Kyungmin Na

Kyungmin Na

Auto-generated profile, based on publicly available information

Kyungmin Na

Gachon University

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 February 2025 in Journal of Health Informatics and Statistics
Verified
Journal Article
Open access
PDF file
KNKyungmin Na
Kyungmin Na
DKDohyoung Kim
Dohyoung Kim
YLYoungho Lee
Youngho Lee
Objectives: This study aims to compare the performance of federated learning (FL) and fair federated learning (FFL) in classifying pneumonia patients based on chest X-ray data. The primary focus is on assessing the accuracy and fairness of these models in handling imbalanced and distributed data in real-world healthcare settings.Methods: We used a large chest X-ray dataset to evaluate the performance of FL and FFL models. The models were built using the ResNet50 architecture, and experiments were conducted under both independent and identically distributed (IID) and non-IID data conditions. The FFL approach applied optimized loss functions to address data imbalance and ensure fair contribution from each client, regardless of the local data distribution.Results: Our findings indicate that FFL consistently outperforms traditional FL models, particularly in non-IID environments. The FFL model demonstrated higher accuracy in pneumonia classification, achieving a significant improvement in model fairness and performance across different client datasets. The use of the ResNet50 architecture further enhanced the model’s ability to handle complex X-ray image patterns.Conclusions: FFL offers a superior solution for handling imbalanced medical data compared to conventional FL models. Its ability to maintain fairness while improving classification accuracy makes it an ideal approach for decentralized healthcare systems, ensuring better patient outcomes while preserving data privacy.

13 November 2025 in JMIR Medical Informatics
Verified
Journal Article
Open access
NPNaYoung Park
NaYoung Park
KNKyungmin Na
Kyungmin Na
WSWoongsang Sunwoo
Woongsang Sunwoo
JBJeong-Heum Baek
Jeong-Heum Baek
YLYoungho Lee
Youngho Lee
HWHyekyung Woo
Hyekyung Woo
Background: As data-driven medical research advances, vast amounts of medical data are being collected, giving researchers access to important information. However, issues such as heterogeneity, complexity, and incompleteness of datasets limit their practical use. Errors and missing data negatively affect artificial intelligence–based predictive models, undermining the reliability of clinical decision-making. Thus, it is important to develop a quality management process (QMP) for clinical data. Objective: This study aimed to develop a rules-based QMP to address errors and impute missing values in real-world data, establishing high-quality data for clinical research. Methods: We used clinical data from 6491 patients with colorectal cancer (CRC) collected at Gachon University Gil Medical Center between 2010 and 2022, leveraging the clinical library established within the Korea Clinical Data Use Network for Research Excellence. First, we conducted a literature review on the prognostic prediction of CRC to assess whether the data met our research purposes, comparing selected variables with real-world data. A labeling process was then implemented to extract key variables, which facilitated the creation of an automatic staging library. This library, combined with a rule-based process, allowed for systematic analysis and evaluation. Results: Theoretically, the tumor, node, metastasis (TNM) stage was identified as an important prognostic factor for CRC, but it was not selected through feature selection in real-world data. After applying the QMP, rates of missing data were reduced from 75.3% to 35.7% for TNM and from 24.3% to 18.5% for surveillance, epidemiology, and end results across 6491 cases, confirming the system’s effectiveness. Variable importance analysis through feature selection revealed that TNM stage and detailed code variables, which were previously unselected, were included in the improved model. Conclusions: In sum, we developed a rules-based QMP to address errors and impute missing values in Korea Clinical Data Use Network for Research Excellence data, enhancing data quality. The applicability of the process to real-world datasets highlights its potential for broader use in clinical studies and cancer research.

13 March 2025 in JMIR Preprints
Verified
Preprint
Open access
NPNaYoung Park
NaYoung Park
KNKyungmin Na
Kyungmin Na
WSWoongsang Sunwoo
Woongsang Sunwoo
JBJeong-Heum Baek
Jeong-Heum Baek
YLYoungho Lee
Youngho Lee
HWHyekyung Woo
Hyekyung Woo
BACKGROUND As data-driven medical research advances, vast amounts of medical data are being collected, giving researchers access to important information. However, issues such as heterogeneity, complexity, and incompleteness of datasets limit their practical use. Errors and missing data negatively affect artificial intelligence (AI)-based predictive models, undermining the reliability of clinical decision-making. Thus, it is important to develop a quality management process (QMP) for clinical data. OBJECTIVE We aimed to develop a rules-based QMP to address errors and impute missing values in real-world data (RWD), establishing high-quality data for clinical research. METHODS We utilized clinical data from 6,491 colorectal cancer (CRC) patients collected at Gachon University Gil Medical Center between 2010 and 2022, leveraging the clinical library established within the Korea Clinical Data Use Network for Research Excellence (K-CURE). First, we conducted a literature review on the prognostic prediction of CRC to assess whether the data met our research purposes, comparing selected variables with RWD. Then a labeling process was implemented to extract key variables, which facilitated the creation of an automatic staging library. This library, combined with a rule-based process, allowed for systematic analysis and evaluation. RESULTS Theoretically, the tumor, node, metastasis (TNM) stage was identified as an important prognostic factor for CRC but it was not selected through feature selection in RWD. After applying the QMP, rates of missing data were reduced from 75.3% to 35.7% for TNM and from 24.3% to 18.5% for Surveillance, Epidemiology, and End Results (SEER) across 6,491 cases, confirming the system’s effectiveness. Variable importance analysis through feature selection revealed that TNM stage and detailed code variables, which were previously unselected, were included in the improved model. CONCLUSIONS In sum, we developed a rules-based QMP to address errors and impute missing values in K-CURE data, enhancing data quality. The applicability of the process to real-world datasets highlights its potential for broader use in clinical studies and cancer research. CLINICALTRIAL

21 January 2026 in Digital Health
Verified
Journal Article
Open access
SKSiyeon Ko
Siyeon Ko
경오경수 오
경수 오
UWUhyeong Won
Uhyeong Won
JOJung-A Oh
Jung-A Oh
NKNak-Jung Kwon
Nak-Jung Kwon
HWHyekyung Woo
Hyekyung Woo
Objective: Adolescence is a critical developmental stage during which mental health vulnerabilities often emerge. Traditional self-report methods are insufficient to capture the complexity of emotional and physiological responses, underscoring the need for data-driven, personalized mental health strategies. This study aimed to develop and validate a structured multimodal data collection system for adolescents to support the future advancement of precision mental health care. Methods: This study was conducted as the baseline phase of a longitudinal panel study designed to construct and validate a structured multimodal dataset for adolescent mental health research. A total of 74 adolescents aged 11–15 years from schools and community facilities in Korea was selected through convenience sampling. Multimodal data were collected by integrating six data types: self-reported surveys, electroencephalography (EEG), heart rate variability (HRV), genotyping, microbiome data, and video-based psychological counseling. Data collection was standardized through a three-phase protocol (pre-, on-site, and post-assessment), and participant privacy was protected via pseudonymization based on international standards. Variables were systematically labeled and structured to enable cross-modality analysis. Statistical analyses, including correlation and descriptive statistics, were performed to examine preliminary relationships across modalities. Results: The study successfully constructed a comprehensive dataset encompassing biological and psychosocial indicators from 74 adolescents. Preliminary analysis revealed statistically significant associations between survey-based BMI and both genomic data (ρ = 0.30, p < 0.01) and microbiome-based obesity indicators (ρ = 0.27, p < 0.05), whereas other psychological constructs (e.g., stress, resilience) showed non-significant cross-modal correlations. Conclusions: This study presents a replicable framework for collecting rich, multimodal data from adolescents in real-world settings. By enabling integrative analysis of biological and psychosocial variables, the dataset lays the groundwork for personalized mental health prediction and intervention strategies. Future research should expand longitudinally and optimize context alignment to improve predictive precision and clinical utility.