Development of Clinically Validated Artificial Intelligence Model for Detecting ST-segment Elevation Myocardial Infarction.

STUDY OBJECTIVE: Although the importance of primary percutaneous coronary intervention has been emphasized for ST-segment elevation myocardial infarction (STEMI), the appropriateness of the cardiac catheterization laboratory activation remains suboptimal. This study aimed to develop a precise artificial intelligence (AI) model for the diagnosis of STEMI and accurate cardiac catheterization laboratory activation. METHODS: We used electrocardiography (ECG) waveform data from a prospective percutaneous coronary intervention registry in Korea in this study. Two independent board-certified cardiologists established a criterion standard (STEMI or Not STEMI) for each ECG based on corresponding coronary angiography data. We developed a deep ensemble model by combining 5 convolutional neural networks. In addition, we performed clinical validation based on a symptom-based ECG data set, comparisons with clinical physicians, and external validation. RESULTS: We used 18,697 ECGs for the model development data set, and 1,745 (9.3%) were STEMI. The AI model achieved an accuracy of 92.1%, sensitivity of 95.4%, and specificity of 91.8 %. The performances of the AI model were well balanced and outstanding in the clinical validation, comparison with clinical physicians, and the external validation. CONCLUSION: The deep ensemble AI model showed a well-balanced and outstanding performance. As visualized with gradient-weighted class activation mapping, the AI model has a reasonable explainability. Further studies with prospective validation regarding clinical benefit in a real-world setting should be warranted.

Comparative estimation of the effects of antihypertensive medications on schizophrenia occurrence: a multinational observational cohort study.

BACKGROUND: The association between antihypertensive medication and schizophrenia has received increasing attention; however, evidence of the impact of antihypertensive medication on subsequent schizophrenia based on large-scale observational studies is limited. We aimed to compare the schizophrenia risk in large claims-based US and Korea cohort of patients with hypertension using angiotensin-converting enzyme (ACE) inhibitors versus those using angiotensin receptor blockers (ARBs) or thiazide diuretics. METHODS: Adults aged 18 years who were newly diagnosed with hypertension and received ACE inhibitors, ARBs, or thiazide diuretics as first-line antihypertensive medications were included. The study population was sub-grouped based on age (> 45 years). The comparison groups were matched using a large-scale propensity score (PS)-matching algorithm. The primary endpoint was incidence of schizophrenia. RESULTS: 5,907,522; 2,923,423; and 1,971,549 patients used ACE inhibitors, ARBs, and thiazide diuretics, respectively. After PS matching, the risk of schizophrenia was not significantly different among the groups (ACE inhibitor vs. ARB: summary hazard ratio [HR] 1.15 [95% confidence interval, CI, 0.99-1.33]; ACE inhibitor vs. thiazide diuretics: summary HR 0.91 [95% CI, 0.78-1.07]). In the older subgroup, there was no significant difference between ACE inhibitors and thiazide diuretics (summary HR, 0.91 [95% CI, 0.71-1.16]). The risk for schizophrenia was significantly higher in the ACE inhibitor group than in the ARB group (summary HR, 1.23 [95% CI, 1.05-1.43]). CONCLUSIONS: The risk of schizophrenia was not significantly different between the ACE inhibitor vs. ARB and ACE inhibitor vs. thiazide diuretic groups. Further investigations are needed to determine the risk of schizophrenia associated with antihypertensive drugs, especially in people aged > 45 years.

Patient-Friendly Discharge Summaries in Korea Based on ChatGPT: Software Development and Validation.

BACKGROUND: Although discharge summaries in patient-friendly language can enhance patient comprehension and satisfaction, they can also increase medical staff workload. Using a large language model, we developed and validated software that generates a patient-friendly discharge summary. METHODS: We developed and tested the software using 100 discharge summary documents, 50 for patients with myocardial infarction and 50 for patients treated in the Department of General Surgery. For each document, three new summaries were generated using three different prompting methods (Zero-shot, One-shot, and Few-shot) and graded using a 5-point Likert Scale regarding factuality, comprehensiveness, usability, ease, and fluency. We compared the effects of different prompting methods and assessed the relationship between input length and output quality. RESULTS: The mean overall scores differed across prompting methods (4.19 ± 0.36 in Few-shot, 4.11 ± 0.36 in One-shot, and 3.73 ± 0.44 in Zero-shot; P < 0.001). Post-hoc analysis indicated that the scores were higher with Few-shot and One-shot prompts than in zero-shot prompts, whereas there was no significant difference between Few-shot and One-shot prompts. The overall proportion of outputs that scored ≥ 4 was 77.0% (95% confidence interval: 68.8-85.3%), 70.0% (95% confidence interval [CI], 61.0-79.0%), and 32.0% (95% CI, 22.9-41.1%) with Few-shot, One-shot, and Zero-shot prompts, respectively. The mean factuality score was 4.19 ± 0.60 with Few-shot, 4.20 ± 0.55 with One-shot, and 3.82 ± 0.57 with Zero-shot prompts. Input length and the overall score showed negative correlations in the Zero-shot (r = -0.437, P < 0.001) and One-shot (r = -0.327, P < 0.001) tests but not in the Few-shot (r = -0.050, P = 0.625) tests. CONCLUSION: Large-language models utilizing Few-shot prompts generally produce acceptable discharge summaries without significant misinformation. Our research highlights the potential of such models in creating patient-friendly discharge summaries for Korean patients to support patient-centered care.

Multi-Institutional Collaborative Research Using Ophthalmic Medical Image Data Standardized by Radiology Common Data Model (R-CDM).

Observational Medical Outcome Partners - Common Data Model (OMOP-CDM) is an international standard model for standardizing electronic medical record data. However, unstructured data such as medical image data which is beyond the scope of standardization by the current OMOP-CDM is difficult to be used in multi-institutional collaborative research. Therefore, we developed the Radiology-CDM (R-CDM) which standardizes medical imaging data. As a proof of concept, 737,500 Optical Coherence Tomography (OCT) data from two tertiary hospitals in South Korea is standardized in the form of R-CDM. The relationship between chronic disease and retinal thickness was analyzed by using the R-CDM. Central macular thickness and retinal nerve fiber layer (RNFL) thickness were significantly thinner in the patients with hypertension compared to the control cohort. It is meaningful in that multi-institutional collaborative research using medical image data and clinical data simultaneously can be conducted very efficiently.

Advancing Medical Imaging Research Through Standardization: The Path to Rapid Development, Rigorous Validation, and Robust Reproducibility.

ABSTRACT: Artificial intelligence (AI) has made significant advances in radiology. Nonetheless, challenges in AI development, validation, and reproducibility persist, primarily due to the lack of high-quality, large-scale, standardized data across the world. Addressing these challenges requires comprehensive standardization of medical imaging data and seamless integration with structured medical data.Developed by the Observational Health Data Sciences and Informatics community, the OMOP Common Data Model enables large-scale international collaborations with structured medical data. It ensures syntactic and semantic interoperability, while supporting the privacy-protected distribution of research across borders. The recently proposed Medical Imaging Common Data Model is designed to encompass all DICOM-formatted medical imaging data and integrate imaging-derived features with clinical data, ensuring their provenance.The harmonization of medical imaging data and its seamless integration with structured clinical data at a global scale will pave the way for advanced AI research in radiology. This standardization will enable federated learning, ensuring privacy-preserving collaboration across institutions and promoting equitable AI through the inclusion of diverse patient populations. Moreover, it will facilitate the development of foundation models trained on large-scale, multimodal datasets, serving as powerful starting points for specialized AI applications. Objective and transparent algorithm validation on a standardized data infrastructure will enhance reproducibility and interoperability of AI systems, driving innovation and reliability in clinical applications.

Comparative Effectiveness and Safety of Ticagrelor and Clopidogrel in Patients With or Without Chronic Liver Disease: A Nationwide Cohort Study.

BACKGROUND: Although the effectiveness and safety of ticagrelor versus clopidogrel may differ in patients with chronic liver disease, there is a scarcity of evidence comparing ticagrelor and clopidogrel in patients with chronic liver disease. We aimed to evaluate the risk of major adverse cardiovascular events (MACE) and major bleeding associated with ticagrelor versus clopidogrel in patients undergoing percutaneous coronary intervention (PCI) due to acute coronary syndrome by chronic liver disease status. METHODS: Using the Korean healthcare claim database, we included adult patients who underwent PCI and initiated ticagrelor or clopidogrel treatment within 7 days of an acute coronary syndrome diagnosis. Patients were classified into 2 mutually exclusive groups: patients with chronic liver disease and patients without chronic liver disease. Within each group, the hazard ratios (HRs) with 95% confidence intervals (CIs) of MACE and major bleeding associated with ticagrelor versus clopidogrel were calculated using a Cox proportional hazards model within a 1:1 propensity score (PS) matched cohort. RESULTS: The final cohort included 14,261 and 148,535 patients with and without chronic liver disease, respectively. After PS matching, the risk of MACE (with chronic liver disease, HR: 1.01, 95% CI: 0.91-1.13; without chronic liver disease, HR: 1.02, 95% CI: 0.98-1.05; P for homogeneity: 0.865) and major bleeding (with chronic liver disease, HR: 1.07, 95% CI: 0.71-1.61; without chronic liver disease, HR: 1.32, 95% CI: 1.15-1.53; P for homogeneity: 0.342) for ticagrelor versus clopidogrel do not vary with chronic liver disease status. CONCLUSIONS: Among acute coronary syndrome patients undergoing PCI, the use of ticagrelor versus clopidogrel was associated with a similar risk of MACE and an increased risk of major bleeding, but these risks did not vary with chronic liver disease status.

Comparative effectiveness of moderate-intensity statin with ezetimibe therapy versus high-intensity statin monotherapy in patients with acute coronary syndrome: a nationwide cohort study.

The long-term outcome of first-line moderate-intensity statin with ezetimibe combination therapy for secondary prevention after percutaneous coronary intervention in patients with acute coronary syndrome (ACS) compared to high-intensity statin monotherapy remains elusive. The objective of this study was to compare the effectiveness of moderate-intensity statin and ezetimibe combination therapy with high-intensity statin monotherapy. We conducted a nationwide, population-based, retrospective, cohort study of patients with ACS from 2013 to 2019. The patients using combination therapy were matched (1:1) to those using monotherapy. The primary outcome was a composite of myocardial infarction, stroke and all-cause mortality. We estimated the hazard ratios (HR) and 95% confidence intervals (CIs) using the Cox proportional hazards regression. After propensity score matching, 10,723 pairs were selected. Men accounted for 70% of the patients and 37% aged > 70 years. The primary endpoint occurred in 1297 patients (12.1%) in the combination group and in 1426 patients (13.3%) in the monotherapy group, and decreased risk (HR 0.85, 95% CI 0.78-0.92, P < 0.001) in the combination group. Among the patients with ACS, moderate-intensity statin with ezetimibe combination therapy was associated with decreased risk of adverse cardiovascular outcomes compared with high-intensity statin monotherapy in a nationwide population-based study representing routine clinical practice.

Development of Medical Imaging Data Standardization for Imaging-Based Observational Research: OMOP Common Data Model Extension.

The rapid growth of artificial intelligence (AI) and deep learning techniques require access to large inter-institutional cohorts of data to enable the development of robust models, e.g., targeting the identification of disease biomarkers and quantifying disease progression and treatment efficacy. The Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) has been designed to accommodate a harmonized representation of observational healthcare data. This study proposes the Medical Imaging CDM (MI-CDM) extension, adding two new tables and two vocabularies to the OMOP CDM to address the structural and semantic requirements to support imaging research. The tables provide the capabilities of linking DICOM data sources as well as tracking the provenance of imaging features derived from those images. The implementation of the extension enables phenotype definitions using imaging features and expanding standardized computable imaging biomarkers. This proposal offers a comprehensive and unified approach for conducting imaging research and outcome studies utilizing imaging features.

Differentiation of glioblastoma from solitary brain metastasis using deep ensembles: Empirical estimation of uncertainty for clinical reliability.

BACKGROUND AND OBJECTIVES: To develop a clinically reliable deep learning model to differentiate glioblastoma (GBM) from solitary brain metastasis (SBM) by providing predictive uncertainty estimates and interpretability. METHODS: A total of 469 patients (300 GBM, 169 SBM) were enrolled in the institutional training set. Deep ensembles based on DenseNet121 were trained on multiparametric MRI. The model performance was validated in the external test set consisting of 143 patients (101 GBM, 42 SBM). Entropy values for each input were evaluated for uncertainty measurement; based on entropy values, the datasets were split to high- and low-uncertainty groups. In addition, entropy values of out-of-distribution (OOD) data from unknown class (257 patients with meningioma) were compared to assess uncertainty estimates of the model. The model interpretability was further evaluated by localization accuracy of the model. RESULTS: On external test set, the area under the curve (AUC), accuracy, sensitivity and specificity of the deep ensembles were 0.83 (95 % confidence interval [CI] 0.76-0.90), 76.2 %, 54.8 % and 85.2 %, respectively. The performance was higher in the low-uncertainty group than in the high-uncertainty group, with AUCs of 0.91 (95 % CI 0.83-0.98) and 0.58 (95 % CI 0.44-0.71), indicating that assessment of uncertainty with entropy values ascertained reliable prediction in the low-uncertainty group. Further, deep ensembles classified a high proportion (90.7 %) of predictions on OOD data to be uncertain, showing robustness in dataset shift. Interpretability evaluated by localization accuracy provided further reliability in the "low-uncertainty and high-localization accuracy" subgroup, with an AUC of 0.98 (95 % CI 0.95-1.00). CONCLUSIONS: Empirical assessment of uncertainty and interpretability in deep ensembles provides evidence for the robustness of prediction, offering a clinically reliable model in differentiating GBM from SBM.

European and US Guideline-Based Statin Eligibility, Genetically Predicted Coronary Artery Disease, and the Risk of Major Coronary Events.

BACKGROUND: A study was designed to investigate whether the coronary artery disease polygenic risk score (CAD-PRS) may guide lipid-lowering treatment initiation as well as deferral in primary prevention beyond established clinical risk scores. METHODS AND RESULTS: Participants were 311 799 individuals from the UK Biobank free of atherosclerotic cardiovascular disease, diabetes, chronic kidney disease, and lipid-lowering treatment at baseline. Participants were categorized as statin indicated, statin indication unclear, or statin not indicated as defined by the European and US guidelines on statin use. For a median of 11.9 (11.2-12.6) years, 8196 major coronary events developed. CAD-PRS added to European-Systematic Coronary Risk Evaluation 2 (European-SCORE2) and US-Pooled Cohort Equation (US-PCE) identified 18% and 12% of statin-indication-unclear individuals whose risk of major coronary events were the same as or higher than the average risk of statin-indicated individuals and 16% and 12% of statin-indicated individuals whose major coronary event risks were the same as or lower than the average risk of statin-indication-unclear individuals. For major coronary and atherosclerotic cardiovascular disease events, CAD-PRS improved C-statistics greater among statin-indicated or statin-indication-unclear than statin-not-indicated individuals. For atherosclerotic cardiovascular disease events, CAD-PRS added to the European evaluation and US equation resulted in a net reclassification improvement of 13.6% (95% CI, 11.8-15.5) and 14.7% (95% CI, 13.1-16.3) among statin-indicated, 10.8% (95% CI, 9.6-12.0) and 15.3% (95% CI, 13.2-17.5) among statin-indication-unclear, and 0.9% (95% CI, 0.6-1.3) and 3.6% (95% CI, 3.0-4.2) among statin-not-indicated individuals. CONCLUSIONS: CAD-PRS may guide statin initiation as well as deferral among statin-indication-unclear or statin-indicated individuals as defined by the European and US guidelines. CAD-PRS had little clinical utility among statin-not-indicated individuals.

Identification of acute myocardial infarction and stroke events using the National Health Insurance Service database in Korea.

OBJECTIVES: The escalating burden of cardiovascular disease (CVD) is a critical public health issue worldwide. CVD, especially acute myocardial infarction (AMI) and stroke, is the leading contributor to morbidity and mortality in Korea. We aimed to develop algorithms for identifying AMI and stroke events from the National Health Insurance Service (NHIS) database and validate these algorithms through medical record review. METHODS: We first established a concept and definition of "hospitalization episode," taking into account the unique features of health claims-based NHIS database. We then developed first and recurrent event identification algorithms, separately for AMI and stroke, to determine whether each hospitalization episode represents a true incident case of AMI or stroke. Finally, we assessed our algorithms' accuracy by calculating their positive predictive values (PPVs) based on medical records of algorithm- identified events. RESULTS: We developed identification algorithms for both AMI and stroke. To validate them, we conducted retrospective review of medical records for 3,140 algorithm-identified events (1,399 AMI and 1,741 stroke events) across 24 hospitals throughout Korea. The overall PPVs for the first and recurrent AMI events were around 92% and 78%, respectively, while those for the first and recurrent stroke events were around 88% and 81%, respectively. CONCLUSIONS: We successfully developed algorithms for identifying AMI and stroke events. The algorithms demonstrated high accuracy, with PPVs of approximately 90% for first events and 80% for recurrent events. These findings indicate that our algorithms hold promise as an instrumental tool for the consistent and reliable production of national CVD statistics in Korea.

Cancer therapy-related cardiac dysfunction and the role of cardiovascular imaging: systemic review and opinion paper from the Working Group on Cardio-Oncology of the Korean Society of Cardiology.

Cardio-oncology is a critical field due to the escalating significance of cardiovascular toxicity as a side effect of anticancer treatments. Cancer therapy-related cardiac dysfunction (CTRCD) is a prevalent condition associated with cardiovascular toxicity, necessitating effective strategies for prediction, monitoring, management, and tracking. This comprehensive review examines the definition and risk stratification of CTRCD, explores monitoring approaches during anticancer therapy, and highlights specific cardiovascular toxicities linked to various cancer treatments. These include anthracyclines, HER2-targeted agents, vascular endothelial growth factor inhibitors, immune checkpoint inhibitors, chimeric antigen receptor T-cell therapies, and tumor-infiltrating lymphocytes therapies. Incorporating the Korean data, this review offers insights into the regional nuances in managing CTRCD. Using systematic follow-up incorporating cardiovascular imaging and biomarkers, a better understanding and management of CTRCD can be achieved, optimizing the cardiovascular health of both cancer patients and survivors.

Comparative Effectiveness of Second-line Antihyperglycemic Agents for Cardiovascular Outcomes: A Large-scale, Multinational, Federated Analysis of the LEGEND-T2DM Study.

Background: SGLT2 inhibitors (SGLT2is) and GLP-1 receptor agonists (GLP1-RAs) reduce major adverse cardiovascular events (MACE) in patients with type 2 diabetes mellitus (T2DM). However, their effectiveness relative to each other and other second-line antihyperglycemic agents is unknown, without any major ongoing head-to-head trials. Methods: Across the LEGEND-T2DM network, we included ten federated international data sources, spanning 1992-2021. We identified 1,492,855 patients with T2DM and established cardiovascular disease (CVD) on metformin monotherapy who initiated one of four second-line agents (SGLT2is, GLP1-RAs, dipeptidyl peptidase 4 inhibitor [DPP4is], sulfonylureas [SUs]). We used large-scale propensity score models to conduct an active comparator, target trial emulation for pairwise comparisons. After evaluating empirical equipoise and population generalizability, we fit on-treatment Cox proportional hazard models for 3-point MACE (myocardial infarction, stroke, death) and 4-point MACE (3-point MACE + heart failure hospitalization) risk, and combined hazard ratio (HR) estimates in a random-effects meta-analysis. Findings: Across cohorts, 16·4%, 8·3%, 27·7%, and 47·6% of individuals with T2DM initiated SGLT2is, GLP1-RAs, DPP4is, and SUs, respectively. Over 5·2 million patient-years of follow-up and 489 million patient-days of time at-risk, there were 25,982 3-point MACE and 41,447 4-point MACE events. SGLT2is and GLP1-RAs were associated with a lower risk for 3-point MACE compared with DPP4is (HR 0·89 [95% CI, 0·79-1·00] and 0·83 [0·70-0·98]), and SUs (HR 0·76 [0·65-0·89] and 0·71 [0·59-0·86]). DPP4is were associated with a lower 3-point MACE risk versus SUs (HR 0·87 [0·79-0·95]). The pattern was consistent for 4-point MACE for the comparisons above. There were no significant differences between SGLT2is and GLP1-RAs for 3-point or 4-point MACE (HR 1·06 [0·96-1·17] and 1·05 [0·97-1·13]). Interpretation: In patients with T2DM and established CVD, we found comparable cardiovascular risk reduction with SGLT2is and GLP1-RAs, with both agents more effective than DPP4is, which in turn were more effective than SUs. These findings suggest that the use of GLP1-RAs and SGLT2is should be prioritized as second-line agents in those with established CVD. Funding: National Institutes of Health, United States Department of Veterans Affairs.