Jiesuck Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jiesuck Park has a total of 168 co-authors. Here are the top co-authors by number of shared publications:
- Yeonyee Elizabeth Yoon
Cardiovascular Center and Division of Cardiology, Department of Internal Medicine, Seoul National University Bundang Hospital, Seongnam, Korea
24 shared publications - In-Chang Hwang
Cardiovascular Center and Division of Cardiology, Department of Internal Medicine, Seoul National University Bundang Hospital, Seongnam, Korea
22 shared publications - Goo-Yeong Cho
Cardiovascular Center and Division of Cardiology, Department of Internal Medicine, Seoul National University Bundang Hospital, Seongnam, Korea
20 shared publications - Hong-Mi Choi
Department of Cardiology, Cardiovascular Center, Seoul National University Bundang Hospital, Seongnam, Korea
19 shared publications - Bon-Kwon Koo
Department of Internal Medicine and Cardiovascular Center, Seoul National University Hospital, Seoul National University of College of Medicine, Seoul, South Korea
7 shared publications - Jeehoon Kang
Department of Internal Medicine, Seoul National University Hospital, Seoul, Korea
7 shared publications
Latest Publications
- Open Access
- 1 January 2027
- Published by XMLink in Korean Circulation Journal
- Vol. 57
Afterload-Adjusted Strain Refines Risk Stratification in Aortic Stenosis With Varying Degrees of Aortic Regurgitation
Sun J, et al. Korean Circ J. 2027 ;57:e74. https://doi.org/10.4070/kcj.2026.0285
- 1 January 2027
- Published by XMLink in Korean Circulation Journal
- Vol. 57
Open AccessAfterload-Adjusted Strain Refines Risk Stratification in Aortic Stenosis With Varying Degrees of Aortic Regurgitation
Sun J, et al. Korean Circ J. 2027 ;57:e74. https://doi.org/10.4070/kcj.2026.0285
- 20 October 2026
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 15 (20)
Cardiac Reverse Remodeling and Clinical Outcomes Following Angiotensin Receptor‐Neprilysin Inhibitor Therapy in Heart Failure With Reduced Ejection Fraction
Background: Cardiac reverse remodeling and associated clinical outcomes following angiotensin receptor‐neprilysin inhibitor (ARNI) therapy in patients with heart failure (HF) with reduced ejection fraction (EF) remain unclear. We investigated differences in 1‐year echocardiographic response after ARNI therapy and predictors of clinical outcomes. Methods: This study involved patients with HF with reduced EF and ARNI therapy for more than 6 months, using data from a 2‐center registry. Echocardiographic data were analyzed at baseline and 1 year after ARNI initiation. Responders were defined as patients with a ≥30% reduction in left ventricular end‐systolic volume at 1 year; all others were nonresponders. The primary outcome was cardiovascular death, and secondary outcomes were hospitalization for HF and all‐cause death. Time‐by‐group interactions in echocardiographic parameters were evaluated using linear mixed‐effects models. Results: Among 1002 patients (mean age: 64.2±13.7 years; 70.8% men), 451 (45.0%) were responders and 551 (55.0%) were nonresponders. Responders had a lower baseline left ventricular EF but higher left ventricular EF at 1 year (27.0% [95% CI, 22.0–33.0] and 48.0% [95% CI, 42.0–55.0]). Both groups showed improvements in diastolic parameters, with more pronounced changes in responders. In multivariable analysis, nonresponders had a significantly higher risk of cardiovascular death, hospitalization for HF, and all‐cause death (all P <0.001). Male sex and a higher baseline left ventricular EF were independent predictors of nonresponse, whereas systolic blood pressure ≥110 mm Hg and atrial fibrillation were associated with better outcomes. Conclusions: Cardiac reverse remodeling after ARNI therapy varies among patients with HF with reduced EF. Positive responders to ARNI therapy at 1 year experienced more favorable clinical outcomes.
- 20 October 2026
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 15 (20)
Cardiac Reverse Remodeling and Clinical Outcomes Following Angiotensin Receptor‐Neprilysin Inhibitor Therapy in Heart Failure With Reduced Ejection Fraction
Background: Cardiac reverse remodeling and associated clinical outcomes following angiotensin receptor‐neprilysin inhibitor (ARNI) therapy in patients with heart failure (HF) with reduced ejection fraction (EF) remain unclear. We investigated differences in 1‐year echocardiographic response after ARNI therapy and predictors of clinical outcomes. Methods: This study involved patients with HF with reduced EF and ARNI therapy for more than 6 months, using data from a 2‐center registry. Echocardiographic data were analyzed at baseline and 1 year after ARNI initiation. Responders were defined as patients with a ≥30% reduction in left ventricular end‐systolic volume at 1 year; all others were nonresponders. The primary outcome was cardiovascular death, and secondary outcomes were hospitalization for HF and all‐cause death. Time‐by‐group interactions in echocardiographic parameters were evaluated using linear mixed‐effects models. Results: Among 1002 patients (mean age: 64.2±13.7 years; 70.8% men), 451 (45.0%) were responders and 551 (55.0%) were nonresponders. Responders had a lower baseline left ventricular EF but higher left ventricular EF at 1 year (27.0% [95% CI, 22.0–33.0] and 48.0% [95% CI, 42.0–55.0]). Both groups showed improvements in diastolic parameters, with more pronounced changes in responders. In multivariable analysis, nonresponders had a significantly higher risk of cardiovascular death, hospitalization for HF, and all‐cause death (all P <0.001). Male sex and a higher baseline left ventricular EF were independent predictors of nonresponse, whereas systolic blood pressure ≥110 mm Hg and atrial fibrillation were associated with better outcomes. Conclusions: Cardiac reverse remodeling after ARNI therapy varies among patients with HF with reduced EF. Positive responders to ARNI therapy at 1 year experienced more favorable clinical outcomes.
- Open Access
- 17 June 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e90099
Multitask Artificial Intelligence–Based Electrocardiogram Tool for Preoperative Cardiac Testing in Noncardiac Surgery: Retrospective Cohort Study of Health Care Utilization and Costs
Background: Preoperative cardiovascular risk stratification is essential in noncardiac surgery, but conventional testing is frequently overused, increasing costs without improving outcomes. Artificial intelligence (AI)–enabled electrocardiography (ECG) may enhance perioperative risk assessment by identifying surgical candidates at very low-risk for adverse events. Objective: This study aimed to evaluate whether AI-ECG–based risk stratification could help decrease low-yield preoperative cardiovascular testing and reduce associated costs, without an observed increase in postoperative adverse outcomes, in candidates for noncardiac surgery. Methods: We retrospectively analyzed 41,218 patients (46,135 ECG-surgery pairs) undergoing noncardiac surgery at Seoul National University Bundang Hospital (2020-2021). An AI-ECG algorithm generated eight probability scores for cardiac conditions, classifying cases as low- or high-risk. Based on the performance and results of preoperative cardiovascular testing (transthoracic echocardiography, coronary computed tomography angiography, single-photon emission computed tomography, or coronary angiography), cases were classified as no advanced cardiovascular imaging, negative-test, or positive-test. The primary end point was a 30-day composite of all-cause mortality and unplanned percutaneous coronary intervention. Results: AI-ECG classified 92.3% (42,599/46,135) of cases as low-risk, with a composite outcome rate of 0.2% (79/42,599) vs 2.9% (101/3536) in high-risk cases. Preoperative cardiovascular testing was performed in 11.8% (5458/46,135) of cases, with only 16.3% (892/5458) yielding positive findings. In AI-ECG low-risk cases, event rates were uniformly low (0.2%-0.4%) irrespective of whether advanced cardiovascular testing was performed, whereas in high-risk cases, rates were consistently high (2.6%-3.4%). The incidence of the composite outcome was consistently higher in AI-ECG–graded high-risk cases across all European Society of Cardiology surgical risk and Revised Cardiac Risk Index strata. Conclusions: In this retrospective cohort, a multitask AI-ECG identified surgical candidates at low-risk for postoperative complications, for whom advanced cardiovascular testing demonstrated low diagnostic yield. Integrating AI-ECG with conventional risk tools may offer an exploratory strategy to optimize resource use and minimize redundant testing. Prospective studies are needed to confirm the clinical and economic benefits of AI-ECG as a screening tool.
- 17 June 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e90099
Open AccessMultitask Artificial Intelligence–Based Electrocardiogram Tool for Preoperative Cardiac Testing in Noncardiac Surgery: Retrospective Cohort Study of Health Care Utilization and Costs
Background: Preoperative cardiovascular risk stratification is essential in noncardiac surgery, but conventional testing is frequently overused, increasing costs without improving outcomes. Artificial intelligence (AI)–enabled electrocardiography (ECG) may enhance perioperative risk assessment by identifying surgical candidates at very low-risk for adverse events. Objective: This study aimed to evaluate whether AI-ECG–based risk stratification could help decrease low-yield preoperative cardiovascular testing and reduce associated costs, without an observed increase in postoperative adverse outcomes, in candidates for noncardiac surgery. Methods: We retrospectively analyzed 41,218 patients (46,135 ECG-surgery pairs) undergoing noncardiac surgery at Seoul National University Bundang Hospital (2020-2021). An AI-ECG algorithm generated eight probability scores for cardiac conditions, classifying cases as low- or high-risk. Based on the performance and results of preoperative cardiovascular testing (transthoracic echocardiography, coronary computed tomography angiography, single-photon emission computed tomography, or coronary angiography), cases were classified as no advanced cardiovascular imaging, negative-test, or positive-test. The primary end point was a 30-day composite of all-cause mortality and unplanned percutaneous coronary intervention. Results: AI-ECG classified 92.3% (42,599/46,135) of cases as low-risk, with a composite outcome rate of 0.2% (79/42,599) vs 2.9% (101/3536) in high-risk cases. Preoperative cardiovascular testing was performed in 11.8% (5458/46,135) of cases, with only 16.3% (892/5458) yielding positive findings. In AI-ECG low-risk cases, event rates were uniformly low (0.2%-0.4%) irrespective of whether advanced cardiovascular testing was performed, whereas in high-risk cases, rates were consistently high (2.6%-3.4%). The incidence of the composite outcome was consistently higher in AI-ECG–graded high-risk cases across all European Society of Cardiology surgical risk and Revised Cardiac Risk Index strata. Conclusions: In this retrospective cohort, a multitask AI-ECG identified surgical candidates at low-risk for postoperative complications, for whom advanced cardiovascular testing demonstrated low diagnostic yield. Integrating AI-ECG with conventional risk tools may offer an exploratory strategy to optimize resource use and minimize redundant testing. Prospective studies are needed to confirm the clinical and economic benefits of AI-ECG as a screening tool.
- Open Access
- 20 May 2026
- Published by Springer Nature in Journal of Cardiovascular Imaging
- Vol. 34 (1) , 10
Fully automated artificial intelligence–based echocardiographic analysis substantially reduces workflow time while preserving measurement accuracy: a pilot study
Background: Transthoracic echocardiography (TTE) requires time-intensive integration of quantitative measurements and qualitative visual assessment. Fully automated artificial intelligence (AI)-based analysis may reduce total analysis time while preserving accuracy, but systematic real-world validation remains limited. Methods: This prospective, single-center pilot study enrolled 40 TTE examinations. Identical deidentified DICOM datasets were independently provided to a trained cardiac sonographer and a fully automated AI system comprising quantitative and qualitative visual interpretation modules. All outputs were compared with a cardiologist-adjudicated reference standard. Primary endpoints were total analysis time and noninferiority of AI-derived left ventricular ejection fraction (LVEF) versus the reference standard, with a prespecified margin of 3 percentage points (one-sided α = 0.025). Results: Median analysis time was 94 s (interquartile range [IQR], 82–106 s) for the AI workflow versus 490 s (IQR, 438–626 s) for the human workflow (P < 0.001). AI-derived LVEF met the noninferiority criterion (mean difference, 0.00 percentage points; upper one-sided 95% confidence bound, 1.41 percentage points; P < 0.001), with an intraclass correlation coefficient (ICC) of 0.902 (95% confidence interval, 0.822–0.947). ICCs for secondary quantitative indices ranged from 0.625 to 0.989. For aortic regurgitation severity grading, AI’s overall accuracy was 75.0% (quadratic weighted κ = 0.762), compared with 82.5% for human interpretation (κ = 0.812, McNemar P = 0.579). Conclusions: Fully automated AI-assisted TTE analysis substantially reduced total analysis time while maintaining noninferior LVEF accuracy and acceptable performance across secondary quantitative and qualitative indices. These findings support the use of AI as a practical workflow accelerator in routine echocardiography.
- 20 May 2026
- Published by Springer Nature in Journal of Cardiovascular Imaging
- Vol. 34 (1) , 10
Open AccessFully automated artificial intelligence–based echocardiographic analysis substantially reduces workflow time while preserving measurement accuracy: a pilot study
Background: Transthoracic echocardiography (TTE) requires time-intensive integration of quantitative measurements and qualitative visual assessment. Fully automated artificial intelligence (AI)-based analysis may reduce total analysis time while preserving accuracy, but systematic real-world validation remains limited. Methods: This prospective, single-center pilot study enrolled 40 TTE examinations. Identical deidentified DICOM datasets were independently provided to a trained cardiac sonographer and a fully automated AI system comprising quantitative and qualitative visual interpretation modules. All outputs were compared with a cardiologist-adjudicated reference standard. Primary endpoints were total analysis time and noninferiority of AI-derived left ventricular ejection fraction (LVEF) versus the reference standard, with a prespecified margin of 3 percentage points (one-sided α = 0.025). Results: Median analysis time was 94 s (interquartile range [IQR], 82–106 s) for the AI workflow versus 490 s (IQR, 438–626 s) for the human workflow (P < 0.001). AI-derived LVEF met the noninferiority criterion (mean difference, 0.00 percentage points; upper one-sided 95% confidence bound, 1.41 percentage points; P < 0.001), with an intraclass correlation coefficient (ICC) of 0.902 (95% confidence interval, 0.822–0.947). ICCs for secondary quantitative indices ranged from 0.625 to 0.989. For aortic regurgitation severity grading, AI’s overall accuracy was 75.0% (quadratic weighted κ = 0.762), compared with 82.5% for human interpretation (κ = 0.812, McNemar P = 0.579). Conclusions: Fully automated AI-assisted TTE analysis substantially reduced total analysis time while maintaining noninferior LVEF accuracy and acceptable performance across secondary quantitative and qualitative indices. These findings support the use of AI as a practical workflow accelerator in routine echocardiography.
- Open Access
A Deep Learning-Based Single-View Echocardiographic Analysis for Prediction of Left Ventricular Outflow Tract Obstruction After Transcatheter Aortic Valve Replacement
Aims: Dynamic left ventricular outflow tract obstruction (LVOTO) is a hemodynamically significant complication following transcatheter aortic valve replacement (TAVR) that remains difficult to predict with conventional transthoracic echocardiography (TTE). We examined whether a deep learning (DL) model developed for LVOTO detection in hypertrophic cardiomyopathy (HCM) could predict post-TAVR LVOTO from pre-TAVR TTE in patients with severe aortic stenosis (AS). Methods and Results: In this retrospective study of 302 consecutive patients undergoing TAVR for severe AS, a pre-trained DL model was applied to pre-TAVR TTE to generate a patient-level DL index of LVOTO (DLi-LVOTO; range 0–100). Post-TAVR LVOTO was defined as a peak pressure gradient ≥30 mmHg on follow-up TTE. Logistic regression and receiver operating characteristic analyses assessed the association and discriminative performance of DLi-LVOTO. Pre-TAVR LVOTO was present in 32 patients (10.6%) and post-TAVR LVOTO in 35 (11.6%). Follow-up TTE was performed at a median of 47 days (IQR 37–63) after TAVR, with the majority of TTE (216 of 302, 71.5%) performed within 2 months. DLi-LVOTO was significantly higher in patients with LVOTO at both pre- and post-TAVR TTE (all p<0.001). In multivariable analysis, DLi-LVOTO remained independently associated with post-TAVR LVOTO even after adjusting for conventional TTE parameters and pre-TAVR LVOTO (adjusted OR 1.29, 95% CI 1.06–1.56 per 10-score increase, p=0.011), with an AUROC of 0.78 (95% CI 0.72–0.85). Among patients without pre-TAVR LVOTO, DLi-LVOTO retained independent predictive value (adjusted OR 1.56, 95% CI 1.19–2.06, p=0.001; AUROC 0.84, 95% CI 0.77–0.91). Conclusion: A DL model originally trained in HCM patients independently predicts post-TAVR LVOTO from pre-TAVR TTE, including in patients without pre-existing LVOTO, suggesting it captures hemodynamic features beyond conventional echocardiographic assessment.
Open AccessA Deep Learning-Based Single-View Echocardiographic Analysis for Prediction of Left Ventricular Outflow Tract Obstruction After Transcatheter Aortic Valve Replacement
Aims: Dynamic left ventricular outflow tract obstruction (LVOTO) is a hemodynamically significant complication following transcatheter aortic valve replacement (TAVR) that remains difficult to predict with conventional transthoracic echocardiography (TTE). We examined whether a deep learning (DL) model developed for LVOTO detection in hypertrophic cardiomyopathy (HCM) could predict post-TAVR LVOTO from pre-TAVR TTE in patients with severe aortic stenosis (AS). Methods and Results: In this retrospective study of 302 consecutive patients undergoing TAVR for severe AS, a pre-trained DL model was applied to pre-TAVR TTE to generate a patient-level DL index of LVOTO (DLi-LVOTO; range 0–100). Post-TAVR LVOTO was defined as a peak pressure gradient ≥30 mmHg on follow-up TTE. Logistic regression and receiver operating characteristic analyses assessed the association and discriminative performance of DLi-LVOTO. Pre-TAVR LVOTO was present in 32 patients (10.6%) and post-TAVR LVOTO in 35 (11.6%). Follow-up TTE was performed at a median of 47 days (IQR 37–63) after TAVR, with the majority of TTE (216 of 302, 71.5%) performed within 2 months. DLi-LVOTO was significantly higher in patients with LVOTO at both pre- and post-TAVR TTE (all p<0.001). In multivariable analysis, DLi-LVOTO remained independently associated with post-TAVR LVOTO even after adjusting for conventional TTE parameters and pre-TAVR LVOTO (adjusted OR 1.29, 95% CI 1.06–1.56 per 10-score increase, p=0.011), with an AUROC of 0.78 (95% CI 0.72–0.85). Among patients without pre-TAVR LVOTO, DLi-LVOTO retained independent predictive value (adjusted OR 1.56, 95% CI 1.19–2.06, p=0.001; AUROC 0.84, 95% CI 0.77–0.91). Conclusion: A DL model originally trained in HCM patients independently predicts post-TAVR LVOTO from pre-TAVR TTE, including in patients without pre-existing LVOTO, suggesting it captures hemodynamic features beyond conventional echocardiographic assessment.
- Open Access
Sarcomere Variants of Uncertain Significance identify an Intermediate Clinical Risk Profile in Hypertrophic Cardiomyopathy
Background: The clinical significance of sarcomere variants of uncertain significance (VUS) in hypertrophic cardiomyopathy (HCM) remains unclear, and VUS are currently regarded as clinically non-actionable despite their increasing prevalence. This study aimed to evaluate genotype–phenotype and genotype–outcome associations according to variant pathogenicity in patients with HCM, with a particular focus on the clinical relevance of sarcomere VUS. Methods: This multicenter retrospective cohort study included 438 patients with HCM who underwent next-generation sequencing-based genetic testing at two tertiary hospitals. Patients were classified into three groups: pathogenic or likely pathogenic (P/LP) variants, VUS, and no sarcomere mutations. Clinical characteristics, imaging phenotypes, and outcomes were compared across groups. The primary endpoint was a composite of cardiovascular death, aborted sudden cardiac death, appropriate implantable cardioverter-defibrillator therapy, and heart transplantation. Time-to-event analyses were performed using Kaplan-Meier methods and Cox proportional hazards models with Firth’s penalized partial likelihood approach. Results: P/LP variants were identified in 171 patients (39.0%) and sarcomere VUS in 159 patients (36.3%). Patients with VUS demonstrated intermediate clinical and phenotypic features between P/LP carriers and genotype-negative patients. Kaplan–Meier analysis showed a graded difference in event-free survival across variant classifications. While VUS were not independently associated with adverse outcomes when modeled as a categorical variable, increasing pathogenicity from genotype-negative to VUS and P/LP variants was associated with a stepwise increase in risk of the primary endpoint (hazard ratio 2.05, 95% confidence interval 1.11–4.16 p=0.019). Identified VUS were preferentially enriched in Z-disc and giant sarcomere scaffolding proteins. Conclusion: Sarcomere VUS represent intermediate characteristics along a continuum of sarcomere dysfunction, associated with distinct phenotypic features and clinical outcomes compared with both P/LP variants and the absence of sarcomere mutations. These findings suggest that sarcomere VUS may not be entirely clinically neutral and should be interpreted within a broader genetic and structural context in patients with HCM.
Open AccessSarcomere Variants of Uncertain Significance identify an Intermediate Clinical Risk Profile in Hypertrophic Cardiomyopathy
Background: The clinical significance of sarcomere variants of uncertain significance (VUS) in hypertrophic cardiomyopathy (HCM) remains unclear, and VUS are currently regarded as clinically non-actionable despite their increasing prevalence. This study aimed to evaluate genotype–phenotype and genotype–outcome associations according to variant pathogenicity in patients with HCM, with a particular focus on the clinical relevance of sarcomere VUS. Methods: This multicenter retrospective cohort study included 438 patients with HCM who underwent next-generation sequencing-based genetic testing at two tertiary hospitals. Patients were classified into three groups: pathogenic or likely pathogenic (P/LP) variants, VUS, and no sarcomere mutations. Clinical characteristics, imaging phenotypes, and outcomes were compared across groups. The primary endpoint was a composite of cardiovascular death, aborted sudden cardiac death, appropriate implantable cardioverter-defibrillator therapy, and heart transplantation. Time-to-event analyses were performed using Kaplan-Meier methods and Cox proportional hazards models with Firth’s penalized partial likelihood approach. Results: P/LP variants were identified in 171 patients (39.0%) and sarcomere VUS in 159 patients (36.3%). Patients with VUS demonstrated intermediate clinical and phenotypic features between P/LP carriers and genotype-negative patients. Kaplan–Meier analysis showed a graded difference in event-free survival across variant classifications. While VUS were not independently associated with adverse outcomes when modeled as a categorical variable, increasing pathogenicity from genotype-negative to VUS and P/LP variants was associated with a stepwise increase in risk of the primary endpoint (hazard ratio 2.05, 95% confidence interval 1.11–4.16 p=0.019). Identified VUS were preferentially enriched in Z-disc and giant sarcomere scaffolding proteins. Conclusion: Sarcomere VUS represent intermediate characteristics along a continuum of sarcomere dysfunction, associated with distinct phenotypic features and clinical outcomes compared with both P/LP variants and the absence of sarcomere mutations. These findings suggest that sarcomere VUS may not be entirely clinically neutral and should be interpreted within a broader genetic and structural context in patients with HCM.
- Open Access
- 3 March 2026
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 15 (5) , e047148
Misperception in Heart Failure Phenotyping: Moving Beyond the Chamber to the Myocardium
Background: Left ventricular ejection fraction (LVEF) remains the cornerstone of heart failure (HF) phenotyping, yet it weakly correlates with outcomes and may overestimate systolic function, especially in elderly women with altered left ventricular geometry. We evaluated the limitations of conventional LVEF‐based phenotyping, assessed sex‐specific differences in left ventricular geometry, and tested whether geometry‐adjusted LVEF or left ventricular global longitudinal strain (LVGLS) improves prognostic performance. Methods: We retrospectively analyzed 3688 patients (53.0% men; median age, 70 years) hospitalized for acute HF from the STRATS‐AHF (Strain for Risk Assessment and Therapeutic Strategies in Patients With Acute Heart Failure) multicenter registry (2009–2016). Population distributions of LVEF, LVGLS, and a geometry‐adjusted index (iLVEF RWT : LVEF indexed to relative wall thickness) were compared by sex, and their prognostic value for all‐cause mortality was evaluated using Cox regression models. Results: Women showed a bimodal distribution of LVEF and a steeper age‐related increase compared with men, accompanied by higher relative wall thickness. In contrast, both iLVEF RWT and LVGLS followed unimodal Gaussian distributions across sexes. During a median follow‐up of 32.6 months (interquartile range, 12.6–55.0), 1427 patients (38.7%) died. All 3 indices predicted mortality (per 10% decrease in LVEF: hazard ratio (HR) 1.16; per 10‐unit decrease in iLVEF RWT : HR 1.05; per 1% decrease in LVGLS: HR 1.07; all P P for interaction =0.035), whereas iLVEF RWT and LVGLS remained predictive regardless of geometry. Conclusions: LVEF may overestimate systolic function in concentric remodeling, particularly in elderly women. Geometry‐adjusted iLVEF RWT and LVGLS can provide consistent physiological interpretation and robust prognostic utility.
- 3 March 2026
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 15 (5) , e047148
Open AccessMisperception in Heart Failure Phenotyping: Moving Beyond the Chamber to the Myocardium
Background: Left ventricular ejection fraction (LVEF) remains the cornerstone of heart failure (HF) phenotyping, yet it weakly correlates with outcomes and may overestimate systolic function, especially in elderly women with altered left ventricular geometry. We evaluated the limitations of conventional LVEF‐based phenotyping, assessed sex‐specific differences in left ventricular geometry, and tested whether geometry‐adjusted LVEF or left ventricular global longitudinal strain (LVGLS) improves prognostic performance. Methods: We retrospectively analyzed 3688 patients (53.0% men; median age, 70 years) hospitalized for acute HF from the STRATS‐AHF (Strain for Risk Assessment and Therapeutic Strategies in Patients With Acute Heart Failure) multicenter registry (2009–2016). Population distributions of LVEF, LVGLS, and a geometry‐adjusted index (iLVEF RWT : LVEF indexed to relative wall thickness) were compared by sex, and their prognostic value for all‐cause mortality was evaluated using Cox regression models. Results: Women showed a bimodal distribution of LVEF and a steeper age‐related increase compared with men, accompanied by higher relative wall thickness. In contrast, both iLVEF RWT and LVGLS followed unimodal Gaussian distributions across sexes. During a median follow‐up of 32.6 months (interquartile range, 12.6–55.0), 1427 patients (38.7%) died. All 3 indices predicted mortality (per 10% decrease in LVEF: hazard ratio (HR) 1.16; per 10‐unit decrease in iLVEF RWT : HR 1.05; per 1% decrease in LVGLS: HR 1.07; all P P for interaction =0.035), whereas iLVEF RWT and LVGLS remained predictive regardless of geometry. Conclusions: LVEF may overestimate systolic function in concentric remodeling, particularly in elderly women. Geometry‐adjusted iLVEF RWT and LVGLS can provide consistent physiological interpretation and robust prognostic utility.
- 20 January 2026
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 15 (2) , e045179
Longitudinal Validation of a Deep Learning Index for Aortic Stenosis Progression
Background: Aortic stenosis (AS) is a progressive disease requiring timely monitoring and intervention. While transthoracic echocardiography remains the diagnostic standard, deep learning–based approaches offer the potential for improved disease tracking. This study examined the longitudinal changes in a previously developed deep learning–derived index for AS continuum (DLi‐ASc) and assessed its prognostic association with progression to severe AS. Methods: We retrospectively analyzed 2373 patients (7371 transthoracic echocardiographies) from 2 tertiary hospitals. DLi‐ASc (scaled 0–100), derived from parasternal long‐axis and short‐axis views, was tracked longitudinally. The median follow‐up duration was 42.8 (interquartile range, 22.2–75.7) months. Results: DLi‐ASc increased in parallel with worsening AS stages ( P for trendP P P for trendP P <0.001). In Fine–Gray competing risk models, baseline DLi‐ASc was independently associated with progression to severe AS, even after adjustment for aortic valve maximal velocity or mean pressure gradient (hazard ratios per 10‐point increase, 2.38 and 2.80, respectively). Conclusions: DLi‐ASc increased in parallel with AS progression and was independently associated with severe AS progression. These findings support its role as a noninvasive imaging‐based digital marker for longitudinal AS monitoring and risk stratification.
- 20 January 2026
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 15 (2) , e045179
Longitudinal Validation of a Deep Learning Index for Aortic Stenosis Progression
Background: Aortic stenosis (AS) is a progressive disease requiring timely monitoring and intervention. While transthoracic echocardiography remains the diagnostic standard, deep learning–based approaches offer the potential for improved disease tracking. This study examined the longitudinal changes in a previously developed deep learning–derived index for AS continuum (DLi‐ASc) and assessed its prognostic association with progression to severe AS. Methods: We retrospectively analyzed 2373 patients (7371 transthoracic echocardiographies) from 2 tertiary hospitals. DLi‐ASc (scaled 0–100), derived from parasternal long‐axis and short‐axis views, was tracked longitudinally. The median follow‐up duration was 42.8 (interquartile range, 22.2–75.7) months. Results: DLi‐ASc increased in parallel with worsening AS stages ( P for trendP P P for trendP P <0.001). In Fine–Gray competing risk models, baseline DLi‐ASc was independently associated with progression to severe AS, even after adjustment for aortic valve maximal velocity or mean pressure gradient (hazard ratios per 10‐point increase, 2.38 and 2.80, respectively). Conclusions: DLi‐ASc increased in parallel with AS progression and was independently associated with severe AS progression. These findings support its role as a noninvasive imaging‐based digital marker for longitudinal AS monitoring and risk stratification.
- Open Access
- 21 December 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Multitask Artificial Intelligence–Based Electrocardiogram Tool for Preoperative Cardiac Testing in Noncardiac Surgery: Retrospective Cohort Study of Health Care Utilization and Costs (Preprint)
BACKGROUND Preoperative cardiovascular risk stratification is essential in noncardiac surgery, but conventional testing is frequently overused, increasing costs without improving outcomes. Artificial intelligence (AI)–enabled electrocardiography (ECG) may enhance perioperative risk assessment by identifying surgical candidates at very low-risk for adverse events. OBJECTIVE This study aimed to evaluate whether AI-ECG–based risk stratification could help decrease low-yield preoperative cardiovascular testing and reduce associated costs, without an observed increase in postoperative adverse outcomes, in candidates for noncardiac surgery. METHODS We retrospectively analyzed 41,218 patients (46,135 ECG-surgery pairs) undergoing noncardiac surgery at Seoul National University Bundang Hospital (2020-2021). An AI-ECG algorithm generated eight probability scores for cardiac conditions, classifying cases as low- or high-risk. Based on the performance and results of preoperative cardiovascular testing (transthoracic echocardiography, coronary computed tomography angiography, single-photon emission computed tomography, or coronary angiography), cases were classified as no advanced cardiovascular imaging, negative-test, or positive-test. The primary end point was a 30-day composite of all-cause mortality and unplanned percutaneous coronary intervention. RESULTS AI-ECG classified 92.3% (42,599/46,135) of cases as low-risk, with a composite outcome rate of 0.2% (79/42,599) vs 2.9% (101/3536) in high-risk cases. Preoperative cardiovascular testing was performed in 11.8% (5458/46,135) of cases, with only 16.3% (892/5458) yielding positive findings. In AI-ECG low-risk cases, event rates were uniformly low (0.2%-0.4%) irrespective of whether advanced cardiovascular testing was performed, whereas in high-risk cases, rates were consistently high (2.6%-3.4%). The incidence of the composite outcome was consistently higher in AI-ECG–graded high-risk cases across all European Society of Cardiology surgical risk and Revised Cardiac Risk Index strata. CONCLUSIONS In this retrospective cohort, a multitask AI-ECG identified surgical candidates at low-risk for postoperative complications, for whom advanced cardiovascular testing demonstrated low diagnostic yield. Integrating AI-ECG with conventional risk tools may offer an exploratory strategy to optimize resource use and minimize redundant testing. Prospective studies are needed to confirm the clinical and economic benefits of AI-ECG as a screening tool. CLINICALTRIAL
- 21 December 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessMultitask Artificial Intelligence–Based Electrocardiogram Tool for Preoperative Cardiac Testing in Noncardiac Surgery: Retrospective Cohort Study of Health Care Utilization and Costs (Preprint)
BACKGROUND Preoperative cardiovascular risk stratification is essential in noncardiac surgery, but conventional testing is frequently overused, increasing costs without improving outcomes. Artificial intelligence (AI)–enabled electrocardiography (ECG) may enhance perioperative risk assessment by identifying surgical candidates at very low-risk for adverse events. OBJECTIVE This study aimed to evaluate whether AI-ECG–based risk stratification could help decrease low-yield preoperative cardiovascular testing and reduce associated costs, without an observed increase in postoperative adverse outcomes, in candidates for noncardiac surgery. METHODS We retrospectively analyzed 41,218 patients (46,135 ECG-surgery pairs) undergoing noncardiac surgery at Seoul National University Bundang Hospital (2020-2021). An AI-ECG algorithm generated eight probability scores for cardiac conditions, classifying cases as low- or high-risk. Based on the performance and results of preoperative cardiovascular testing (transthoracic echocardiography, coronary computed tomography angiography, single-photon emission computed tomography, or coronary angiography), cases were classified as no advanced cardiovascular imaging, negative-test, or positive-test. The primary end point was a 30-day composite of all-cause mortality and unplanned percutaneous coronary intervention. RESULTS AI-ECG classified 92.3% (42,599/46,135) of cases as low-risk, with a composite outcome rate of 0.2% (79/42,599) vs 2.9% (101/3536) in high-risk cases. Preoperative cardiovascular testing was performed in 11.8% (5458/46,135) of cases, with only 16.3% (892/5458) yielding positive findings. In AI-ECG low-risk cases, event rates were uniformly low (0.2%-0.4%) irrespective of whether advanced cardiovascular testing was performed, whereas in high-risk cases, rates were consistently high (2.6%-3.4%). The incidence of the composite outcome was consistently higher in AI-ECG–graded high-risk cases across all European Society of Cardiology surgical risk and Revised Cardiac Risk Index strata. CONCLUSIONS In this retrospective cohort, a multitask AI-ECG identified surgical candidates at low-risk for postoperative complications, for whom advanced cardiovascular testing demonstrated low diagnostic yield. Integrating AI-ECG with conventional risk tools may offer an exploratory strategy to optimize resource use and minimize redundant testing. Prospective studies are needed to confirm the clinical and economic benefits of AI-ECG as a screening tool. CLINICALTRIAL
- Open Access
Afterload-Adjusted Strain Improves Risk Stratification Beyond Structural Remodeling in Mixed Aortic Valve Disease
Background: Mixed aortic valve disease (MAVD) exposes the left ventricle (LV) to combined pressure and volume overload, which may not be adequately captured by conventional valve-centric parameters. We evaluated an integrated echocardiographic framework incorporating ventricular geometry and afterload-adjusted myocardial performance to better characterize LV adaptation in MAVD. Methods: We retrospectively analyzed 950 patients with moderate or greater aortic stenosis categorized by aortic regurgitation (AR) severity. The integrated geometry index (IGI) was defined as the z-standardized sum of relative wall thickness and indexed LV end-diastolic volume. Afterload-adjusted strain (AAS) was calculated as absolute LV global longitudinal strain multiplied by estimated LV systolic pressure (systolic blood pressure + aortic valve mean pressure gradient), followed by z-standardization. The primary outcome was all-cause death or heart failure hospitalization; the secondary outcome was aortic valve replacement (AVR). Results: During a median follow-up of 3.5 years, 122 primary events occurred. Increasing AR severity was associated with progressive LV remodeling and higher IGI, whereas AAS remained similar across MAVD phenotypes. IGI was associated with AVR but not with the primary outcome. In contrast, lower AAS was independently associated with the primary outcome (adjusted HR 1.59 per unit decrease, 95% CI 1.30–1.96; p<0.001) and improved discrimination beyond clinical variables (AUC 0.69 vs. 0.62). These associations were consistent across MAVD phenotypes and LV remodeling patterns. Conclusions: In MAVD, afterload-adjusted myocardial performance provides independent and incremental prognostic value beyond structural remodeling. Incorporating AAS may improve risk stratification and complement conventional valve-centric assessment.
Open AccessAfterload-Adjusted Strain Improves Risk Stratification Beyond Structural Remodeling in Mixed Aortic Valve Disease
Background: Mixed aortic valve disease (MAVD) exposes the left ventricle (LV) to combined pressure and volume overload, which may not be adequately captured by conventional valve-centric parameters. We evaluated an integrated echocardiographic framework incorporating ventricular geometry and afterload-adjusted myocardial performance to better characterize LV adaptation in MAVD. Methods: We retrospectively analyzed 950 patients with moderate or greater aortic stenosis categorized by aortic regurgitation (AR) severity. The integrated geometry index (IGI) was defined as the z-standardized sum of relative wall thickness and indexed LV end-diastolic volume. Afterload-adjusted strain (AAS) was calculated as absolute LV global longitudinal strain multiplied by estimated LV systolic pressure (systolic blood pressure + aortic valve mean pressure gradient), followed by z-standardization. The primary outcome was all-cause death or heart failure hospitalization; the secondary outcome was aortic valve replacement (AVR). Results: During a median follow-up of 3.5 years, 122 primary events occurred. Increasing AR severity was associated with progressive LV remodeling and higher IGI, whereas AAS remained similar across MAVD phenotypes. IGI was associated with AVR but not with the primary outcome. In contrast, lower AAS was independently associated with the primary outcome (adjusted HR 1.59 per unit decrease, 95% CI 1.30–1.96; p<0.001) and improved discrimination beyond clinical variables (AUC 0.69 vs. 0.62). These associations were consistent across MAVD phenotypes and LV remodeling patterns. Conclusions: In MAVD, afterload-adjusted myocardial performance provides independent and incremental prognostic value beyond structural remodeling. Incorporating AAS may improve risk stratification and complement conventional valve-centric assessment.