주요 논문
3
*2026년 기준 최근 6년 이내 논문에 한해 Impact Factor가 표기됩니다.
1
article
|
인용수 0
·
2023Abstract 18249: Artificial Intelligence-Based Electrocardiogram Prediction for Duration of Atrial Fibrillation
Young Jun Park, Kyung Geun Kim, Sunghoon Joo, Mineok Chang, Yeha Lee
IF 35.5 (2023)
Circulation
Introduction: Atrial fibrillation (AF) is the most common sustained arrhythmia and is associated with poor clinical outcomes, including stroke, acute coronary events, and heart failure. Recent studies have shown that early rhythm treatment of new-onset atrial fibrillation improves the patient's prognosis. However, atrial fibrillation is often asymptomatic, and it is difficult to determine its duration accurately. Recently, AI-based ECG has been studied for various cardiovascular diseases. Hypothesis: We sought to develop and validate a predictive model of the ECG for the duration of atrial fibrillation . Methods: All patients aged 18 years older from the two hospitals with at least one ECG were included in the study. Only patients with sinus rhythm with ECG prior to atrial fibrillation with ECG were selected. An ECG within 1 year from AF was first documented in ECG was defined as new onset AF. After dividing our datasets into training (and test sets, we developed an end-to-end deep neural network to predict for the duration of AF. Performance evaluation was conducted using various metrics, including AUROC, AUPRC, sensitivity, specificity, F1 score. Results: The dataset consisted of 83,525 ECGs from 16,193 patients from two hospitals. The AUROC for discriminating old AF and new-onset AF is 0.8186 (0.8181 - 0.8190) on internal validation set and 0.7967 (0.7966 - 0.7969) on external validation set. Sensitivity, Specificity, and F1 score are 0.7126((0.7118-0.7134), 0.7697 (0.7693-0.7701) and 0.5751 (0.5745-0.5757) on internal validation set and 0.7309 (0.7307-0.7311), 0.7225 (0.7224-0.7227) and 0.6354 (0.6352-0.6356)on external validation set. Conclusions: Our deep learning model can be used to predict atrial fibrillation's duration. Additional studies are ongoing to understand the relative importance of ECG features.
http://dx.doi.org/10.1161/circ.148.suppl_1.18249
Medicine
Atrial fibrillation
Internal medicine
Cardiology
Sinus rhythm
Asymptomatic
Stroke (engine)
Heart failure
2
article
|
인용수 0
·
2023Abstract 14208: New Artificial Intelligence Algorithms of Electrocardiogram Detection for Patients With Heart Failure
Young Jun Park, Kyung Geun Kim, Sunghoon Joo, Mineok Chang, Yeha Lee
IF 35.5 (2023)
Circulation
Introduction: Heart failure (HF) is a global pandemic with an increasing prevalence. The burden of HF-related hospitalizations and costs are increasing. Artificial intelligence(AI) algorithms applied to electrocardiograms have shown promise in diagnosing HF, but they require a large amount of training data, which is scarce and costly. Transfer learning addresses this challenge by utilizing knowledge from previous tasks, resulting in superior performance with limited data compared to conventional AI algorithms Hypothesis: AI algorithms using transfer learning can be accurately diagnose heart failure with reduced ejection fraction(HFrEF) using electrocardiograms compared to conventional AI algorithms. Methods: All patients aged 18 years older from the two hospitals with at least one ECG were included in the study. Electrocardiogram, transthoracic Echocardiogram (TTE), and demographic data were collected. The AI algorithm consisted of two phases: conventional AI algorithms, pre-training with a large-scale ECG dataset and transfer learning for HFrEF detection. Performance evaluation was conducted using various metrics, including AUROC, sensitivity, specificity, accuracy, F1 score. Results: The dataset consisted of 687,911 ECGs from 259,943 patients. Testing the conventional model on the HFrEF resulted in a sensitivity of 63.8%, specificity of 96.2%, accuracy of 93.6%, area under the receiver operating curve (AUC) of 0.93 (95% CI, 0.92 - 0.94), and F1 score of 61.6%. Testing the transfer learning model on the HFrEF increased the sensitivity of 75.1%, accuracy of 93.7%, area under the receiver operating curve (AUC) of 0.952 (95% CI, 0.93 - 0.96), and F1 score of 65.6%. but lowered the specificity of 95.3% Conclusions: A New AI-enabled ECG algorithm for identifying patients with HFrEF can be more accurately diagnosed than conventional AL algorithms.
http://dx.doi.org/10.1161/circ.148.suppl_1.14208
Medicine
Receiver operating characteristic
Ejection fraction
Heart failure
Machine learning
Algorithm
Artificial intelligence
Area under the curve
Transfer of learning
Internal medicine
3
article
|
인용수 0
·
2022Abstract 12393: Two-Year Clinical Outcome of Mid-Range Ejection Fraction at Admission in Patients With Acute Myocardial Infarction
Ho Sung Jeon, Young In Kim, Junghee Lee, Dong‐Hyuk Cho, Young Jun Park, Jung‐Woo Son, Jun‐Won Lee, Young Jin Youn, Sung Gyun Ahn, Min‐Soo Ahn, Jang‐Young Kim, Byung‐Su Yoo, Seung‐Hwan Lee, Junghan Yoon, Dae Ryong Kang
IF 37.8 (2022)
Circulation
Introduction: The American Heart Association and European Society of cardiology guidelines reclassified heart failure according to left ventricular ejection fraction, recognizing patients with mid-range EF (mrEF; 40% to 49%) as a distinct group. However, studies on the clinical characteristics of mid-range EF patients and the occurrence of cardiovascular events in acute MI patients are insufficient. Methods: We categorized 6,553 patients with acute myocardial infarction (AMI) from the Korea AMI-National Institutes of Health between November 2011 and December 2015 into three groups (reduced EF ; LVEF < 40% at admission, mild-reduced EF ; LVEF 40 to 49%, preserved EF ;LVEF ≥50%). The primary endpoint was defined as any death at two-year. Secondary endpoints were defined as any myocardial infarction, any revascularization, patient-oriented composite outcome(POCE). Results: Compared to patients with other two groups, the reduced EF group had a highest overall mortality, POCE, and any MI (24.7% vs 8.3% vs 4.6%, p < 0.0001, 33.0% vs 15.6% vs 12.4%, p<0.0001, 3.9% vs 2.7% vs 2.6%, p<0.0046). When mid-range EF group was designated as a reference, in multivariate analysis including all variables, significant differences with HFrEF group was found. (Hazard ratio ). When compared with HFpEF, only Model 1 and Model 2 showed a significant statistical difference (Model 1 ; 0.65 (0.53-0.81), Model 2 ; 0.56 (0.56-0.86). Conclusions: Followed up for two years, significant differences in survival rates were observed between the mid-range EF, reduced EF, and preserved EF group. After adjusting for common prognostic factors affecting the overall mortality rate, the reduced EF group had a significantly higher mortality rate than mid-range EF group, but no significant difference was observed between the preserved EF and the mid-range EF group.
http://dx.doi.org/10.1161/circ.146.suppl_1.12393
Medicine
Ejection fraction
Internal medicine
Myocardial infarction
Cardiology
Hazard ratio
Heart failure
Revascularization
Clinical endpoint
Proportional hazards model