전기현 교수

None.

The DAMI predicted in-hospital mortality and 12-month mortality of AMI patients more accurately than the existing risk scores and other machine-learning methods.

Cardiac trauma from penetrating chest injury is a life-threatening condition. It was reported that < 10% of patients arrives at the emergency department alive. Penetrating chest injury can cause serious damage in more than 1 cardiac structure, including myocardial lacerations, ventricular septal defect (VSD), fistula between aorta and right cardiac chamber and valves. The presence of pericardial effusion (even a small amount) on the initial echocardiography might be the only clue to serious card

The proposed DLM demonstrated a high performance in identifying PSVT during normal sinus rhythm. Thus, it can be used as a rapid, inexpensive, point-of-care means of identifying PSVT in patients.

The DLA accurately identified paroxysmal AF using 12-lead SR ECG in patients with ESUS and outperformed the conventional models. The DLA model along with the traditional AF risk factors could be a useful tool to identify paroxysmal AF in ESUS patients.

gov . Unique identifier: NCT04734028.

Electrocardiogram (ECG) changes after primary percutaneous coronary intervention (PCI) in ST-segment elevation myocardial infarction (STEMI) patients are associated with prognosis. This study investigated the feasibility of predicting left ventricular (LV) dysfunction in STEMI patients using an artificial intelligence (AI)-enabled ECG algorithm developed to diagnose STEMI. Serial ECGs from 637 STEMI patients were analyzed with the AI algorithm, which quantified the probability of STEMI at variou

Abstract Background It is not well-known which components of central blood pressure (CBP) are more influential to target organ damage (TOD). This study aimed to determine the relationship between CBP measurements and various types of TOD in high-risk patients. Methods A total of 148 patients who had documented atherosclerotic cardiovascular disease or its multiple risk factors were prospectively enrolled. CBP was measured by using applanation tonometry of the radial artery. The following nine TO

Abstract Background Anemia changed the morphology of electrocardiography (ECG), and researchers suggested that mismatching oxygen demand and supply in the myocardium affects the ECG Purpose A deep-learning-based algorithm (DLA) that enables non-invasive anemia screening from electrocardiograms (ECGs) may improve the detection of anemia. Methods A DLA was developed using 57,435 ECGs from 31,898 patients and was internally validated using 7,369 ECGs from 7,369 patients taken at one hospital. Exter

Objective: In hypertensive patients, U-shaped relationship has been reported between blood pressure and future events. However, there is little information about the significance of blood pressure on the outcomes of patients with coronary artery disease who underwent revascularization. We assessed the risk of cardiovascular events according to diastolic blood pressure (DBP) at discharge in patients with acute myocardial infarction (AMI) underwent percutaneous coronary intervention (PCI). Design

Abstract Background Atrial fibrillation (AF) is the most cause of cardioembolic source causing cryptogenic stroke. In these, anticoagulation therapy could reduce recurrence of stroke. However, paroxysmal AF would not be detected even by 24 hours Holter monitoring. Deep learning-based electrocardiogram (ECG) analysis models were recently developed to detect AF during sinus rhythm. Purpose We aimed to develop a deep learning algorithm (DLA) to detect AF during sinus rhythm and validate the model i

Statistical analysis is essential for drawing meaningful conclusions and ensuring the validity and reliability of medical research.However, many researchers face challenges due to the complexity of statistical techniques.Recent advances in artificial intelligence, particularly large language models such as ChatGPT, offer new opportunities to make statistical processes more accessible.ChatGPT can explain complex statistical concepts in plain language, assist with data management, generate Python

Medical therapies and mechanical interventions for the treatment of myocardial infarction (MI) and ischemic heart failure have seen great progress. However, current therapies only slow the progression to heart failure, but do not stimulate regeneration to recover the loss of functional myocytes. Stem cell-based therapy is a novel modality that can potentially be used for the treatment of ischemic cardiac injury and heart failure wherein cardiac tissue is regenerated thereby improving cardiac fun

This study developed a machine learning-based Clinical Decision Support System (CDSS) by integrating an AI-derived Congestion Index (CIx) from chest X-rays with clinical and laboratory data in patients with acute decompensated heart failure (ADHF). Among 9,286 patients, the model incorporating imaging data showed the highest predictive accuracy (AUROC 0.750). CIx demonstrated prognostic performance comparable to NT-proBNP and showed a significant increase in event rates across quartiles. The fin