J Am Heart Assoc. 2026;15(9):e046989.

Artificial Intelligence-Enabled ECG for Elevated E/e' on Echocardiography: Hemodynamic Relevance and Prognostic Value.

, , , , , , , , , ,

제1저자 임재현 · 교신저자 이승표, 김경희

PMID 42047199 PMC13279472 DOI 10.1161/JAHA.125.046989 IF 6 순환기내과

소속 (6)

Department of Internal Medicine, Seoul National University College of Medicine and Seoul National University Hospital Seoul Republic of Korea.
Digital Healthcare Institute Sejong Hospital Bucheon Republic of Korea.
Medical AI Co., Ltd. Seoul Republic of Korea.
Biomedical Research Institute, Seoul National University Seoul Republic of Korea.
Healthcare AI Research Institute, Seoul National University Hospital Seoul Republic of Korea.
Division of Cardiology, Department of Internal Medicine, Incheon Sejong Hospital, Cardiovascular Center Incheon Republic of Korea.

Abstract

BACKGROUND Left ventricular filling pressure is associated with heart failure symptoms and a key prognostic marker and therapeutic target, but a scalable, accessible, and affordable tool for its noninvasive, serial estimation remains lacking. We developed an artificial intelligence (AI) model using a standard 12-lead ECG to detect increased E/e', a general surrogate of elevated left ventricular filling pressure on echocardiography.

METHODS The AI model was built upon a foundation model trained with >1 million multiethnic ECGs and fine-tuned through a development cohort of 225 737 ECGs and 115 982 echocardiogram records from 92 775 unique patients across 2 tertiary hospitals. The model performance was assessed in a separate internal test set (n=9278) and an independent external cohort from another tertiary hospital (n=17 926). Prognostic significance of the AI-ECG output was evaluated in these hospital cohorts, as well as the UK Biobank (n=43 347). Finally, we validated the model output against invasively measured left ventricular filling pressure through cardiac catheterization (n=60).

RESULTS The AI-ECG model detected increased E/e' with an area under the curve of 0.868 (95% CI, 0.859-0.877) and 0.850 (95% CI, 0.841-0.858) in the internal and external test cohorts, respectively. The AI-ECG output value demonstrated a strong correlation with invasively measured left ventricular end-diastolic pressure (Pearson's r=0.655) and was significantly associated with incident heart failure and mortality.

CONCLUSIONS The AI-ECG may enable identification of patients with increased left ventricular filling pressure and provide powerful prognostic information. Further prospective studies are warranted to evaluate its clinical utility.

Keywords

ECGartificial intelligenceleft ventricular filling pressureprognosis

Figures

**Figure 1** Study workflow. The study outlines the AiTiALVDD model development process, comprising upstream and downstream tasks using large‐scale ECG and echocardiogram data sets. External validation was conducted at Seoul National University Hospital and UK Biobank to assess primary, secondary, survival, and exploratory outcomes. ECHO indicates echocardiogram; ECMO, extracorporeal membrane oxygenation; HF, heart failure; LVAD, left ventricular assist device; LVEF, left ventricular ejection fraction; and LVFP, left ventricular filling pressure.

**Figure 2** Comparison of the AI‐ECG score distribution between increased and normal E/e' groups. Distribution of the AI‐ECG scores according to E/e' >15 or ≤15. The boxplots illustrate the AI‐ECG scores for the increased E/e' group (blue) and the normal E/e' group (pink). In the increased E/e' group (internal test), the mean AI‐ECG score was 37.2±22.1, with a median of 34.1 (interquartile range, 18.1–54.8). In contrast, the normal E/e' group had a mean AI‐ECG score of 10.6±13.1 and a median of 5.9 (1.6–14.7). In the increased E/e' group (external test), the mean AI‐ECG score was 32.2±20.7, with a median of 28.4 (14.8–46.3). In contrast, the normal E/e' group had a mean AI‐ECG score of 10.0±11.7 and a median of 6.0 (2.3–13.3). The cutoff score of 13.3 (indicated by the blue dashed line) was predefined during the model development phase using Youden's J statistic. A represents the internal test; B represents the external test. AI indicates artificial intelligence.

**Figure 3** Receiver operating characteristic curve analyses for primary and secondary outcomes. Receiver operating characteristics curves (A, internal test; B, external test), illustrating the discriminative ability of the AI‐ECG model in detecting elevated left ventricular filling pressure, defined by a mitral E/e' ratio >15 (primary outcome), and in identifying left ventricular diastolic dysfunction grade II/III (secondary outcome). The primary outcome is depicted in blue, and the secondary outcome is depicted in red. AI indicates artificial intelligence; AUPRC, area under the precision‐recall curve; and AUROC, area under the receiver operating characteristic curve.

**Figure 4** Model validation against invasively measured LVEDP. Correlation coefficients between parameters. AI indicates artificial intelligence; LAVI, left atrial volume index; LVEDP, left ventricular end‐diastolic pressure; and PCWP; pulmonary capillary wedge pressure.

그림 출처: PubMed Central 공개 논문 (PMC13279472)

Conflict of interest statement

Min Sung Lee, Sora Kang, Hak Seung Lee, Jong‐Hwan Jang, Jeong Min Son, and Joon‐Myoung Kwon are employees of Medical AI Co., Ltd. and are involved in an equity/royalty relationship with Medical AI Co., Ltd. Joon‐Myoung Kwon is the founder of Medical AI Co., Ltd. Seung‐Pyo Lee is involved in an equity relationship with Medical AI Co., Ltd. No other conflicts of interest relevant to this article were reported.

그 밖의 정보