ECG-Derived Synthetic Left Ventricular Mechanics Predict Mortality After Acute Myocardial Infarction and Fatal Myocardial Infarction in the General Population

Q: What are the key findings of this study?

ECG-derived synthetic e′ independently predicted all-cause mortality after AMI beyond GRACE (HR 0.90 per 1 cm/s, P=0.006), and synthetic LV mechanics predicted fatal MI in the general population.

Q: What is the clinical evidence from this study?

Study design: Cohort. Population: Acute Myocardial Infarction and General Outpatient Risk Stratification (n=221575). Intervention: ECG-derived synthetic early diastolic mitral annular velocity (synthetic e′) and LV mechanical parameters (s′, MAPSE) vs. Per 1 cm/s (or 1 cm for MAPSE) increase and benchmarked against GRACE 2.0 score and LVEF. Primary outcome: All-cause mortality after acute myocardial infarction (adjusted for GRACE 2.0 score) (HR 0.90 per 1 cm/s, 95% CI 0.83-0.97, p=0.006).

Douglas Robert Corsi; John Furst; Ankush D. Jamthikar; Sajeev Singh; Gabriela M M Paixao; Antonio Ribeiro; Jagat Narula; BERNARD R. CHAITMAN; Jeffrey L. Carson; Naveena V. K. Yanamala; Partho P. Sengupta

doi:10.64898/2026.10.21.26366159

October 24, 2026Open Access

ECG-Derived Synthetic Left Ventricular Mechanics Predict Mortality After Acute Myocardial Infarction and Fatal Myocardial Infarction in the General Population

View Full Paper

Ask AI

Bookmark

Share

Key result

Synthetic ECG-derived e′ links to ~10% lower post-AMI mortality per cm/s beyond GRACE.

HR 0.90 per 1 cm/s
95% CI 0.83-0.97
P=0.006
n=221,575

Why the study?

Left ventricular mechanical function predicts outcomes after AMI, and recovering these parameters from the 12-lead ECG could enable point-of-care risk assessment. Whether ECG-derived synthetic LV mechanics predict post-AMI all-cause mortality and population MI-specific mortality beyond the GRACE score and LVEF was unknown.

Do 12-lead ECG-derived synthetic left ventricular mechanical parameters (s′, e′, and MAPSE) predict all-cause mortality after acute myocardial infarction and fatal myocardial infarction in the general population beyond the GRACE score and left ventricular ejection fraction?

Key Points

To determine whether synthetic left ventricular mechanical parameters derived from 12-lead ECGs predict post-infarction and population mortality, adding prognostic value beyond the GRACE score and ejection fraction.
Synthetic peak systolic velocity (s′), early diastolic velocity (e′), and mitral annular plane systolic excursion (MAPSE) were generated from 12-lead ECGs using a validated generative adversarial network without retraining.
Associations were evaluated in an acute myocardial infarction cohort (n=1,065; median follow-up 1.44 years) using Cox regression and in a general population cohort (n=219,564; median follow-up 3.42 years) using Fine-Gray competing risk models.
Incremental prognostic performance was benchmarked against the GRACE score, measured echocardiographic ejection fraction, and three AI-ECG reduced ejection fraction models.
In the post-discharge infarction cohort (n=1,017; 61 deaths), synthetic e′ independently predicted mortality beyond GRACE (HR=0.84 per 1 cm/s; 95% CI 0.76-0.93; P=0.001; C-index increased from 0.67 to 0.70) and beyond measured LVEF <50% (HR=0.85; 95% CI 0.76-0.94; P=0.002).
In the population cohort (817 MI deaths), all synthetic metrics predicted MI mortality after adjusting for age, sex, and ECG abnormalities: MAPSE (adjusted sHR=0.49; 95% CI 0.37-0.65), s′ (adjusted sHR=0.78; 95% CI 0.72-0.84), and e′ (adjusted sHR=0.87; 95% CI 0.82-0.93; each P<0.001).

Study Design

Type

Cohort (n=221,575)

Blinding

Blinded to outcome

Multicenter

Yes

Structured PICO

Do 12-lead ECG-derived synthetic left ventricular mechanical parameters (s′, e′, and MAPSE) predict all-cause mortality after acute myocardial infarction and fatal myocardial infarction in the general population beyond the GRACE score and left ventricular ejection fraction?

P

Population

1,065 hospitalized adults with acute myocardial infarction (median age 65 years, 32% female) followed for a median of 1.44 years alongside 946 non-AMI controls in the US, and 219,564 primary-care outpatients (median age 50 years, 60.4% female) followed for a median of 3.42 years in Brazil.

E

Exposure

12-lead ECG-derived synthetic left ventricular (LV) mechanical parameters — peak systolic mitral annular velocity (synthetic s′), peak early diastolic mitral annular velocity (synthetic e′), peak late diastolic velocity (synthetic a′), and mitral annular plane systolic excursion (synthetic MAPSE) — generated by a previously validated generative adversarial network (GAN) applied without retraining.

C

Comparator

GRACE 2.0 risk score, measured echocardiographic LVEF (<50%) and tissue Doppler imaging (TDI), and three open-source AI-ECG reduced ejection fraction models (AiTiA and HeartWise predicting concurrent LVEF <50%, and the Pan et al. AI-ECG HFrEF risk model predicting incident LVEF ≤40% over 1-5 years).

O

Outcome

All-cause mortality following index AMI hospitalization in the clinical AMI cohort (at median follow-up of 1.44 years [IQR 0.48-2.60]), and cause-specific myocardial infarction (MI) mortality (with heart failure, other cardiac, and non-cardiac deaths as competing events) in the general population cohort (at median follow-up of 3.42 years [IQR 2.1-5.1]).hard clinical

Main Result

Hazard Ratio: 0.9 (95% CI 0.83–0.97)

p-value: p=0.006

Limitations

Retrospective observational analysis of electronic health records and registry data
Exclusion of 109 AMI patients due to incompatible ECG sampling frequency (<500 Hz) and 106,387 CODE-15 participants due to incomplete follow-up
AiTiA and HeartWise AI-ECG models could not be applied as external comparators in the Brazilian population cohort

Implication

AI-enabled recovery of synthetic left ventricular tissue Doppler mechanical indices (s′, e′, and MAPSE) directly from a standard 12-lead ECG independently predicts all-cause mortality after acute myocardial infarction and fatal MI in the general population, providing incremental prognostic value beyond the GRACE score and LVEF.

Abstract

Background: Left ventricular (LV) mechanical function predicts outcomes after acute myocardial infarction (AMI). Recovering these parameters from the 12-lead electrocardiogram (ECG) could enable point-of-care risk assessment wherever an ECG is acquired. Objectives: To determine whether ECG-derived synthetic LV mechanics predict all-cause mortality after AMI and myocardial infarction (MI)-specific mortality in the general population and add information beyond the GRACE score and ejection fraction. Methods: Synthetic peak systolic (s′) and early diastolic (e′) mitral annular velocities and mitral annular plane systolic excursion (MAPSE) were derived from the 12-lead ECG by a previously validated generative adversarial network, applied without retraining and blinded to outcome. Associations were assessed in an AMI cohort (n=1,065) by Cox regression and a population cohort (n=219,564) by Fine-Gray models. Incremental value was tested against GRACE, three AI-ECG reduced ejection fraction (EF) models, and measured LVEF. Results: In the AMI cohort (109 deaths; median follow-up 1.44 years), all three parameters predicted all-cause mortality (each P<0.001). Synthetic e′ was the sole independent predictor after adjustment for clinical covariates (HR=0.90 per 1 cm/s; 95% CI 0.84-0.98) and for GRACE (HR=0.90; 0.83-0.97; P=0.006). In the post-discharge cohort (n=1,017; 61 deaths), synthetic e′ improved discrimination beyond GRACE (C-index 0.67 to 0.70; HR=0.84 per 1 cm/s; 95% CI 0.76-0.93; P=0.001) and remained independent of AI-ECG-predicted and measured LVEF (HR 0.84-0.86 per 1 cm/s; all P≤0.004), contributing 28-46% of each model's prognostic information. In the population cohort (817 MI deaths; median follow-up 3.42 years), all three predicted MI-specific mortality after adjustment for age, sex, and ECG abnormalities, MAPSE showing the largest effect (sHR=0.49; 95% CI 0.37-0.65), with s′ (sHR=0.78; 0.72-0.84) and e′ (sHR=0.87; 0.82-0.93) also predictive (each P<0.001). Conclusions: ECG-derived synthetic LV mechanical parameters predict all-cause mortality after AMI and fatal MI in the general population, adding information beyond the GRACE score and LVEF.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Corsi et al. (2026) conducted a cohort in Acute Myocardial Infarction and General Outpatient Risk Stratification (n=221,575). ECG-derived synthetic early diastolic mitral annular velocity (synthetic e′) and LV mechanical parameters (s′, MAPSE) vs. Per 1 cm/s (or 1 cm for MAPSE) increase and benchmarked against GRACE 2.0 score and LVEF was evaluated on All-cause mortality after acute myocardial infarction (adjusted for GRACE 2.0 score) (HR 0.90 per 1 cm/s, 95% CI 0.83-0.97, p=0.006). ECG-derived synthetic e′ independently predicted all-cause mortality after AMI beyond GRACE (HR 0.90 per 1 cm/s, P=0.006), and synthetic LV mechanics predicted fatal MI in the general population.

synapsesocial.com/papers/6ae28f09cbadf70daf6c43dc https://doi.org/10.64898/2026.10.21.26366159

View Full Paper

Ask AI

Bookmark

Share

ECG-Derived Synthetic Left Ventricular Mechanics Predict Mortality After Acute Myocardial Infarction and Fatal Myocardial Infarction in the General Population

Key Points

Study Design

Structured PICO

Main Result

Limitations

Implication

Abstract

Discussion

Cite This Study

ECG-Derived Synthetic Left Ventricular Mechanics Predict Mortality After Acute Myocardial Infarction and Fatal Myocardial Infarction in the General Population

Key Points

Study Design

Structured PICO

Main Result

Limitations

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading