Kwangsoo Kim
YOU?
Author Swipe
View article: Multimodal Electronic Health Record Foundation Models with Electrocardiogram for Cardiovascular Disease Prediction
Multimodal Electronic Health Record Foundation Models with Electrocardiogram for Cardiovascular Disease Prediction Open
Electronic health record (EHR) foundation models (FMs) have improved clinical task performance by learning comprehensive clinical context from sequential medical records called patient trajectories. However, existing multimodal approaches …
View article: Corrigendum to “Identifying potential medical aid beneficiaries using machine learning: A Korean Nationwide cohort study” [Int. J. Med. Inform. 195 (2025) 105775]
Corrigendum to “Identifying potential medical aid beneficiaries using machine learning: A Korean Nationwide cohort study” [Int. J. Med. Inform. 195 (2025) 105775] Open
View article: Fracture risks in patients aged 50 years and older with panhypopituitarism: a nationwide cohort study
Fracture risks in patients aged 50 years and older with panhypopituitarism: a nationwide cohort study Open
View article: Pretrained patient trajectories for adverse drug event prediction using common data model-based electronic health records
Pretrained patient trajectories for adverse drug event prediction using common data model-based electronic health records Open
The CDM-based EHR pretraining model with DE can improve prediction performance for various ADEs and can provide proper explanation at cohort and patient level. Our model has the potential to serve as a foundation model due to its strong pr…
View article: Secondary Cancer Risk in Breast Cancer with and without Radiotherapy: The Observational Health Data Sciences and Informatics (OHDSI) Cohort Study
Secondary Cancer Risk in Breast Cancer with and without Radiotherapy: The Observational Health Data Sciences and Informatics (OHDSI) Cohort Study Open
There was no difference in the risk of secondary cancer in the patients diagnosed with breast cancer depending on whether or not radiotherapy was performed after surgery. In the future, it is necessary to analyze including data generated d…
View article: 155eP Treatment of cervical/vaginal intraepthelial neoplasia with high-dose rate brachytherapy: A multicenter retrospective analysis
155eP Treatment of cervical/vaginal intraepthelial neoplasia with high-dose rate brachytherapy: A multicenter retrospective analysis Open
View article: scTELL: A Single-Cell ATAC-seq Tool for Locus-Specific Transposable Element Identification in Chromatin Accessibility
scTELL: A Single-Cell ATAC-seq Tool for Locus-Specific Transposable Element Identification in Chromatin Accessibility Open
Transposable elements (TEs) are essential genomic entities that play the roles of eukaryotic genome regulators and are involved in controlling gene expression patterns, cell-type specialization, and diseases. Recent improvements of single-…
View article: Artificial Intelligence Models for Pediatric Lung Sound Analysis: Systematic Review and Meta-Analysis
Artificial Intelligence Models for Pediatric Lung Sound Analysis: Systematic Review and Meta-Analysis Open
Background Pediatric respiratory diseases, including asthma and pneumonia, are major causes of morbidity and mortality in children. Auscultation of lung sounds is a key diagnostic tool but is prone to subjective variability. The integratio…
View article: SNUH methylation classifier for CNS tumors
SNUH methylation classifier for CNS tumors Open
Background Methylation profiling of central nervous system (CNS) tumors, pioneered by the German Cancer Research Center, has significantly improved diagnostic accuracy. This study aimed to further enhance the performance of methylation cla…
View article: EpicPred: predicting phenotypes driven by epitope-binding TCRs using attention-based multiple instance learning
EpicPred: predicting phenotypes driven by epitope-binding TCRs using attention-based multiple instance learning Open
Motivation Correctly identifying epitope-binding T-cell receptors (TCRs) is important to both understand their underlying biological mechanism in association to some phenotype and accordingly develop T-cell mediated immunotherapy treatment…
View article: Postoperative mid-to-long-term adverse event prediction model for patients receiving non-cardiac surgery: An extension of the Simple Postoperative AKI RisK (SPARK) model
Postoperative mid-to-long-term adverse event prediction model for patients receiving non-cardiac surgery: An extension of the Simple Postoperative AKI RisK (SPARK) model Open
Background Postoperative acute kidney injury (PO-AKI) is a critical complication of adverse kidney outcomes, both short and long-term. We aimed to expand our pre-existing PO-AKI prediction model to predict mid-to long-term adverse kidney o…
View article: Sex-Specific Cardiovascular Risks and Mortality in Patients with Panhypopituitarism: A Nationwide Cohort Study
Sex-Specific Cardiovascular Risks and Mortality in Patients with Panhypopituitarism: A Nationwide Cohort Study Open
Background: Panhypopituitarism is a condition of combined deficiency of multiple pituitary hormones, which requires lifelong hormone replacement therapy. Hormone deficiency or inadequate hormone replacement may contribute to cardiovascular…
View article: Contrastive Learning for Omics-guided Whole-slide Visual Embedding Representation
Contrastive Learning for Omics-guided Whole-slide Visual Embedding Representation Open
While computational pathology has transformed cancer diagnosis and prognosis prediction, existing computational methods remain limited in their ability to decipher the complex molecular characteristics within tumors. We present CLOVER (Con…
View article: Development of Predictive Model of Surgical Case Durations Using Machine Learning Approach
Development of Predictive Model of Surgical Case Durations Using Machine Learning Approach Open
View article: scMILD: Single-cell Multiple Instance Learning for Sample Classification and Associated Subpopulation Discovery
scMILD: Single-cell Multiple Instance Learning for Sample Classification and Associated Subpopulation Discovery Open
SUMMARY Linking cellular states to clinical phenotypes is a major challenge in single-cell analysis. Here, we present scMILD, a weakly supervised Multiple Instance Learning framework that robustly identifies condition-associated cells usin…
View article: Development of a Visualization Dashboard for Medication Prescriptions Using Diagnostic and Prescription Data From Seoul National University Hospital
Development of a Visualization Dashboard for Medication Prescriptions Using Diagnostic and Prescription Data From Seoul National University Hospital Open
View article: scMILD: Single-Cell Multiple Instance Learning for Sample Classification and Associated Subpopulation Discovery
scMILD: Single-Cell Multiple Instance Learning for Sample Classification and Associated Subpopulation Discovery Open
View article: Prediction of reduced left ventricular ejection fraction using atrial fibrillation or flutter electrocardiograms: A machine-learning study
Prediction of reduced left ventricular ejection fraction using atrial fibrillation or flutter electrocardiograms: A machine-learning study Open
Objective Although the evaluation of left ventricular ejection fraction (LVEF) in patients with atrial fibrillation (AF) or atrial flutter (AFL) is crucial for appropriate medical management, the prediction of reduced LVEF (<50%) with AF/A…
View article: Supplementary Table S9 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression
Supplementary Table S9 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression Open
The most up- or downregulated gene sets in tumor cells between IF_PDL1H and ID_PDL1H
View article: Data from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression
Data from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression Open
The expression of PD-L1 on tumor cells (TC) is used as an immunotherapy biomarker in lung cancer, but heterogeneous intratumoral expression is often observed. To better understand heterogeneity in the lung cancer tumor microenvironment, we…
View article: Supplementary Tables S3 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression
Supplementary Tables S3 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression Open
Characteristics of patients with lung cancer treated with immune checkpoint inhibitor (immunohistochemistry cohort)
View article: Supplementary Figure S3 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression
Supplementary Figure S3 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression Open
The characteristics of immune cells according to tumor PD-L1 expression in immune deficient tumor microenvironment.
View article: Supplementary Table S7 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression
Supplementary Table S7 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression Open
The most up- or downregulated gene sets in immune cells between IF_PDL1H and IF_PDL1L
View article: Supplementary Figure S6 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression
Supplementary Figure S6 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression Open
Survival analysis according to subtype of NSCLC in ICI cohort
View article: Supplementary Tables S4 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression
Supplementary Tables S4 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression Open
List of protein molecules identified using nCounter analysis
View article: Supplementary Figure S2 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression
Supplementary Figure S2 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression Open
Principal Component Analysis (PCA) and the distribution of tumor PD-L1 expression in total or per group using DSP analysis.
View article: Supplementary Table 8S from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression
Supplementary Table 8S from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression Open
The most up- or downregulated gene sets in immune cells between ID_PDL1H and ID_PDL1L
View article: Supplementary Table S6 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression
Supplementary Table S6 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression Open
Publicly available data source and analysis
View article: Supplementary Table S5 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression
Supplementary Table S5 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression Open
List of genes in various T cell status signatures
View article: Supplementary Table S13 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression
Supplementary Table S13 from Spatially Resolved Whole-Transcriptomic and Proteomic Profiling of Lung Cancer and Its Immune Microenvironment According to PD-L1 Expression Open
The most up- or downregulated gene sets in tumor cells between IF_PDL1L and ID_PDL1H