Materiały źródłowe

• #1 Myocardial ischemia – Symptoms & causes – Mayo Clinic

  https://www.mayoclinic.org/diseases-conditions/myocardial-ischemia/symptoms-causes/syc-20375417

  Myocardial ischemia occurs when blood flow to your heart is reduced, preventing the heart muscle from receiving enough oxygen. The reduced blood flow is usually the result of a partial or complete blockage of your heart’s arteries (coronary arteries). […] Myocardial ischemia can lead to serious complications, including: […] Heart attack. If a coronary artery becomes completely blocked, the lack of blood and oxygen can lead to a heart attack that destroys part of the heart muscle. The damage can be serious and sometimes fatal. […] Myocardial ischemia can develop slowly as arteries become blocked over time. Or it can occur quickly when an artery becomes blocked suddenly. […] Myocardial ischemia, also called cardiac ischemia, reduces the heart muscle’s ability to pump blood. A sudden, severe blockage of one of the heart’s artery can lead to a heart attack. Myocardial ischemia might also cause serious abnormal heart rhythms.

• #2 Acute myocardial infarction prognosis prediction with reliable and interpretable artificial intelligence system

  https://pmc.ncbi.nlm.nih.gov/articles/PMC11187491/

  Predicting mortality after AMI is critical for timely and personalized interventions to reduce AMI mortality and hinder heart failure progression. However, there is a lack of RIASs that clinicians can trust. In this study, we propose the RIAS, an end-to-end framework designed to address these prevailing challenges.

• #3 Frontiers | Prediction of longitudinal clinical outcomes after acute myocardial infarction using a dynamic machine learning algorithm

  https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2024.1340022/full

  Several regression-based models for predicting outcomes after acute myocardial infarction (AMI) have been developed. However, prediction models that encompass diverse patient-related factors over time are limited. This study aimed to develop a machine learning-based model to predict longitudinal outcomes after AMI. […] The appropriate prediction of prognosis in acute myocardial infarction (AMI) is crucial for proper clinical decision-making at an individual patient level. Appropriate prediction is important for the alleviation of expenditures and effective distribution of resources. Over the last two decades, several prognosis predicting models for AMI patients have been introduced, which reflect numerous patient-level risk factors. […] The main findings from this study could be summarized as follows. First, the machine learning-based algorithms, especially the random forest approach, outperformed the conventional logistic regression-based algorithms in predicting the outcomes after AMI. In particular, the random forest model’s prediction of the primary and secondary outcomes of cardiovascular death at 1-year resulted in outstanding performance.

• #4 Development and validation of a risk prediction model for in-hospital major cardiovascular events in patients hospitalised for acute myocardial infarction | BMJ Open

  https://bmjopen.bmj.com/content/11/5/e042506

  Patients admitted to hospital with acute myocardial infarction (AMI) have considerable variability in in-hospital risks, resulting in higher demands on healthcare resources. […] Simple risk-assessment tools are important for the identification of patients with higher risk to inform clinical decisions. […] A prediction model using readily available clinical parameters was developed and externally validated to estimate risks of in-hospital MACE among patients with AMI, thereby better informing decision-making in improving clinical care. […] The model performed well on both discrimination and calibration capability, with areas under the Receiver Operating Characteristic Curve (ROC) curve of 0.85, 0.74 and 0.80, and calibration slopes of 0.98, 0.84 and 0.97 in the development sample and two external validation samples, respectively.

• #5 Development and validation of a risk prediction model for in-hospital major cardiovascular events in patients hospitalised for acute myocardial infarction | BMJ Open

  https://bmjopen.bmj.com/content/11/5/e042506

  Patients admitted to hospital with acute myocardial infarction (AMI) have considerable variability in in-hospital risks, resulting in higher demands on healthcare resources. […] Simple risk-assessment tools are important for the identification of patients with higher risk to inform clinical decisions. […] A prediction model using readily available clinical parameters was developed and externally validated to estimate risks of in-hospital MACE among patients with AMI, thereby better informing decision-making in improving clinical care. […] The model performed well on both discrimination and calibration capability, with areas under the Receiver Operating Characteristic Curve (ROC) curve of 0.85, 0.74 and 0.80, and calibration slopes of 0.98, 0.84 and 0.97 in the development sample and two external validation samples, respectively.

• #6 Transitioning to high-sensitivity troponin: 1-year mortality outcomes in patients with suspected acute coronary syndrome presenting to emergency departments | Heart

  https://heart.bmj.com/content/111/10/471

  Switching from a conventional to a high-sensitivity cardiac troponin (hs-cTn) assay enables detection of smaller amounts of myocardial damage, but the clinical benefit is unclear. […] The use of an hs-cTnI assay in an ED population with suspected ACS was associated with lower mortality at 1 year. […] In a large Emergency Department population with suspected acute coronary syndrome, shifting from a conventional to a high-sensitivity troponin assay was associated with a significant reduction in all-cause mortality at 1 year. […] This study endorses the transition to a high-sensitivity cardiac troponin I assay with sex-specific thresholds to enhance early detection and management of myocardial infarction. […] Using data from nearly 180,000 consecutive ED patients who were investigated with a troponin test for suspected ACS, switching from conventional troponin to a hs-cTnI assay was associated with a significant decrease in all-cause death at 1-year follow-up.

• #7 Myocardial Ischemia: Causes, Symptoms and Treatment

  https://my.clevelandclinic.org/health/diseases/17848-myocardial-ischemia

  Its common for people with unstable angina to have a heart attack in the next three months. Heart attacks are fatal in the first few hours for up to a third of people who have them. […] Most people who get through the first few days after a heart attack recover completely. However, 10% live less than a year after their heart attack.

• #8 Prognostic implications of myocardial ischemia during daily life in low risk patients with coronary artery disease – PubMed

  https://pubmed.ncbi.nlm.nih.gov/8436752/

  Objectives: The purpose of this study was to determine the incidence and prognostic importance of myocardial ischemia detected by ambulatory monitoring in low risk, medically managed patients with coronary artery disease. […] In patients categorized as at low risk on the basis of the results of cardiac catheterization and stress testing, silent myocardial ischemia during daily life was not uncommon, and its presence failed to predict future coronary events.

• #9 Machine learning for diagnosis of myocardial infarction using cardiac troponin concentrations | Nature Medicine

  https://www.nature.com/articles/s41591-023-02325-4

  At 1year, there were 144 (1.4%) deaths from a cardiac cause and 317 (3.1%) deaths of any cause in the external validation cohort. Compared with patients identified by CoDE-ACS at presentation as intermediate or high probability, those who were low probability of myocardial infarction had a lower rate of cardiac death and all-cause death at 30days (cardiac death: 0.1 versus 0.5 and 1.8%; all-cause death: 0.1 versus 0.9 and 2.0%, respectively) and at 1year (cardiac death: 0.3 versus 2.8 and 4.2%; all-cause death: 1.1 versus 6.1 and 6.7%, respectively; log-rank test P<0.001) [...] In patients presenting with possible acute myocardial infarction, we developed and validated the CoDE-ACS clinical decision support system using machine learning with single or serial high-sensitivity cardiac troponin measurements to inform the probability of acute myocardial infarction.

• #10 Transitioning to high-sensitivity troponin: 1-year mortality outcomes in patients with suspected acute coronary syndrome presenting to emergency departments | Heart

  https://heart.bmj.com/content/111/10/471

  Adjusted analyses revealed a 12% lower incidence of death at 30 days and a 10% reduction at 1 year with the hs-cTnI assay. […] Our findings support the adoption of high-sensitivity troponin testing for patients with suspected ACS and emphasise the potential clinical benefits of more sensitive troponin assays. […] In a large and consecutive ED population presenting with suspected ACS, switching from conventional troponin to hs-cTn assay, vs not switching, was associated with lower rates of all-cause death and new MI at 30 days and 1 year.

• #11

  https://link.springer.com/article/10.1007/s12350-013-9696-0

  The prognostic value of a normal myocardial perfusion scintigraphy (MPS) may be well described, but long-term follow-up data are sparse, and temporal variations in risk are insufficiently elucidated. […] Following a normal MPS, rates of death and hard cardiac events were low. Risk varied with age, gender, and disease history. Novel aspects of temporal risk variation suggested a general warranty period of 5 years, but less in risk groups. […] During a period of up to 10 (mean 6.2) years following normal MPS, rates of ACD (1.9%/year) and hard cardiac events (0.8%/year) were low, but higher than in the general population. Event rates varied with gender, age, and known CAD. Of particular interest, patients with known CAD, but no prior revascularization, constituted a subset with the highest and fastest growing mortality risk, reaching 6% in 4 years. Another novel finding was that events occurred relatively late, suggesting a general warranty period of 5 years, but somewhat shorter in risk groups.

• #12 Machine learning for diagnosis of myocardial infarction using cardiac troponin concentrations | Nature Medicine

  https://www.nature.com/articles/s41591-023-02325-4

  At 1year, there were 144 (1.4%) deaths from a cardiac cause and 317 (3.1%) deaths of any cause in the external validation cohort. Compared with patients identified by CoDE-ACS at presentation as intermediate or high probability, those who were low probability of myocardial infarction had a lower rate of cardiac death and all-cause death at 30days (cardiac death: 0.1 versus 0.5 and 1.8%; all-cause death: 0.1 versus 0.9 and 2.0%, respectively) and at 1year (cardiac death: 0.3 versus 2.8 and 4.2%; all-cause death: 1.1 versus 6.1 and 6.7%, respectively; log-rank test P<0.001) [...] In patients presenting with possible acute myocardial infarction, we developed and validated the CoDE-ACS clinical decision support system using machine learning with single or serial high-sensitivity cardiac troponin measurements to inform the probability of acute myocardial infarction.

• #13

  https://link.springer.com/article/10.1007/s12350-013-9696-0

  The prognostic value of a normal myocardial perfusion scintigraphy (MPS) may be well described, but long-term follow-up data are sparse, and temporal variations in risk are insufficiently elucidated. […] Following a normal MPS, rates of death and hard cardiac events were low. Risk varied with age, gender, and disease history. Novel aspects of temporal risk variation suggested a general warranty period of 5 years, but less in risk groups. […] During a period of up to 10 (mean 6.2) years following normal MPS, rates of ACD (1.9%/year) and hard cardiac events (0.8%/year) were low, but higher than in the general population. Event rates varied with gender, age, and known CAD. Of particular interest, patients with known CAD, but no prior revascularization, constituted a subset with the highest and fastest growing mortality risk, reaching 6% in 4 years. Another novel finding was that events occurred relatively late, suggesting a general warranty period of 5 years, but somewhat shorter in risk groups.

• #14 Acute myocardial infarction prognosis prediction with reliable and interpretable artificial intelligence system

  https://pmc.ncbi.nlm.nih.gov/articles/PMC11187491/

  Predicting mortality after acute myocardial infarction (AMI) is crucial for timely prescription and treatment of AMI patients, but there are no appropriate AI systems for clinicians. Our primary goal is to develop a reliable and interpretable AI system and provide some valuable insights regarding short, and long-term mortality. […] RIAS reveals the significance of statin-based medications, beta-blockers, and age on mortality regardless of time period. Lastly, we showcase reliable and interpretable results of RIAS with local explanations and counterfactual examples for several realistic scenarios. […] RIAS addresses the black-box issue in AI by providing both global and local explanations based on SHAP values and reliable predictions, interpretable as actual likelihoods. […] The proposed framework provides reliable and interpretable predictions along with counterfactual examples.

• #15 Predicting Remodeling and Outcome from Molecular Imaging of Fibroblast Activation in Patients after Acute Myocardial Infarction | Journal of Nuclear Medicine

  https://jnm.snmjournals.org/content/63/supplement_2/2217

  Early after acute myocardial infarction and reperfusion therapy, activation of fibroblasts markedly exceeds the hypoperfused infarct region and involves non-infarcted myocardium. […] A higher extent of myocardial FAP upregulation was predictive of subsequent left ventricular dysfunction. […] Thus, fibroblast activation in non-infarcted myocardial areas may contribute to adverse outcome. […] FAP-imaging may be used to establish treatment strategies to mitigate pro-fibrotic activity outside of the primary infarct region in order to prevent adverse remodeling.

• #16 Acute myocardial infarction prognosis prediction with reliable and interpretable artificial intelligence system

  https://pmc.ncbi.nlm.nih.gov/articles/PMC11187491/

  Predicting mortality after acute myocardial infarction (AMI) is crucial for timely prescription and treatment of AMI patients, but there are no appropriate AI systems for clinicians. Our primary goal is to develop a reliable and interpretable AI system and provide some valuable insights regarding short, and long-term mortality. […] RIAS reveals the significance of statin-based medications, beta-blockers, and age on mortality regardless of time period. Lastly, we showcase reliable and interpretable results of RIAS with local explanations and counterfactual examples for several realistic scenarios. […] RIAS addresses the black-box issue in AI by providing both global and local explanations based on SHAP values and reliable predictions, interpretable as actual likelihoods. […] The proposed framework provides reliable and interpretable predictions along with counterfactual examples.

• #17 Short- and long-term mortality prediction after an acute ST-elevation myocardial infarction (STEMI) in Asians: A machine learning approach | PLOS One

  https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0254894

  Conventional risk score for predicting short and long-term mortality following an ST-segment elevation myocardial infarction (STEMI) is often not population specific. […] The best machine learning model for in-hospital, 30 days, and 1-year outperformed TIMI risk score (AUC = 0.88, 95% CI: 0.8460.910; vs AUC = 0.81, 95% CI:0.7720.845, AUC = 0.90, 95% CI: 0.8700.935; vs AUC = 0.80, 95% CI: 0.7460.838, AUC = 0.84, 95% CI: 0.7980.872; vs AUC = 0.76, 95% CI: 0.7150.802, p 0.0001 for all). […] In a multi-ethnic population, patients with STEMI were better classified using the machine learning method compared to TIMI scoring. Machine learning allows for the identification of distinct factors in individual Asian populations for better mortality prediction. […] Our study is the first to show better short- and long-term mortality prediction using the ML method in a multi-ethnic Asian patient with STEMI.

• #18 Acute myocardial infarction prognosis prediction with reliable and interpretable artificial intelligence system

  https://pmc.ncbi.nlm.nih.gov/articles/PMC11187491/

  Predicting mortality after acute myocardial infarction (AMI) is crucial for timely prescription and treatment of AMI patients, but there are no appropriate AI systems for clinicians. Our primary goal is to develop a reliable and interpretable AI system and provide some valuable insights regarding short, and long-term mortality. […] RIAS reveals the significance of statin-based medications, beta-blockers, and age on mortality regardless of time period. Lastly, we showcase reliable and interpretable results of RIAS with local explanations and counterfactual examples for several realistic scenarios. […] RIAS addresses the black-box issue in AI by providing both global and local explanations based on SHAP values and reliable predictions, interpretable as actual likelihoods. […] The proposed framework provides reliable and interpretable predictions along with counterfactual examples.

• #19 Acute myocardial infarction prognosis prediction with reliable and interpretable artificial intelligence system

  https://pmc.ncbi.nlm.nih.gov/articles/PMC11187491/

  To deliver timely intervention and personalized therapy for AMI patients, it is crucial to assess prognosis and predict short-term mortality. […] Recent studies have proposed advanced machine learning (ML) techniques using electronic health record (EHR) data to assess risk and predict mortality in AMI cases. […] RIAS has resolved these issues by providing global (overall) and local (individual patient) explanations based on SHAP values and reliable predictions which can be interpreted as the actual likelihood through confidence calibration. […] The implications of RIAS can be summarized as follows: (1) expediting the development of a new AI system with a different dataset and model; (2) enabling the use of predictions as actual likelihoods; (3) facilitating systematic studies on features contributing to prognosis, both globally and locally, based on SHAP values; (4) offering what if scenarios for patient treatment applications.

• #20 Acute myocardial infarction prognosis prediction with reliable and interpretable artificial intelligence system

  https://pmc.ncbi.nlm.nih.gov/articles/PMC11187491/

  To deliver timely intervention and personalized therapy for AMI patients, it is crucial to assess prognosis and predict short-term mortality. […] Recent studies have proposed advanced machine learning (ML) techniques using electronic health record (EHR) data to assess risk and predict mortality in AMI cases. […] RIAS has resolved these issues by providing global (overall) and local (individual patient) explanations based on SHAP values and reliable predictions which can be interpreted as the actual likelihood through confidence calibration. […] The implications of RIAS can be summarized as follows: (1) expediting the development of a new AI system with a different dataset and model; (2) enabling the use of predictions as actual likelihoods; (3) facilitating systematic studies on features contributing to prognosis, both globally and locally, based on SHAP values; (4) offering what if scenarios for patient treatment applications.

• #21 Short- and long-term mortality prediction after an acute ST-elevation myocardial infarction (STEMI) in Asians: A machine learning approach | PLOS One

  https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0254894

  Conventional risk score for predicting short and long-term mortality following an ST-segment elevation myocardial infarction (STEMI) is often not population specific. […] The best machine learning model for in-hospital, 30 days, and 1-year outperformed TIMI risk score (AUC = 0.88, 95% CI: 0.8460.910; vs AUC = 0.81, 95% CI:0.7720.845, AUC = 0.90, 95% CI: 0.8700.935; vs AUC = 0.80, 95% CI: 0.7460.838, AUC = 0.84, 95% CI: 0.7980.872; vs AUC = 0.76, 95% CI: 0.7150.802, p 0.0001 for all). […] In a multi-ethnic population, patients with STEMI were better classified using the machine learning method compared to TIMI scoring. Machine learning allows for the identification of distinct factors in individual Asian populations for better mortality prediction. […] Our study is the first to show better short- and long-term mortality prediction using the ML method in a multi-ethnic Asian patient with STEMI.

• #22 Short- and long-term mortality prediction after an acute ST-elevation myocardial infarction (STEMI) in Asians: A machine learning approach | PLOS One

  https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0254894

  Overall ML model performed better than TIMI for in-hospital, 30days and 1-year AUC of (0.88vs 0.81, 0.90 vs 0.80, 0.84 vs 0.76). […] The TIMI risk score was originally developed to estimate 30 days mortality risk. […] TIMI is known to underestimate mortality risk in the lower risk group. […] Feature selection algorithms are essential in mortality prediction. […] Our results indicate that ML model predictive performance requires 15 predictors for in-hospital, 13 for 30 days and 12 for 1-year mortality prediction that performs better than models developed using a conventional statistical approach. […] ML models in this study have demonstrated higher performance compared to TIMI scoring that was extrapolated from a Caucasian cohort.

• #23 Using machine learning to predict acute myocardial infarction and ischemic heart disease in primary care cardiovascular patients | PLOS One

  https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0307099

  Early recognition, which preferably happens in primary care, is the most important tool to combat cardiovascular disease (CVD). This study aims to predict acute myocardial infarction (AMI) and ischemic heart disease (IHD) using Machine Learning (ML) in primary care cardiovascular patients. We compare the ML-models performance with that of the common SMART algorithm and discuss clinical implications. […] Our findings underline the potential of using ML for CVD prediction purposes in primary care, although the interpretation of predictors can be difficult. Clinicians, patients, and researchers might benefit from transitioning to using ML-models in support of individualized predictions by primary care physicians and subsequent (secondary) prevention. […] The results indicate that given the data, ML can accurately predict whether patients will or will not develop AMI or IHD. The model for AMI had a sensitivity of 68% (i.e., this model correctly predicts around seven out of ten AMIs) and a specificity of 100% (i.e., nearly all patients without AMI were identified correctly as such), with excellent discrimination (AUC), calibration (Brier score) and accuracy (i.e., nearly all patients who are predicted to suffer an AMI indeed suffered from one). Performance metrics for the IHD prediction model were slightly lower, but overall similar. By contrast, performance of the SMART algorithm on the same populations was substantially lower, for both AMI and IHD. This suggest that ML may be more appropriate for predicting CVD than the existing SMART algorithm, although the question remains whether the superior performance of our ML models would also be achieved when the available set of predictors is less extensive.

• #24 Markers of imminent myocardial infarction | Nature Cardiovascular Research

  https://www.nature.com/articles/s44161-024-00422-2

  We hypothesized that circulating biomarkers of the dynamic biological processes that operate in the months preceding a myocardial infarction could be measured and used to assess risk. […] We also derived a prediction model to discriminate between subsequent cases and noncases. […] The findings may have implications for both clinical primary prevention studies and further etiological studies. […] In conclusion, we identified biomarkers associated with the risk of an imminent first myocardial infarction, including BNP. […] We developed and validated a prediction model with a fair ability to discriminate between persons with and without risk of an imminent first myocardial infarction. Risk prediction in the short term may enhance the motivation of patients and doctors for primary prevention.

• #25 The Predictive Role of Cardiac Troponin Elevation Ratio Combined With Heart Function Index Model in the Prognosis of Non-ST-Segment Elevation Myocardial Infarction Patients | Hu | Cardiology Research

  https://www.cardiologyres.org/index.php/Cardiologyres/article/view/1639

  Background: Non-ST-segment elevation myocardial infarction (NSTEMI) is a common form of coronary artery disease, and its prognosis is influenced by multiple factors. This study aimed to analyze the predictive role of the combined application of cardiac troponin and cardiac function indices in NSTEMI patients prognosis. […] In NSTEMI patients, a 36.25-fold increase in cTnI/ULN, coupled with NYHA class III and IV, independently predicted prognosis. We developed a nomogram model integrating cTnI/ULN and cardiac function indices, aiding clinicians in assessing risk and implementing early interventions for improved outcomes.

• #26 Cardiac ultrasomics for acute myocardial infarction risk stratification and prediction of all-cause mortality: a feasibility study | Echo Research & Practice | Full Text

  https://echo.biomedcentral.com/articles/10.1186/s44156-024-00057-w

  Current risk stratification tools for acute myocardial infarction (AMI) have limitations, particularly in predicting mortality. […] This study utilizes cardiac ultrasound radiomics (i.e., ultrasomics) to risk stratify AMI patients when predicting all-cause mortality. […] Three phenogroups were identified: Cluster A (high-risk), Cluster B (intermediate-risk), and Cluster C (low-risk). Cluster A patients had decreased LV ejection fraction (P0.01) and global longitudinal strain (P=0.03) and increased mortality at 1-year (log rank P=0.05). […] Ultrasomics features alone (C-Index: 0.74 vs. 0.70, P=0.04) and combined with global longitudinal strain (C-Index: 0.81 vs. 0.70, P0.01) increased prediction of mortality beyond the GRACE 2.0 score. […] The concordance index was calculated for our four groups of variables: (A) GRACE 2.0 score alone, (B) GRACE+Cluster A, (C) GRACE+LV global longitudinal strain, and (D) using all three variables together.

• #27 Cardiac ultrasomics for acute myocardial infarction risk stratification and prediction of all-cause mortality: a feasibility study | Echo Research & Practice | Full Text

  https://echo.biomedcentral.com/articles/10.1186/s44156-024-00057-w

  Current risk stratification tools for acute myocardial infarction (AMI) have limitations, particularly in predicting mortality. […] This study utilizes cardiac ultrasound radiomics (i.e., ultrasomics) to risk stratify AMI patients when predicting all-cause mortality. […] Three phenogroups were identified: Cluster A (high-risk), Cluster B (intermediate-risk), and Cluster C (low-risk). Cluster A patients had decreased LV ejection fraction (P0.01) and global longitudinal strain (P=0.03) and increased mortality at 1-year (log rank P=0.05). […] Ultrasomics features alone (C-Index: 0.74 vs. 0.70, P=0.04) and combined with global longitudinal strain (C-Index: 0.81 vs. 0.70, P0.01) increased prediction of mortality beyond the GRACE 2.0 score. […] The concordance index was calculated for our four groups of variables: (A) GRACE 2.0 score alone, (B) GRACE+Cluster A, (C) GRACE+LV global longitudinal strain, and (D) using all three variables together.

• #28 Cardiac ultrasomics for acute myocardial infarction risk stratification and prediction of all-cause mortality: a feasibility study | Echo Research & Practice | Full Text

  https://echo.biomedcentral.com/articles/10.1186/s44156-024-00057-w

  When examining GRACE scoring combined with ultrasomics (Concordance: 0.74 vs. 0.70, P=0.04) and further adding LV GLS (Concordance: 0.81 vs. 0.70, P0.01), an increase in prediction of all-cause mortality is shown beyond that of the GRACE 2.0 score alone, respectively. […] We provide a proof-of-concept application of ultrasomics (i.e., cardiac ultrasound radiomics) in risk stratifying AMI patients. […] These phenogroups demonstrated significant differences in clinical outcomes, particularly in terms of all-cause mortality at 1 year. […] The developed supervised model was further applied to the external participants to assign phenogroup labels (i.e., Cluster A, B, and C).

• #29

  https://link.springer.com/article/10.1007/s12350-013-9696-0

  The prognostic value of a normal myocardial perfusion scintigraphy (MPS) may be well described, but long-term follow-up data are sparse, and temporal variations in risk are insufficiently elucidated. […] Following a normal MPS, rates of death and hard cardiac events were low. Risk varied with age, gender, and disease history. Novel aspects of temporal risk variation suggested a general warranty period of 5 years, but less in risk groups. […] During a period of up to 10 (mean 6.2) years following normal MPS, rates of ACD (1.9%/year) and hard cardiac events (0.8%/year) were low, but higher than in the general population. Event rates varied with gender, age, and known CAD. Of particular interest, patients with known CAD, but no prior revascularization, constituted a subset with the highest and fastest growing mortality risk, reaching 6% in 4 years. Another novel finding was that events occurred relatively late, suggesting a general warranty period of 5 years, but somewhat shorter in risk groups.

• #30 Predicting Remodeling and Outcome from Molecular Imaging of Fibroblast Activation in Patients after Acute Myocardial Infarction | Journal of Nuclear Medicine

  https://jnm.snmjournals.org/content/63/supplement_2/2217

  Early after acute myocardial infarction and reperfusion therapy, activation of fibroblasts markedly exceeds the hypoperfused infarct region and involves non-infarcted myocardium. […] A higher extent of myocardial FAP upregulation was predictive of subsequent left ventricular dysfunction. […] Thus, fibroblast activation in non-infarcted myocardial areas may contribute to adverse outcome. […] FAP-imaging may be used to establish treatment strategies to mitigate pro-fibrotic activity outside of the primary infarct region in order to prevent adverse remodeling.

• #31 Development and validation of a risk prediction model for in-hospital major cardiovascular events in patients hospitalised for acute myocardial infarction | BMJ Open

  https://bmjopen.bmj.com/content/11/5/e042506

  The prediction model demonstrated good discrimination and calibration ability. […] The model indicated good model discrimination and calibration ability as suggested by external validations. […] Our prediction model included nine predictors which were consistent with prior studies. […] A score greater than 50 indicates a high risk (about 50% probability) of in-hospital MACE, suggesting more attention and evidence-based treatment for these patients during their hospitalisation for AMI. […] The model and risk score performed well on discrimination and calibration capability in the development sample, and showed high consistency during external validation among populations that were enrolled 24 years later and with distinguished population characteristics. […] In conclusion, we developed and validated a useful and easily used prediction model and risk score to estimate risks of in-hospital MACE among patients hospitalised for AMI.

• #32 Development and validation of a risk prediction model for in-hospital major cardiovascular events in patients hospitalised for acute myocardial infarction | BMJ Open

  https://bmjopen.bmj.com/content/11/5/e042506

  Patients admitted to hospital with acute myocardial infarction (AMI) have considerable variability in in-hospital risks, resulting in higher demands on healthcare resources. […] Simple risk-assessment tools are important for the identification of patients with higher risk to inform clinical decisions. […] A prediction model using readily available clinical parameters was developed and externally validated to estimate risks of in-hospital MACE among patients with AMI, thereby better informing decision-making in improving clinical care. […] The model performed well on both discrimination and calibration capability, with areas under the Receiver Operating Characteristic Curve (ROC) curve of 0.85, 0.74 and 0.80, and calibration slopes of 0.98, 0.84 and 0.97 in the development sample and two external validation samples, respectively.

• #33 Development and validation of a risk prediction model for in-hospital major cardiovascular events in patients hospitalised for acute myocardial infarction | BMJ Open

  https://bmjopen.bmj.com/content/11/5/e042506

  The prediction model demonstrated good discrimination and calibration ability. […] The model indicated good model discrimination and calibration ability as suggested by external validations. […] Our prediction model included nine predictors which were consistent with prior studies. […] A score greater than 50 indicates a high risk (about 50% probability) of in-hospital MACE, suggesting more attention and evidence-based treatment for these patients during their hospitalisation for AMI. […] The model and risk score performed well on discrimination and calibration capability in the development sample, and showed high consistency during external validation among populations that were enrolled 24 years later and with distinguished population characteristics. […] In conclusion, we developed and validated a useful and easily used prediction model and risk score to estimate risks of in-hospital MACE among patients hospitalised for AMI.

• #34 Machine learning for diagnosis of myocardial infarction using cardiac troponin concentrations | Nature Medicine

  https://www.nature.com/articles/s41591-023-02325-4

  CoDE-ACS identified twice as many patients as low probability of myocardial infarction at presentation with a similar negative predictive value and fewer patients as high probability with an improved positive predictive value. […] If adopted in practice, the CoDE-ACS clinical decision support system could reduce time spent in emergency departments, prevent unnecessary hospital admission in patients unlikely to have myocardial infarction and at low risk of cardiac death, and improve the recognition and treatment of those with myocardial infarction rather than myocardial injury, with benefits for both patients and health care providers.

• #35 Using machine learning to predict acute myocardial infarction and ischemic heart disease in primary care cardiovascular patients | PLOS One

  https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0307099

  Our ML models showed high predictive performance and outperformed the existing SMART algorithm in predicting AMI and IHD in primary care cardiovascular patients. This underlines the potential of using ML for CVD prediction purposes in primary care settings. Although in this respect ML models seems promising for cardiovascular risk prediction, interpretability of the (interacting) effects of predictor variables remain an issue. Nonetheless, primary care providers, patients, and researchers may benefit from transitioning towards using ML models for support of individualized predictions and subsequent (secondary) prevention in primary care cardiovascular patients.

• #36 Myocardial ischemia – Symptoms & causes – Mayo Clinic

  https://www.mayoclinic.org/diseases-conditions/myocardial-ischemia/symptoms-causes/syc-20375417

  Treatment for myocardial ischemia involves improving blood flow to the heart muscle. Treatment may include medications, a procedure to open blocked arteries (angioplasty) or bypass surgery. […] The same lifestyle habits that can help treat myocardial ischemia can also help prevent it from developing in the first place. Leading a heart-healthy lifestyle can help keep your arteries strong, elastic and smooth, and allow for maximum blood flow.

• #37 Frontiers | Prediction of longitudinal clinical outcomes after acute myocardial infarction using a dynamic machine learning algorithm

  https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2024.1340022/full

  In AMI patients, numerous patient-related risk factors spanning the prehospitalization, in-hospitalization, and postdischarge periods exert an impact on both 1-year and 3-year outcomes. Dynamic associations among risk factors should be understood, and appropriate clinical interventions are needed after AMI. Our study suggests potential role of machine learning-based algorithm to predict adverse outcomes in patients with AMI. Further validation based on an external cohort may be needed to generalize the prediction model.

• #38 Short- and long-term mortality prediction after an acute ST-elevation myocardial infarction (STEMI) in Asians: A machine learning approach | PLOS One

  https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0254894

  Conventional risk score for predicting short and long-term mortality following an ST-segment elevation myocardial infarction (STEMI) is often not population specific. […] The best machine learning model for in-hospital, 30 days, and 1-year outperformed TIMI risk score (AUC = 0.88, 95% CI: 0.8460.910; vs AUC = 0.81, 95% CI:0.7720.845, AUC = 0.90, 95% CI: 0.8700.935; vs AUC = 0.80, 95% CI: 0.7460.838, AUC = 0.84, 95% CI: 0.7980.872; vs AUC = 0.76, 95% CI: 0.7150.802, p 0.0001 for all). […] In a multi-ethnic population, patients with STEMI were better classified using the machine learning method compared to TIMI scoring. Machine learning allows for the identification of distinct factors in individual Asian populations for better mortality prediction. […] Our study is the first to show better short- and long-term mortality prediction using the ML method in a multi-ethnic Asian patient with STEMI.

• #39 Using machine learning to predict acute myocardial infarction and ischemic heart disease in primary care cardiovascular patients | PLOS One

  https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0307099

  Our ML models showed high predictive performance and outperformed the existing SMART algorithm in predicting AMI and IHD in primary care cardiovascular patients. This underlines the potential of using ML for CVD prediction purposes in primary care settings. Although in this respect ML models seems promising for cardiovascular risk prediction, interpretability of the (interacting) effects of predictor variables remain an issue. Nonetheless, primary care providers, patients, and researchers may benefit from transitioning towards using ML models for support of individualized predictions and subsequent (secondary) prevention in primary care cardiovascular patients.

• #40 Frontiers | Prediction of longitudinal clinical outcomes after acute myocardial infarction using a dynamic machine learning algorithm

  https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2024.1340022/full

  In AMI patients, numerous patient-related risk factors spanning the prehospitalization, in-hospitalization, and postdischarge periods exert an impact on both 1-year and 3-year outcomes. Dynamic associations among risk factors should be understood, and appropriate clinical interventions are needed after AMI. Our study suggests potential role of machine learning-based algorithm to predict adverse outcomes in patients with AMI. Further validation based on an external cohort may be needed to generalize the prediction model.

• #41 Markers of imminent myocardial infarction | Nature Cardiovascular Research

  https://www.nature.com/articles/s44161-024-00422-2

  Myocardial infarction is a leading cause of death globally but is notoriously difficult to predict. […] We aimed to identify biomarkers of an imminent first myocardial infarction and design relevant prediction models. […] Forty-eight proteins, 43 metabolites, age, sex and systolic blood pressure were associated with the risk of an imminent first myocardial infarction. […] Brain natriuretic peptide was most consistently associated with the risk of imminent myocardial infarction. […] Using clinically readily available variables, we devised a prediction model for an imminent first myocardial infarction for clinical use in the general population, with good discriminatory performance and potential for motivating primary prevention efforts. […] Risk prediction in the short term based on biomarkers of IMI might tilt the scales for prevention, as the knowledge of an increased risk of a first myocardial infarction within the ensuing few months might motivate patients and doctors to consider preventive strategies.

Zobacz więcej