conclusion
Our results provide the evidence base that may be utilized in clinical settings to predict the degree of attachment type using bio-psychological factors.
10.Prevalence and characteristics of impacted teeth in Korean orthodontic patients at ten university dental hospitals
Youn-Kyung CHOI ; Sung-Hun KIM ; Yong-Il KIM ; Seong-Sik KIM ; Soo-Byung PARK ; Dong-Soon CHOI ; Ho-Jin KIM ; Kyung-A KIM ; Mo-Hyeon LEE ; Sung-Hwan CHOI ; Sung-Kwon CHOI ; Kyungmin Clara LEE ; Young-Mi JEON ; Sewoong OH ; Seorin JEONG
The Korean Journal of Orthodontics 2025;55(3):234-241
Objective:
This study aimed to investigate the prevalence and characteristics of impacted teeth (ITs) in orthodontic patients at university dental hospitals in Korea.
Methods:
This study included 14,774 patients who visited the Department of Orthodontics at 10 university dental hospitals in Korea between 2020 and 2022 and underwent orthodontic diagnosis. The prevalence and characteristics of ITs were investigated using orthodontic diagnostic records, radiographs, and diagnostic casts.
Results:
The prevalence of ITs, excluding third molar impaction, in Korean orthodontic patients was 13.6% (n = 2,014).The prevalence of ITs in pediatric orthodontic patients was 24.5% (n = 1,614).Of these patients, 68.2% had one IT, 27.5% had two ITs, 24.3% had bilateral IT, and 75.7% had unilateral IT. The most frequent IT was the maxillary canine (50.1%), followed by the mandibular second molar (11.7%), and maxillary second premolar (9.6%). An abnormal eruption path (46.5%) was the most frequent etiology. Orthodontic traction after surgical exposure (70.6%) was the most frequent treatment option. Among the patients with ITs, 29.8% had other dental anomalies, such as tooth agenesis (8.7%), microdontia (8.0%), and supernumerary teeth (5.1%). Furthermore, 50.8% had complications such as cystic lesions (18.3%), transposition (17.7%), and root resorption (14.8%).Among the patients with maxillary canine impaction, 62.2% had labial maxillary canine impaction and 21.1% had palatal maxillary canine impaction.
Conclusions
The prevalence of ITs in Korean orthodontic patients at university dental hospitals was high, particularly in pediatric orthodontic patients.

Result Analysis
Print
Save
E-mail