Young‐Hak Kim
YOU?
Author Swipe
View article: Optimal time for collateral channel wiring in retrograde chronic total occlusion percutaneous coronary intervention
Optimal time for collateral channel wiring in retrograde chronic total occlusion percutaneous coronary intervention Open
Collateral channel wiring (CCW) is important in a retrograde chronic total occlusion (CTO) procedure. However, the guidance is insufficient. To investigate the optimal CCW time, patients who had received retrograde CTO procedures were enro…
View article: Leveraging BERT for embedding ICD codes from large scale cardiovascular EMR data to understand patient diagnostic patterns
Leveraging BERT for embedding ICD codes from large scale cardiovascular EMR data to understand patient diagnostic patterns Open
The integration of electronic medical records (EMRs) with artificial intelligence (AI) is enhancing medical research, particularly in real-world evidence (RWE) studies. Extracting insights from coded medical data, such as ICD-10 codes, is …
Large Language Models for Automating Clinical Trial Criteria Conversion to Observational Medical Outcomes Partnership Common Data Model Queries: Validation and Evaluation Study Open
Background Real-world data–based feasibility assessments enhance clinical trial design, but automating eligibility criteria conversion to database queries is hindered by challenges related to ensuring high accuracy and generating clear, us…
Clinical Assessment of Fine-Tuned Open-Source LLMs in Cardiology: From Progress Notes to Discharge Summary Open
The generation of accurate discharge summaries from clinical progress notes represents a critical challenge in healthcare documentation, particularly in specialized domains like cardiology where limited annotated data and complex medical t…
Large Language Models for Automating Clinical Trial Criteria Conversion to OMOP CDM Queries: Accuracy and Efficiency Evaluation (Preprint) Open
BACKGROUND Clinical trials are vital for advancing medical knowledge but often face recruitment challenges. Real World Data (RWD)-based feasibility assessments show promise in improving trial design, but automating eligibility criteria con…
View article: Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation
Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation Open
Large language models (LLMs) have exhibited outstanding performance in natural language processing tasks. However, these models remain susceptible to adversarial attacks in which slight input perturbations can lead to harmful or misleading…
Medical language model specialized in extracting cardiac knowledge Open
The advent of the Transformer has significantly altered the course of research in Natural Language Processing (NLP) within the domain of deep learning, making Transformer-based studies the mainstream in subsequent NLP research. There has a…
Correction: Association of dietary sodium intake with impaired fasting glucose in adult cancer survivors: A population-based cross-sectional study Open
[This corrects the article DOI: 10.1371/journal.pone.0286346.].
View article: Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: machine learning model development and evaluation
Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: machine learning model development and evaluation Open
We successfully predicted the length of stay after surgery and provide explainable models with supporting analyses. In summary, we demonstrate the interpretation with the XGBoost model presenting insights on preoperative features and defin…
View article: Safety and Feasibility of Robot-Assisted Percutaneous Coronary Intervention Using the AVIAR 2.0 System: A Prospective, Multi-Center, Single-Arm, Open, Investigator-Initiated, Post-Approval Clinical Trial
Safety and Feasibility of Robot-Assisted Percutaneous Coronary Intervention Using the AVIAR 2.0 System: A Prospective, Multi-Center, Single-Arm, Open, Investigator-Initiated, Post-Approval Clinical Trial Open
ClinicalTrials.gov Identifier: NCT05981859.
View article: Long-term impacts of complete revascularization on clinical outcomes in patients with coronary chronic total occlusion
Long-term impacts of complete revascularization on clinical outcomes in patients with coronary chronic total occlusion Open
The impact of complete revascularization (CR), achieved through the recanalization of coronary chronic total occlusions (CTOs), on long-term patient outcomes remains uncertain. To evaluate this in patients who achieved CR after CTO-PCI wit…
View article: Artificial Intelligence–Based Fully Automated Quantitative Coronary Angiography vs Optical Coherence Tomography–Guided PCI
Artificial Intelligence–Based Fully Automated Quantitative Coronary Angiography vs Optical Coherence Tomography–Guided PCI Open
This study demonstrated the noninferiority of AI-QCA-assisted PCI to OCT-guided PCI in achieving MSA with comparable OCT-defined endpoints. (Fully Automated Quantitative Coronary Angiography Versus Optical Coherence Tomography Guidance for…
View article: Task-Specific Transformer-Based Language Models in Health Care: Scoping Review
Task-Specific Transformer-Based Language Models in Health Care: Scoping Review Open
Background Transformer-based language models have shown great potential to revolutionize health care by advancing clinical decision support, patient interaction, and disease prediction. However, despite their rapid development, the impleme…
View article: Optimal Time for Collateral Channel Wiring in Retrograde Chronic Total Occlusion Percutaneous Coronary Intervention
Optimal Time for Collateral Channel Wiring in Retrograde Chronic Total Occlusion Percutaneous Coronary Intervention Open
Collateral channel wiring (CCW) is important in a retrograde chronic total occlusion (CTO) procedure. However, the guidance is insufficient. To investigate the optimal CCW time, patients who had received retrograde CTO procedures were enro…
View article: Development and transfer learning of self-attention model for major adverse cardiovascular events prediction across hospitals
Development and transfer learning of self-attention model for major adverse cardiovascular events prediction across hospitals Open
Predicting major adverse cardiovascular events (MACE) is crucial due to its high readmission rate and severe sequelae. Current risk scoring model of MACE are based on a few features of a patient status at a single time point. We developed …
View article: Association of Lipoprotein(a) With Severe Degenerative Aortic Valve Stenosis
Association of Lipoprotein(a) With Severe Degenerative Aortic Valve Stenosis Open
Lp(a) levels >100 mg/dL were significantly associated with risk for severe degenerative AS and subsequent AVR, regardless of the baseline severity of AS. Such associations were not observed in other etiologies of severe AS.
View article: Automated, standardized, quantitative analysis of cardiovascular borders on chest X-rays using deep learning for assessing cardiovascular disease
Automated, standardized, quantitative analysis of cardiovascular borders on chest X-rays using deep learning for assessing cardiovascular disease Open
S OBJECTIVE The analysis of cardiovascular borders (CVBs) on chest X-rays (CXRs) has traditionally relied on subjective assessment, and the cardiothoracic (CT) ratio, its sole quantitative marker, does not reflect great vessel changes and …
View article: Fully automated quantitative coronary angiography versus optical coherence tomography guidance for coronary stent implantation (FLASH): Study protocol for a randomized controlled noninferiority trial
Fully automated quantitative coronary angiography versus optical coherence tomography guidance for coronary stent implantation (FLASH): Study protocol for a randomized controlled noninferiority trial Open
gov. Unique identifier: NCT05388357.
View article: Development and transfer learning of self-attention model for major adverse cardiovascular events prediction across hospitals
Development and transfer learning of self-attention model for major adverse cardiovascular events prediction across hospitals Open
Predicting major adverse cardiovascular events (MACE) is crucial due to its high readmission rate and severe sequelae. Current risk scoring model of MACE are based on a few features of a patient status at a single time point. We developed …
View article: HeartBERT : A language model pre-trained on anopen source dataset for cardiac text mining
HeartBERT : A language model pre-trained on anopen source dataset for cardiac text mining Open
The advent of the Transformer has significantly altered the course of research in Natural Language Processing (NLP) within thedomain of deep learning, making Transformer-based studies the mainstream in subsequent NLP research. There has al…
View article: Enhancing Clinical Efficiency through LLM: Discharge Note Generation for Cardiac Patients
Enhancing Clinical Efficiency through LLM: Discharge Note Generation for Cardiac Patients Open
Medical documentation, including discharge notes, is crucial for ensuring patient care quality, continuity, and effective medical communication. However, the manual creation of these documents is not only time-consuming but also prone to i…
View article: Quantitative Coronary Angiography vs Intravascular Ultrasonography to Guide Drug-Eluting Stent Implantation
Quantitative Coronary Angiography vs Intravascular Ultrasonography to Guide Drug-Eluting Stent Implantation Open
Importance Although intravascular ultrasonography (IVUS) guidance promotes favorable outcomes after percutaneous coronary intervention (PCI), many catheterization laboratories worldwide lack access. Objective To investigate whether systema…
View article: Artificial intelligence-based quantitative coronary angiography of major vessels using deep-learning
Artificial intelligence-based quantitative coronary angiography of major vessels using deep-learning Open
AI-QCA demonstrates promise as an automated tool for analysis in coronary angiography, offering potential advantages for the quantitative assessment of coronary lesions and clinical decision-making.