1.Development of Child-Teen Obesity Treatment Service Platform.
Kahyun LIM ; Byung Mun LEE ; Youngho LEE
Healthcare Informatics Research 2016;22(3):243-249
OBJECTIVES: This study aimed to develop an effective and efficient obesity treatment and management service platform for obese children/teenagers. METHODS: The integrated smart platform was planned and established through cooperation with service providers such as hospitals and public health centers, obese children/teenagers who constitute the service's user base, and IT development and policy institutions and companies focusing on child-teen obesity management and treatment. RESULTS: Based on guidelines on intervention strategies to manage child-teen obesity, we developed two patient/parent mobile applications, one web-monitoring service for medical staff, one mobile application for food-craving endurance, and one mobile application for medical examinations. CONCLUSIONS: The establishment of the integrated service platform was successfully completed; however, this study was restrictively to the hospital where the pilot program took place. The effectiveness of the proposed platform will be verified in the future in tests involving other organizations.
Delivery of Health Care
;
Humans
;
Medical Staff
;
Mobile Applications
;
Obesity*
;
Pediatric Obesity
;
Public Health
;
User-Computer Interface
2.Data-Mining-Based Coronary Heart Disease Risk Prediction Model Using Fuzzy Logic and Decision Tree.
Jaekwon KIM ; Jongsik LEE ; Youngho LEE
Healthcare Informatics Research 2015;21(3):167-174
OBJECTIVES: The importance of the prediction of coronary heart disease (CHD) has been recognized in Korea; however, few studies have been conducted in this area. Therefore, it is necessary to develop a method for the prediction and classification of CHD in Koreans. METHODS: A model for CHD prediction must be designed according to rule-based guidelines. In this study, a fuzzy logic and decision tree (classification and regression tree [CART])-driven CHD prediction model was developed for Koreans. Datasets derived from the Korean National Health and Nutrition Examination Survey VI (KNHANES-VI) were utilized to generate the proposed model. RESULTS: The rules were generated using a decision tree technique, and fuzzy logic was applied to overcome problems associated with uncertainty in CHD prediction. CONCLUSIONS: The accuracy and receiver operating characteristic (ROC) curve values of the propose systems were 69.51% and 0.594, proving that the proposed methods were more efficient than other models.
Classification
;
Coronary Disease*
;
Data Mining
;
Dataset
;
Decision Trees*
;
Fuzzy Logic*
;
Heart Diseases
;
Korea
;
Nutrition Surveys
;
ROC Curve
;
Uncertainty
3.Korean Anaphora Recognition System to Develop Healthcare Dialogue-Type Agent.
Healthcare Informatics Research 2014;20(4):272-279
OBJECTIVES: Anaphora recognition is a process to identify exactly which noun has been used previously and relates to a pronoun that is included in a specific sentence later. Therefore, anaphora recognition is an essential element of a dialogue agent system. In the current study, all the merits of rule-based, machine learning-based, semantic-based anaphora recognition systems were combined to design and realize a new hybrid-type anaphora recognition system with an optimum capacity. METHODS: Anaphora recognition rules were encoded on the basis of the internal traits of referred expressions and adjacent contexts to realize a rule-based system and to serve as a baseline. A semantic database, related to predicate instances of sentences including referred expressions, was constructed to identify semantic co-relationships between the referent candidates (to which semantic tags were attached) and the semantic information of predicates. This approach would upgrade the anaphora recognition system by reducing the number of referent candidates. Additionally, to realize a machine learning-based system, an anaphora recognition model was developed on the basis of training data, which indicated referred expressions and referents. The three methods were further combined to develop a new single hybrid-based anaphora recognition system. RESULTS: The precision rate of the rule-based systems was 54.9%. However, the precision rate of the hybrid-based system was 63.7%, proving it to be the most efficient method. CONCLUSIONS: The hybrid-based method, developed by the combination of rule-based and machine learning-based methods, represents a new system with enhanced functional capabilities as compared to other pre-existing individual methods.
Delivery of Health Care*
;
Natural Language Processing
;
Semantics
4.Posttraumatic Aortic Regurgitation: Two Cases.
Bum Ju KIM ; Ji Hun KANG ; Youngho JIN ; Jae Baek LEE
Journal of the Korean Society of Emergency Medicine 2000;11(3):406-410
No abstract available.
Aortic Valve Insufficiency*
5.Statistics and Deep Belief Network-Based Cardiovascular Risk Prediction.
Jaekwon KIM ; Ungu KANG ; Youngho LEE
Healthcare Informatics Research 2017;23(3):169-175
OBJECTIVES: Cardiovascular predictions are related to patients' quality of life and health. Therefore, a risk prediction model for cardiovascular conditions is needed. METHODS: In this paper, we propose a cardiovascular disease prediction model using the sixth Korea National Health and Nutrition Examination Survey (KNHANES-VI) 2013 dataset to analyze cardiovascular-related health data. First, statistical analysis was performed to find variables related to cardiovascular disease using health data related to cardiovascular disease. Second, a model of cardiovascular risk prediction by learning based on the deep belief network (DBN) was developed. RESULTS: The proposed statistical DBN-based prediction model showed accuracy and an ROC curve of 83.9% and 0.790, respectively. Thus, the proposed statistical DBN performed better than other prediction algorithms. CONCLUSIONS: The DBN proposed in this study appears to be effective in predicting cardiovascular risk and, in particular, is expected to be applicable to the prediction of cardiovascular disease in Koreans.
Cardiovascular Diseases
;
Dataset
;
Korea
;
Learning
;
Machine Learning
;
Nutrition Surveys
;
Quality of Life
;
ROC Curve
6.Postpartum Transmission as a Major Route of Mother-to-Child Helicobacter felis Infection.
Sunhwa HONG ; Hyun A LEE ; Youngho KIM ; Okjin KIM
Laboratory Animal Research 2010;26(3):319-321
In this study we investigated maternal Helicobacter felis (H. felis) infection status to determine the potential of maternal transmission. Pregnant Beagle dogs were infected experimentally with H. felis. Following the experimental design, the stools of the mother and litters were isolated and assessed for transmission of H. felis at parturition day, 1-week old age and 6-week old age respectively. Polymerase chain reaction (PCR) was used to examine the presence of transmitted H. felis. All litters showed no transmission of H. felis at parturition day. However, they revealed 14.3% and 100% at 1-week old age and 6-week old age respectively by PCR. These results suggested that vertical infection during prenatal period or delivery procedure is unlikely as a route of mother-to-child H. felis infection. It might be acquired H. felis through breast-feeding, contaminating saliva and fecal-oral during co-habitat.
Animals
;
Cats
;
Dogs
;
Felis
;
Helicobacter
;
Helicobacter felis
;
Humans
;
Mothers
;
Parturition
;
Polymerase Chain Reaction
;
Postpartum Period
;
Research Design
;
Saliva
7.Postpartum Transmission as a Major Route of Mother-to-Child Helicobacter felis Infection.
Sunhwa HONG ; Hyun A LEE ; Youngho KIM ; Okjin KIM
Laboratory Animal Research 2010;26(3):319-321
In this study we investigated maternal Helicobacter felis (H. felis) infection status to determine the potential of maternal transmission. Pregnant Beagle dogs were infected experimentally with H. felis. Following the experimental design, the stools of the mother and litters were isolated and assessed for transmission of H. felis at parturition day, 1-week old age and 6-week old age respectively. Polymerase chain reaction (PCR) was used to examine the presence of transmitted H. felis. All litters showed no transmission of H. felis at parturition day. However, they revealed 14.3% and 100% at 1-week old age and 6-week old age respectively by PCR. These results suggested that vertical infection during prenatal period or delivery procedure is unlikely as a route of mother-to-child H. felis infection. It might be acquired H. felis through breast-feeding, contaminating saliva and fecal-oral during co-habitat.
Animals
;
Cats
;
Dogs
;
Felis
;
Helicobacter
;
Helicobacter felis
;
Humans
;
Mothers
;
Parturition
;
Polymerase Chain Reaction
;
Postpartum Period
;
Research Design
;
Saliva
8.Stacking Ensemble Technique for Classifying Breast Cancer
Hyunjin KWON ; Jinhyeok PARK ; Youngho LEE
Healthcare Informatics Research 2019;25(4):283-288
OBJECTIVES: Breast cancer is the second most common cancer among Korean women. Because breast cancer is strongly associated with negative emotional and physical changes, early detection and treatment of breast cancer are very important. As a supporting tool for classifying breast cancer, we tried to identify the best meta-learner model in a stacking ensemble when the same machine learning models for the base learner and meta-learner are used. METHODS: We used machine learning models, such as the gradient boosted model, distributed random forest, generalized linear model, and deep neural network in a stacking ensemble. These models were used to construct a base learner, and each of them was used as a meta-learner again. Then, we compared the performance of machine learning models in the meta-learner to determine the best meta-learner model in the stacking ensemble. RESULTS: Experimental results showed that using the GBM as a meta-learner led to higher accuracy than that achieved with any other model for breast cancer data and using the GLM as a meta learner led to low root-mean-squared error for both sets of breast cancer data. CONCLUSIONS: We compared the performance of every meta-learner model in a stacking ensemble as a supporting tool for classifying breast cancer. The study showed that using specific models as a metalearner resulted in better performance than single classifiers, and using GBM and GLM as a meta-learner is appropriate as a supporting tool for classifying breast cancer data.
Breast Neoplasms
;
Breast
;
Classification
;
Female
;
Forests
;
Humans
;
Linear Models
;
Machine Learning
;
Medical Informatics
;
Statistics as Topic
9.Gambling Disorder Symptoms, Suicidal Ideation, and Suicide Attempts
Kounseok LEE ; Hyesun KIM ; YoungHo KIM
Psychiatry Investigation 2021;18(1):88-93
Objective:
Gambling disorder (GD) patients have a higher suicide risk compared to the general population. The present study investigates the suicide-related risk factors of GD patients by analyzing GD diagnosis-related symptoms and suicide-related behaviors of subjects.
Methods:
This study investigated which symptoms among GD diagnosis criteria are related to suicide risk in 142 patients diagnosed with GD. To analyze the relationship between GD symptoms and suicidal ideation and suicide attempt, the odds ratio (OR) was determined through multivariate logistic regression.
Results:
The number of symptoms was significantly higher in the subjects who had suicidal ideation group and attempt group. In the cases of past suicide attempts, responses to withdrawal and escape questions were significantly higher; in the cases of ongoing suicidal ideation, responses to negative consequences and bailout questions were significantly higher. When depression was corrected, the ‘bailout’ item was, indicating that ‘bailout’ increased suicidal ideation (OR=4.937, 95% CI=1.009–24.164). In the suicide attempt group, ‘relieve’ item may increase suicide attempt (OR=6.978, 95% CI=1.300–35.562).
Conclusion
Past suicide attempts in GD patients correlated with withdrawal symptoms, and financial problem correlated with suicidal ideation. This suggests that evaluating suicide risk is important when evaluating GD patients, and evaluation of financial problems is important for GD patients with suicide risks.
10.Protected Health Information Recognition by Fine-Tuning a Pre-training Transformer Model
Seo Hyun OH ; Min KANG ; Youngho LEE
Healthcare Informatics Research 2022;28(1):16-24
Objectives:
De-identifying protected health information (PHI) in medical documents is important, and a prerequisite to deidentification is the identification of PHI entity names in clinical documents. This study aimed to compare the performance of three pre-training models that have recently attracted significant attention and to determine which model is more suitable for PHI recognition.
Methods:
We compared the PHI recognition performance of deep learning models using the i2b2 2014 dataset. We used the three pre-training models—namely, bidirectional encoder representations from transformers (BERT), robustly optimized BERT pre-training approach (RoBERTa), and XLNet (model built based on Transformer-XL)—to detect PHI. After the dataset was tokenized, it was processed using an inside-outside-beginning tagging scheme and WordPiecetokenized to place it into these models. Further, the PHI recognition performance was investigated using BERT, RoBERTa, and XLNet.
Results:
Comparing the PHI recognition performance of the three models, it was confirmed that XLNet had a superior F1-score of 96.29%. In addition, when checking PHI entity performance evaluation, RoBERTa and XLNet showed a 30% improvement in performance compared to BERT.
Conclusions
Among the pre-training models used in this study, XLNet exhibited superior performance because word embedding was well constructed using the two-stream self-attention method. In addition, compared to BERT, RoBERTa and XLNet showed superior performance, indicating that they were more effective in grasping the context.