Prospective benchmarking of an observational analysis in the SWEDEHEART registry against the REDUCE-AMI randomized trial.

Prospective benchmarking of an observational analysis against a randomized trial increases confidence in the benchmarking process as it relies exclusively on aligning the protocol of the trial and the observational analysis, while the trials findings are unavailable. The Randomized Evaluation of Decreased Usage of Betablockers After Myocardial Infarction (REDUCE-AMI, ClinicalTrials.gov ID: NCT03278509) trial started recruitment in September 2017 and results are expected in 2024. REDUCE-AMI aimed to estimate the effect of long-term use of beta blockers on the risk of death and myocardial following a myocardial infarction with preserved left ventricular systolic ejection fraction. We specified the protocol of a target trial as similar as possible to that of REDUCE-AMI, then emulated the target trial using observational data from Swedish healthcare registries. Had everyone followed the treatment strategy as specified in the target trial protocol, the observational analysis estimated a reduction in the 5-year risk of death or myocardial infarction of 0.8 percentage points for beta blockers compared with no beta blockers; effects ranging from an absolute reduction of 4.5 percentage points to an increase of 2.8 percentage points in the risk of death or myocardial infarction were compatible with our data under conventional statistical criteria. Once results of REDUCE-AMI are published, we will compare the results of our observational analysis against those from the trial. If this prospective benchmarking is successful, it supports the credibility of additional analyses using these observational data, which can rapidly deliver answers to questions that could not be answered by the initial trial. If benchmarking proves unsuccessful, we will conduct a "postmortem" analysis to identify the reasons for the discrepancy. Prospective benchmarking shifts the investigator focus away from an endeavour to use observational data to obtain similar results as a completed randomized trial, to a systematic attempt to align the design and analysis of the trial and the observational analysis.

In patients with type 2 diabetes and recent MI, colchicine reduced a composite CV outcome at 23 mo.

SOURCE CITATION: Roubille F, Bouabdallaoui N, Kouz S, et al. Low-dose colchicine in patients with type 2 diabetes and recent myocardial infarction in the COLchicine Cardiovascular Outcomes Trial (COLCOT). Diabetes Care. 2024;47:467-470. 38181203.

Comprehensive bioinformatics analytics and in vivo validation reveal SLC31A1 as an emerging diagnostic biomarker for acute myocardial infarction.

BACKGROUND: Globally, Acute Myocardial Infarction (AMI) is a common cause of heart failure (HF), which has been a leading cause of mortality resulting from non-communicable diseases. On the other hand, increasing evidence suggests that the role of energy production within the mitochondria strongly links to the development and progression of heart diseases, while Cuproptosis, a newly identified cell death mechanism, has not yet been comprehensively analyzed from the aspect of cardiovascular medicine. MATERIALS AND METHODS: 8 transcriptome profiles curated from the GEO database were integrated, from which a diagnostic model based on the Stacking algorithm was established. The efficacy of the model was evaluated in a multifaced manner (i.e., by Precision-Recall curve, Receiver Operative Characteristic curve, etc.). We also sequenced our animal models at the bulk RNA level and conducted qPCR and immunohistochemical staining, with which we further validated the expression of the key contributor gene to the model. Finally, we explored the immune implications of the key contributor gene. RESULTS: A merged machine learning model containing 4 Cuproptosis-related genes (i.e., PDHB, CDKN2A, GLS, and SLC31A1) for robust AMI diagnosis was developed, in which SLC31A1 served as the key contributor. Through in vivo modeling, we validated the aberrant overexpression of SLC31A1 in AMI. Besides, further transcriptome analysis revealed that its high expression was correlated with significant potential immunological implications in the infiltration of many immune cell types, especially monocyte. CONCLUSIONS: We constructed an AMI diagnostic model based on Cuproptosis-related genes and validated the key contributor gene in animal modeling. We also analyzed the effects on the immune system for its overexpression in AMI.

Risk of Heart Disease in Patients With Amputation: A Nationwide Cohort Study in South Korea.

BACKGROUND: Amputation confers disabilities upon patients and is linked to substantial morbidity and death attributed to heart disease. While some studies have focused on traumatic amputees in veterans, few studies have focused on traumatic amputees within the general population. Therefore, the present study aimed to assess the risk of heart disease in patients with traumatic amputation with disability within the general population using a large-scale nationwide population-based cohort. METHODS AND RESULTS: We used data from the Korean National Health Insurance System. A total of 22 950 participants with amputation were selected with 1:3 age, sex-matched controls between 2010 and 2018. We used Cox proportional hazard models to calculate the risk of myocardial infarction, heart failure, and atrial fibrillation among amputees. Participants with amputation had a higher risk of myocardial infarction (adjusted hazard ratio [aHR], 1.30 [95% CI, 1.14-1.47]), heart failure (aHR, 1.27 [95% CI, 1.17-1.38]), and atrial fibrillation (aHR, 1.17 [95% CI, 1.03-1.33]). The risks of myocardial infarction and heart failure were further increased by the presence of disability (aHR, 1.43 [95% CI, 1.04-1.95]; and aHR, 1.38 [95% CI, 1.13-1.67], respectively). CONCLUSIONS: We demonstrate an increased risk of myocardial infarction, heart failure, and atrial fibrillation among individuals with amputation, and the risk further increased in those with disabilities. Clinicians should pay attention to the increased risk for heart disease in patients with amputation.

Construction and validation of nomogram model for predicting the risk of ventricular arrhythmia after emergency PCI in patients with acute myocardial infarction.

OBJECTIVE: To make predictions about the risk of MVA (Malignant Ventricular Arrhythmia) after primary PCI (Percutaneous Coronary Intervention) in patients with AMI (Acute Myocardial Infarction) through constructing and validating the Nomogram model. METHODS: 311 AMI patients who suffered from emergency PCI in Hefei Second People's Hospital from January 2020 to May 2023 were selected as the training set; 253 patients suffering from the same symptom in Hefei First People's Hospital during the same period were selected as the validation set. Risk factors were further screened by means of multivariate logistic and stepwise regression. The nomogram model was constructed, and then validated by using C-index, ROC curve, decision curve and calibration curve. RESULTS: Multivariate logistic analysis revealed that urea, systolic pressure, hypertension, Killip class II-IV, as well as LVEF (Left Ventricular Ejection Fraction) were all unrelated hazards for MVA after emergency PCI for AMI (P<0.05); a risk prediction nomogram model was constructed. The C-index was calculated to evaluate the predictive ability of the model. Result showed that the index of the training and the validation set was 0.783 (95% CI: 0.726-0.84) and 0.717 (95% CI: 0.65-0.784) respectively, which suggested that the model discriminated well. Meanwhile, other tools including ROC curve, calibration curve and decision curve also proved that this nomogram plays an effective role in forecasting the risk for MVA after PCI in AMI patients. CONCLUSIONS: The study successfully built the nomogram model and made predictions for the development of MVA after PCI in AMI patients.

Cardiovascular Risk Estimation Is Suboptimal in People With HIV.

BACKGROUND: Established cardiovascular disease (CVD) risk prediction functions may not accurately predict CVD risk in people with HIV. We assessed the performance of 3 CVD risk prediction functions in 2 HIV cohorts. METHODS AND RESULTS: CVD risk scores were calculated in the Mass General Brigham and Kaiser Permanente Northern California HIV cohorts, using the American College of Cardiology/American Heart Association atherosclerotic CVD function, the FHS (Framingham Heart Study) hard coronary heart disease function and the Framingham Heart Study hard CVD function. Outcomes were myocardial infarction or coronary death for FHS hard coronary heart disease function; and myocardial infarction, stroke, or coronary death for American College of Cardiology/American Heart Association and FHS hard CVD function. We calculated regression coefficients and assessed discrimination and calibration by sex; predicted to observed risk of outcome was also compared. In the combined cohort of 9412, 158 (1.7%) had a coronary heart disease event, and 309 (3.3%) had a CVD event. Among women, CVD risk was generally underestimated by all 3 risk functions. Among men, CVD risk was underestimated by the American College of Cardiology/American Heart Association and FHS hard CVD function, but overestimated by the FHS hard coronary heart disease function. Calibration was poor for women using the FHS hard CVD function and for men using all functions. Discrimination in all functions was good for women (c-statistics ranging from 0.78 to 0.90) and moderate for men (c-statistics ranging from 0.71 to 0.72). CONCLUSIONS: Established CVD risk prediction functions generally underestimate risk in people with HIV. Differences in model performance by sex underscore the need for both HIV-specific and sex-specific functions. Development of CVD risk prediction models tailored to HIV will enhance care for aging people with HIV.

Trends in Survival After First Myocardial Infarction in People With Diabetes.

BACKGROUND: The aim of this study was to investigate temporal trends in survival and subsequent cardiovascular events in a nationwide myocardial infarction population with and without diabetes. METHODS AND RESULTS: Between 2006 and 2020, we identified 2527 individuals with type 1 diabetes, 48 321 individuals with type 2 diabetes and 243 170 individuals without diabetes with first myocardial infarction in national health care registries. Outcomes were trends in all-cause death after 30 and 365 days, cardiovascular death and major adverse cardiovascular events (ie, nonfatal stroke, nonfatal myocardial infarction, cardiovascular death, and heart failure hospitalization). Pseudo-observations were used to estimate the mortality risk, with 95% CIs, using linear regression, adjusted for age and sex. Individuals with type 1 diabetes were younger (62±12.2 years) and more often women (43.6%) compared with individuals with type 2 diabetes (75±10.8 years; women, 38.1%), and individuals without diabetes (73±13.2 years; women, 38.4%). Early death decreased in people without diabetes from 23.1% to 17.5%, (annual change -0.48% [95% CI, -0.52% to -0.44%]) and in people with type 2 diabetes from 22.6% to 19.3% (annual change, -0.33% [95% CI, -0.43% to -0.24%]), with no such significant trend in people with type 1 diabetes from 23.8% to 21.7% (annual change, -0.18% [95% CI, -0.53% to 0.17%]). Similar trends were observed with regard to 1-year death, cardiovascular death, and major adverse cardiovascular events. CONCLUSIONS: During the past 15 years, the trend in survival and major adverse cardiovascular events in people with first myocardial infarction without diabetes and with type 2 diabetes have improved significantly. In contrast, a similar improvement was not seen in people with type 1 diabetes.

Association of Lipoprotein (a) and Standard Modifiable Cardiovascular Risk Factors With Incident Myocardial Infarction: The Mass General Brigham Lp(a) Registry.

BACKGROUND: Lipoprotein (a) [Lp(a)] is a robust predictor of coronary heart disease outcomes, with targeted therapies currently under investigation. We aimed to evaluate the association of high Lp(a) with standard modifiable risk factors (SMuRFs) for incident first acute myocardial infarction (AMI). METHODS AND RESULTS: This retrospective study used the Mass General Brigham Lp(a) Registry, which included patients aged ≥18 years with an Lp(a) measurement between 2000 and 2019. Exclusion criteria were severe kidney dysfunction, malignant neoplasm, and prior known atherosclerotic cardiovascular disease. Diabetes, dyslipidemia, hypertension, and smoking were considered SMuRFs. High Lp(a) was defined as >90th percentile, and low Lp(a) was defined as <50th percentile. The primary outcome was fatal or nonfatal AMI. A combination of natural language processing algorithms, International Classification of Diseases (ICD) codes, and laboratory data was used to identify the outcome and covariates. A total of 6238 patients met the eligibility criteria. The median age was 54 (interquartile range, 43-65) years, and 45% were women. Overall, 23.7% had no SMuRFs, and 17.8% had ≥3 SMuRFs. Over a median follow-up of 8.8 (interquartile range, 4.2-12.8) years, the incidence of AMI increased gradually, with higher number of SMuRFs among patients with high (log-rank P=0.031) and low Lp(a) (log-rank P<0.001). Across all SMuRF subgroups, the incidence of AMI was significantly higher for patients with high Lp(a) versus low Lp(a). The risk of high Lp(a) was similar to having 2 SMuRFs. Following adjustment for confounders and number of SMuRFs, high Lp(a) remained significantly associated with the primary outcome (hazard ratio, 2.9 [95% CI, 2.0-4.3]; P<0.001). CONCLUSIONS: Among patients with no prior atherosclerotic cardiovascular disease, high Lp(a) is associated with significantly higher risk for first AMI regardless of the number of SMuRFs.

Melatonin alleviates myocardial dysfunction through inhibition of endothelial-to-mesenchymal transition via the NF-κB pathway.

Endothelial-to-mesenchymal transition (EndMT) is a complex biological process of cellular transdifferentiation by which endothelial cells (ECs) lose their characteristics and acquire mesenchymal properties, leading to cardiovascular remodeling and complications in the adult cardiovascular diseases environment. Melatonin is involved in numerous physiological and pathological processes, including aging, and has anti-inflammatory and antioxidant activities. This molecule is an effective therapeutic candidate for preventing oxidative stress, regulating endothelial function, and maintaining the EndMT balance to provide cardiovascular protection. Although recent studies have documented improved cardiac function by melatonin, the mechanism of action of melatonin on EndMT remains unclear. The present study investigated the effects of melatonin on induced EndMT by transforming growth factor-ß2/interleukin-1ß in both in vivo and in vitro models. The results revealed that melatonin reduced the migratory ability and reactive oxygen species levels of the cells and ameliorated mitochondrial dysfunction in vitro. Our findings indicate that melatonin prevents endothelial dysfunction and inhibits EndMT by activating related pathways, including nuclear factor kappa B and Smad. We also demonstrated that this molecule plays a crucial role in restoring cardiac function by regulating the EndMT process in the ischemic myocardial condition, both in vessel organoids and myocardial infarction (MI) animal models. In conclusion, melatonin is a promising agent that attenuates EC dysfunction and ameliorates cardiac damage compromising the EndMT process after MI.

DJ-1 preserves ischemic postconditioning-induced cardioprotection in STZ-induced type 1 diabetic rats: role of PTEN and DJ-1 subcellular translocation.

BACKGROUND: Ischemic postconditioning (IPostC) has been reported as a promising method for protecting against myocardial ischemia-reperfusion (MI/R) injury. Our previous study found that the infarct-limiting effect of IPostC is abolished in the heart of diabetes whose cardiac expression of DJ-1 (also called PARK7, Parkinsonism associated deglycase) is reduced. However, the role and in particular the underlying mechanism of DJ-1 in the loss of sensitivity to IPostC-induced cardioprotection in diabetic hearts remains unclear. METHODS: Streptozotocin-induced type 1 diabetic rats were subjected to MI/R injury by occluding the left anterior descending artery (LAD) and followed by reperfusion. IPostC was induced by three cycles of 10s of reperfusion and ischemia at the onset of reperfusion. AAV9-CMV-DJ-1, AAV9-CMV-C106S-DJ-1 or AAV9-DJ-1 siRNA were injected via tail vein to either over-express or knock-down DJ-1 three weeks before inducing MI/R. RESULTS: Diabetic rats subjected to MI/R exhibited larger infarct area, more severe oxidative injury concomitant with significantly reduced cardiac DJ-1 expression and increased PTEN expression as compared to non-diabetic rats. AAV9-mediated cardiac DJ-1 overexpression, but not the cardiac overexpression of DJ-1 mutant C106S, restored IPostC-induced cardioprotection and this effect was accompanied by increased cytoplasmic DJ-1 translocation toward nuclear and mitochondrial, reduced PTEN expression, and increased Nrf-2/HO-1 transcription. Our further study showed that AAV9-mediated targeted DJ-1 gene knockdown aggravated MI/R injury in diabetic hearts, and this exacerbation of MI/R injury was partially reversed by IPostC in the presence of PTEN inhibition or Nrf-2 activation. CONCLUSIONS: These findings suggest that DJ-1 preserves the cardioprotective effect of IPostC against MI/R injury in diabetic rats through nuclear and mitochondrial DJ-1 translocation and that inhibition of cardiac PTEN and activation of Nrf-2/HO-1 may represent the major downstream mechanisms whereby DJ-1 preserves the cardioprotective effect of IPostC in diabetes.

El shock cardiogénico como problema de salud. Fisiología, clasificación y detección / Cardiogenic shock as a health issue: Physiology, classification, and detection

El shock cardiogénico (SC) es un síndrome heterogéneo con elevada mortalidad y creciente incidencia. Se trata de una situación en la que existe un desequilibrio entre las necesidades tisulares de oxígeno y la capacidad del sistema cardiovascular para satisfacerlas debido a una disfunción cardiaca aguda. Históricamente, los síndromes coronarios agudos han sido la causa principal de SC; sin embargo, los casos no isquémicos han aumentado en incidencia. Su fisiopatología implica el daño isquémico del miocardio, una respuesta tanto simpática como del sistema renina-angiotensina-aldosterona e inflamatoria, que perpetúan la situación de hipoperfusión tisular conduciendo finalmente a la disfunción multiorgánica. La caracterización de los pacientes con SC mediante una valoración triaxial y la universalización de la escala SCAI ha permitido una estandarización de la estratificación de la gravedad del SC que, sumada a la detección precoz y el enfoque Hub and Spoke, podrían contribuir a mejorar el pronóstico de los pacientes en SC. (AU)

Cardiogenic shock (CS) is a heterogeneous syndrome with high mortality and increasing incidence. It is a condition where there is an imbalance between tissue oxygen demands and the cardiovascular system's capacity to meet them due to acute cardiac dysfunction. Historically, acute coronary syndromes have been the primary cause of CS; however, non-ischemic cases have seen a rise in incidence. Its pathophysiology involves myocardial ischemic damage, a sympathetic, renin–angiotensin–aldosterone system, and inflammatory response, perpetuating the situation of tissue hypoperfusion, ultimately leading to multiorgan dysfunction. Characterizing CS patients through a triaxial assessment and the widespread use of the SCAI scale has allowed standardization of CS severity stratification, which, coupled with early detection and the “Hub and Spoke” approach, could contribute to improve the prognosis of CS patients. (AU)

[A transcriptomic analysis of correlation between mitochondrial function and energy metabolism remodeling in mice with myocardial fibrosis following myocardial infarction].

OBJECTIVE: To investigate the changes of mitochondrial respiratory function during myocardial fibrosis in mice with myocardial infarction (MI) and its correlation with the increase of glycolytic flux. METHODS: Forty C57BL/6N mice were randomized into two equal groups to receive sham operation or ligation of the left anterior descending coronary artery to induce acute MI. At 28 days after the operation, 5 mice from each group were euthanized and left ventricular tissue samples were collected for transcriptomic sequencing. FPKM method was used to calculate gene expression levels to identify the differentially expressed genes (DEGs) in MI mice, which were analyzed using GO and KEGG databases to determine the pathways affecting the disease process. Heat maps were drawn to show the differential expressions of the pathways and the related genes in the enrichment analysis. In primary cultures of neonatal mouse cardiac fibroblasts (CFs), the changes in mitochondrial respiration and glycolysis levels in response to treatment with the pro-fibrotic agonist TGF-ß1 were analyzed using Seahorse experiment. RESULTS: The mouse models of MI showed significantly increased diastolic and systolic left ventricular diameter (P < 0.05) and decreased left ventricular ejection fraction (P < 0.0001). A total of 124 up-regulated and 106 down-regulated DEGs were identified in the myocardial tissues of MI mice, and GO and KEGG enrichment analysis showed that these DEGs were significantly enriched in fatty acid metabolism, organelles and other metabolic pathways and in the mitochondria. Heat maps revealed fatty acid beta oxidation, mitochondrial dysfunction and increased glycolysis levels in MI mice. In the primary culture of CFs, treatment with TGF-ß1 significantly reduced the basal and maximum respiratory levels and increased the basal and maximum glycolysis levels (P < 0.0001). CONCLUSION: During myocardial fibrosis, energy metabolism remodeling occurs in the CFs, manifested by lowered mitochondrial function and increased energy generation through glycolysis.

Association between physical activity changes and incident myocardial infarction after ischemic stroke: a nationwide population-based study.

BACKGROUND: The impact of changes in physical activity after ischemic stroke (IS) on the subsequent myocardial infarction (MI) risk is not fully understood. We aimed to investigate the effects of changes in physical activity on the risk of MI after acute IS using data from the Korean National Health Insurance Services Database. METHODS: 224,764 patients newly diagnosed with IS between 2010 and 2016 who underwent two serial biannual health checkups were included. The participants were divided into four categories according to changes in their physical activity: persistent non-exercisers, new exercisers, exercise dropouts, and exercise maintainers. The primary outcome was a new diagnosis of incident MI. Multivariable Cox proportional models were used to assess the effects of changes in exercise habits on the risk of MI. RESULTS: After a median of 4.25 years of follow-up, 6,611 (2.94%) MI cases were observed. After adjusting for confounders, new exercisers and exercise maintainers were significantly associated with a lower risk of incident MI than persistent non-exercisers (aHR, 0.849; 95% CI, 0.792-0.911; P-value < 0.001; and aHR, 0.746; 95% CI, 0.696-0.801; P-value < 0.001, respectively). Effects were consistent across sexes, more pronounced in those > 65 years. Notably, any level of physical activity after stroke was associated with a reduced MI risk compared to no exercise. CONCLUSIONS: In this nationwide cohort study, commencing or sustaining physical activity after an IS corresponded to a diminished likelihood of subsequent MI development. Advocating physical activity in ambulatory stroke survivors could potentially attenuate the prospective risk of MI.

Head-to-head comparison of relevant cell sources of small extracellular vesicles for cardiac repair: Superiority of embryonic stem cells.

Small extracellular vesicles (sEV) derived from various cell sources have been demonstrated to enhance cardiac function in preclinical models of myocardial infarction (MI). The aim of this study was to compare different sources of sEV for cardiac repair and determine the most effective one, which nowadays remains limited. We comprehensively assessed the efficacy of sEV obtained from human primary bone marrow mesenchymal stromal cells (BM-MSC), human immortalized MSC (hTERT-MSC), human embryonic stem cells (ESC), ESC-derived cardiac progenitor cells (CPC), human ESC-derived cardiomyocytes (CM), and human primary ventricular cardiac fibroblasts (VCF), in in vitro models of cardiac repair. ESC-derived sEV (ESC-sEV) exhibited the best pro-angiogenic and anti-fibrotic effects in vitro. Then, we evaluated the functionality of the sEV with the most promising performances in vitro, in a murine model of MI-reperfusion injury (IRI) and analysed their RNA and protein compositions. In vivo, ESC-sEV provided the most favourable outcome after MI by reducing adverse cardiac remodelling through down-regulating fibrosis and increasing angiogenesis. Furthermore, transcriptomic, and proteomic characterizations of sEV derived from hTERT-MSC, ESC, and CPC revealed factors in ESC-sEV that potentially drove the observed functions. In conclusion, ESC-sEV holds great promise as a cell-free treatment for promoting cardiac repair following MI.

Ventricular Pseudoaneurysm and Free Wall Rupture After Acute Myocardial Infarction: JACC Focus Seminar 4/5.

Postinfarction ventricular free-wall rupture is a rare mechanical complication, accounting for <0.01% to 0.02% of cases. As an often-catastrophic event, death typically ensues within minutes due to sudden massive hemopericardium resulting in cardiac tamponade. Early recognition is pivotal, and may allow for pericardial drainage and open surgical repair as the only emergent life-saving procedure. In cases of contained rupture with pseudo-aneurysm (PSA) formation, hospitalization with subsequent early surgical intervention is warranted. Not uncommonly, PSA may go unrecognized in asymptomatic patients and diagnosed late during subsequent cardiac imaging. In these patients, the unsettling risk of complete rupture demands early surgical repair. Novel developments, in the field of transcatheter-based therapies and multimodality imaging, have enabled percutaneous PSA repair as a feasible alternate strategy for patients at high or prohibitive surgical risk. Contemporary advancements in the diagnosis and treatment of postmyocardial infarction ventricular free-wall rupture and PSA are provided in this review.

Ventricular Septal Rupture After Myocardial Infarction: JACC Focus Seminar 3/5.

Ventricular septal rupture remains a dreadful complication of acute myocardial infarction. Although less commonly observed than during the prethrombolytic era, the condition remains complex and is often associated with refractory cardiogenic shock and death. Corrective surgery, although superior to medical treatment, has been associated with high perioperative morbidity and mortality. Transcatheter closure techniques are less invasive to surgery and offer a valuable alternative, particularly in patients with cardiogenic shock. In these patients, percutaneous mechanical circulatory support represents a novel opportunity for immediate stabilization and preserved end-organ function. Multimodality imaging can identify favorable septal anatomy for the most appropriate type of repair. The heart team approach will define optimal timing for surgery vs percutaneous repair. Emerging concepts are proposed for a deferred treatment approach, including orthotropic heart transplantation in ideal candidates. Finally, for futile situations, palliative care experts and a medical ethics team will provide the best options for end-of-life clinical decision making.

Postmyocardial Infarction Ventricular Aneurysm: JACC Focus Seminar 5/5.

Ventricular aneurysm represents a rare complication of transmural acute myocardial infarction, although other cardiac, congenital, or metabolic diseases may also predispose to such condition. Ventricular expansion includes all the cardiac layers, usually with a large segment involved. Adverse events include recurrent angina, reduced ventricular stroke volume with congestive heart failure, mitral regurgitation, thromboembolism, and ventricular arrhythmias. Multimodality imaging is paramount to provide comprehensive assessment, allowing for appropriate therapeutic decision-making. When indicated, surgical intervention remains the gold standard, although additional therapy (heart failure, anticoagulation, and advanced antiarrhythmic treatment) might be required. However, the STICH (Surgical Treatment for Ischemic Heart Failure) trial did not show any advantage from adding surgical ventricular reconstruction to coronary artery bypass surgery in terms of survival, rehospitalization or symptoms, compared with revascularization alone. Finally, implantable cardiac defibrillator may reduce the risk of fatal arrhythmias.

Development and Validation of an Explainable Deep Learning Model to Predict In-Hospital Mortality for Patients With Acute Myocardial Infarction: Algorithm Development and Validation Study.

BACKGROUND: Acute myocardial infarction (AMI) is one of the most severe cardiovascular diseases and is associated with a high risk of in-hospital mortality. However, the current deep learning models for in-hospital mortality prediction lack interpretability. OBJECTIVE: This study aims to establish an explainable deep learning model to provide individualized in-hospital mortality prediction and risk factor assessment for patients with AMI. METHODS: In this retrospective multicenter study, we used data for consecutive patients hospitalized with AMI from the Chongqing University Central Hospital between July 2016 and December 2022 and the Electronic Intensive Care Unit Collaborative Research Database. These patients were randomly divided into training (7668/10,955, 70%) and internal test (3287/10,955, 30%) data sets. In addition, data of patients with AMI from the Medical Information Mart for Intensive Care database were used for external validation. Deep learning models were used to predict in-hospital mortality in patients with AMI, and they were compared with linear and tree-based models. The Shapley Additive Explanations method was used to explain the model with the highest area under the receiver operating characteristic curve in both the internal test and external validation data sets to quantify and visualize the features that drive predictions. RESULTS: A total of 10,955 patients with AMI who were admitted to Chongqing University Central Hospital or included in the Electronic Intensive Care Unit Collaborative Research Database were randomly divided into a training data set of 7668 (70%) patients and an internal test data set of 3287 (30%) patients. A total of 9355 patients from the Medical Information Mart for Intensive Care database were included for independent external validation. In-hospital mortality occurred in 8.74% (670/7668), 8.73% (287/3287), and 9.12% (853/9355) of the patients in the training, internal test, and external validation cohorts, respectively. The Self-Attention and Intersample Attention Transformer model performed best in both the internal test data set and the external validation data set among the 9 prediction models, with the highest area under the receiver operating characteristic curve of 0.86 (95% CI 0.84-0.88) and 0.85 (95% CI 0.84-0.87), respectively. Older age, high heart rate, and low body temperature were the 3 most important predictors of increased mortality, according to the explanations of the Self-Attention and Intersample Attention Transformer model. CONCLUSIONS: The explainable deep learning model that we developed could provide estimates of mortality and visual contribution of the features to the prediction for a patient with AMI. The explanations suggested that older age, unstable vital signs, and metabolic disorders may increase the risk of mortality in patients with AMI.