Determinants of In-Hospital Mortality After Percutaneous Coronary Intervention: A Machine Learning Approach

Comparison of machine learning models with conventional statistical methods for prediction of percutaneous coronary intervention outcomes: a systematic review and meta-analysis

INTRODUCTION

Percutaneous coronary intervention (PCI) has been the main treatment of coronary artery disease (CAD). In this review, we aimed to compare the performance of machine learning (ML) vs. logistic regression (LR) models in predicting different outcomes after PCI.

METHODS

Studies using ML or deep learning (DL) models to predict mortality, MACE, in-hospital bleeding, and acute kidney injury (AKI) after PCI or primary PCI were included. Articles were excluded if they did not provide a c-statistic, solely used ML models for feature selection, were not in English, or only used logistic or LASSO regression models. Best-performing ML and LR-based models (LR model or conventional risk score) from the same studies were pooled separately to directly compare the performance of ML versus LR. Risk of bias was assessed using the PROBAST and CHARMS checklists.

RESULTS

A total of 59 studies were included. Meta-analysis showed that ML models resulted in a higher c-statistic compared to LR in long-term mortality (0.84 vs. 0.79, P-value = 0.178), short-term mortality (0.91 vs. 0.85, P = 0.149), bleeding (0.81 vs. 0.77 P = 0.261), acute kidney injury (AKI; 0.81 vs. 0.75, P = 0.373), and major adverse cardiac events (MACE; 0.85 vs. 0.75, P = 0.406). PROBAST analysis showed that 93% of long-term mortality, 70% of short-term mortality, 89% of bleeding, 69% of AKI, and 86% of MACE studies had a high risk of bias.

CONCLUSION

No statistical significance existed between ML and LR model. In addition, the high risk of bias in ML studies and complexity in interpretation undermines their validity and may impact their adaption in a clinical settings.

Predicting In-Hospital Mortality in Patients With Acute Myocardial Infarction: A Comparison of Machine Learning Approaches

BACKGROUND

Acute myocardial infarction (AMI) remains a leading global cause of mortality. This study explores predictors of in-hospital mortality among AMI patients using advanced machine learning (ML) techniques.

METHODS

Data from 7422 AMI patients treated with percutaneous coronary intervention (PCI) at Tehran Heart Center (2015-2021) were analyzed. Fifty-eight clinical, demographic, and laboratory variables were evaluated. Seven ML algorithms, including Random Forest (RF), logistic regression with LASSO, and XGBoost, were implemented. The data set was divided into training (70%) and testing (30%) subsets, with fivefold cross-validation. The class imbalance was addressed using the synthetic minority oversampling technique (SMOTE). Model predictions were interpreted using SHapley Additive exPlanations (SHAP).

RESULTS

In-hospital mortality occurred in 129 patients (1.74%). RF achieved the highest predictive performance, with an area under the curve (AUC) of 0.924 (95% CI 0.893-0.954), followed by XGBoost (AUC 0.905) and logistic regression with LASSO (AUC 0.893). Sensitivity analysis in STEMI patients confirmed RF's robust performance (AUC 0.900). SHAP analysis identified key predictors, including lower left ventricular ejection fraction (LVEF; 33.24% vs. 43.46% in survivors, p < 0.001), higher fasting blood glucose (190.38 vs. 132.29 mg/dL, p < 0.001), elevated serum creatinine, advanced age (70.92 vs. 61.88 years, p < 0.001), and lower LDL-C levels. Conversely, BMI showed no significant association (p = 0.456).

CONCLUSION

ML algorithms, particularly RF, effectively predict in-hospital mortality in AMI patients, highlighting critical predictors such as LVEF and biochemical markers. These insights offer valuable tools for enhancing clinical decision-making and improving patient outcomes.

Predictive performance of machine learning models for kidney complications following coronary interventions: a systematic review and meta-analysis

BACKGROUND

Acute kidney injury (AKI) and contrast-induced nephropathy (CIN) are common complications following percutaneous coronary intervention (PCI) or coronary angiography (CAG), presenting significant clinical challenges. Machine learning (ML) models offer promise for improving patient outcomes through early detection and intervention strategies.

METHODS

A comprehensive literature search following PRISMA guidelines was conducted in PubMed, Scopus, and Embase from inception to June 11, 2024. Study characteristics, ML models, performance metrics (AUC, accuracy, sensitivity, specificity, precision), and risk-of-bias assessment using the PROBAST tool were extracted. Statistical analysis used a random-effects model to pool AUC values, with heterogeneity assessed via the I2 statistic.

RESULTS

From 431 initial studies, 14 met the inclusion criteria. Gradient Boosting Machine (GBM) and Support Vector Machine (SVM) models showed the highest pooled AUCs of 0.87 (95% CI: 0.82-0.92) and 0.85 (95% CI: 0.80-0.90), respectively, with low heterogeneity (I2 < 30%). Random Forest (RF) had a similar AUC of 0.85 (95% CI: 0.78-0.92) but significant heterogeneity (I2 > 90%). Multilayer perceptron (MLP) and XGBoost models had moderate pooled AUCs of 0.79 (95% CI: 0.74-0.84) with high heterogeneity. RF showed strong accuracy (0.83, 95% CI: 0.70-0.96), while SVM had balanced sensitivity (0.69, 95% CI: 0.63-0.75) and specificity (0.73, 95% CI: 0.60-0.86). Age, serum creatinine, left ventricular ejection fraction, and hemoglobin consistently influenced model efficacy.

CONCLUSIONS

GBM and SVM models, with robust AUCs and low heterogeneity, are effective in predicting AKI and CIN post-PCI/CAG. RF, MLP, and XGBoost, despite competitive AUCs, showed considerable heterogeneity, emphasizing the need for further validation.

Construction and validation of a personalized risk prediction model for in-hospital mortality in patients with acute myocardial infarction undergoing percutaneous coronary intervention

BACKGROUND

Although emergency Percutaneous Coronary Intervention (PCI) has been shown to reduce mortality in patients with Acute Myocardial Infarction (AMI), the risk of in-hospital death remains high. In this study, the authors aimed to identify risk factors associated with in-hospital mortality in AMI patients who underwent PCI, develop a nomogram prediction model, and evaluate its effectiveness.

METHODS

The authors retrospectively analyzed data from 1260 patients who underwent emergency PCI at Dongyang People's Hospital between June 1, 2013, and December 31, 2021. Patients were divided into two groups based on in-hospital mortality: the death group (n = 61) and the survival group (n = 1199). Clinical data between the two groups were compared. The Least Absolute Shrinkage and Selection Operator (LASSO) regression was used to select non-zero coefficients of predictive factors. Multivariable logistic regression analysis was then performed to identify independent risk factors for in-hospital mortality in AMI patients after emergency PCI. A nomogram model for predicting the risk of in-hospital mortality in AMI patients after PCI was constructed, and its predictive performance was evaluated using the c-index. Internal validation was performed using the bootstrap method with 1000 resamples. The Hosmer-Lemeshow test was used to assess the goodness of fit, and a calibration curve was plotted to evaluate the model's calibration.

RESULTS

LASSO regression identified d-dimer, B-type natriuretic peptide, white blood cell count, heart rate, aspartate aminotransferase, systolic blood pressure, and the presence of postoperative respiratory failure as important predictive factors for in-hospital mortality in AMI patients after PCI. Multivariable logistic regression analysis showed that d-dimer, B-type natriuretic peptide, white blood cell count, systolic blood pressure, and the presence of postoperative respiratory failure were independent factors for in-hospital mortality. A nomogram model for predicting the risk of in-hospital mortality in AMI patients after PCI was constructed using these independent predictive factors. The Hosmer-Lemeshow test yielded a Chi-Square value of 9.43 (p = 0.331), indicating a good fit for the model, and the calibration curve closely approximated the ideal model. The c-index for internal validation was 0.700 (0.560‒0.834), further confirming the predictive performance of the model. Clinical decision analysis demonstrated that the nomogram model had good clinical utility, with an area under the ROC curve of 0.944 (95 % CI 0.903‒0.963), indicating excellent discriminative ability.

CONCLUSION

This study identified B-type natriuretic peptide, white blood cell count, systolic blood pressure, d-dimer, and the presence of respiratory failure as independent factors for in-hospital mortality in AMI patients undergoing emergency PCI. The nomogram model based on these factors showed high predictive accuracy and feasibility.

Machine Learning Applications in Acute Coronary Syndrome: Diagnosis, Outcomes and Management

Acute coronary syndrome (ACS) is a leading cause of death worldwide. Prompt and accurate diagnosis of acute myocardial infarction (AMI) or ACS is crucial for improved management and prognosis of patients. The rapid growth of machine learning (ML) research has significantly enhanced our understanding of ACS. Most studies have focused on applying ML to detect ACS, predict prognosis, manage treatment, identify risk factors, and discover potential biomarkers, particularly using data from electrocardiograms (ECGs), electronic medical records (EMRs), imaging, and omics as the main data modality. Additionally, integrating ML with smart devices such as wearables, smartphones, and sensor technology enables real-time dynamic assessments, enhancing clinical care for patients with ACS. This review provided an overview of the workflow and key concepts of ML as they relate to ACS. It then provides an overview of current ML algorithms used for ACS diagnosis, prognosis, identification of potential risk biomarkers, and management. Furthermore, we discuss the current challenges faced by ML algorithms in this field and how they might be addressed in the future, especially in the context of medicine.

Predicting the risk of heart failure after acute myocardial infarction using an interpretable machine learning model

Background

Early prediction of heart failure (HF) after acute myocardial infarction (AMI) is essential for personalized treatment. We aimed to use interpretable machine learning (ML) methods to develop a risk prediction model for HF in AMI patients.

Methods

We retrospectively included patients initially with AMI who received percutaneous coronary intervention (PCI) in our hospital from November 2016 to February 2020. The primary endpoint was the occurrence of HF within 3 years after operation. For developing a predictive model for HF risk in AMI patients, the least absolute shrinkage and selection operator (LASSO) Regression was used to feature selection, and four ML algorithms including Random Forest (RF), Extreme Gradient Boost (XGBoost), Support Vector Machine (SVM), and Logistic Regression (LR) were employed to develop the model on the training set. The performance evaluation of the prediction model was carried out on the training set and the testing set, utilizing metrics including AUC (Area under the receiver operating characteristic curve), calibration plot, and decision curve analysis (DCA). In addition, we used the Shapley Additive Explanations (SHAP) value to determine the importance of the selected features and interpret the optimal model.

Results

A total of 1220 AMI patients were included and 244 (20%) patients developed HF during follow-up. Among the four evaluated ML models, the XGBoost model exhibited exceptional accuracy, with an AUC value of 0.922. The SHAP method showed that left ventricular ejection fraction (LVEF), left ventricular end-systolic diameter (LVDs) and lactate dehydrogenase (LDH) were identified as the three most important characteristics to predict HF risk in AMI patients. Individual risk assessment was performed using SHAP plots and waterfall plot analysis.

Conclusions

Our research demonstrates the potential of ML methods in the early prediction of HF risk in AMI patients. Furthermore, it enhances the interpretability of the XGBoost model through SHAP analysis to guide clinical decision-making.

Maximizing Survival in Pediatric Congenital Cardiac Surgery Using Machine Learning, Explainability, and Simulation Techniques

Background: Pediatric and congenital heart surgery (PCHS) is highly risky. Complications associated with this surgical procedure are mainly caused by the severity of the disease or the unnecessary, late, or premature execution of the procedure, which can be fatal. In this context, prognostic models are crucial to reduce the uncertainty of the decision to perform surgery; however, these models alone are insufficient to maximize the probability of success or to reverse a future scenario of patient death. Method: A new approach is proposed to reverse the prognosis of death in PCHS through the use of (1) machine learning (ML) models to predict the outcome of surgery; (2) an explainability technique (ET) to determine the impact of main risk factors; and (3) a simulation method to design health scenarios that potentially reverse a negative prognosis. Results: Accuracy levels of 96% in the prediction of mortality and survival were achieved using a dataset of 565 patients undergoing PCHS and assessing 10 risk factors. Three case studies confirmed that the ET known as LIME provides explanations that are consistent with the observed results, and the simulation of one real case managed to reverse the initial prognosis of death to one of survival. Conclusions: An innovative method that integrates ML models, ETs, and Simulation has been developed to reverse the prognosis of death in patients undergoing PCHS. The experimental results validate the relevance of this approach in medical decision-making, demonstrating its ability to reverse negative prognoses and provide a solid basis for more informed and personalized medical decisions.

QTc interval prolongation impact on in-hospital mortality in acute coronary syndromes patients using artificial intelligence and machine learning

BACKGROUND

Prediction of mortality in hospitalized patients is a crucial and important problem. Several severity scoring systems over the past few decades and machine learning models for mortality prediction have been developed to predict in-hospital mortality. Our aim in this study was to apply machine learning (ML) algorithms using QTc interval to predict in-hospital mortality in ACS patients and compare them to the validated conventional risk scores.

RESULTS

This study was retrospective, using supervised learning, and data mining. Out of a cohort of 500 patients admitted to a tertiary care hospital from September 2018 to August 2020, who presented with ACS. Prediction models for in-hospital mortality in ACS patients were developed using 3 ML algorithms. We employed the ensemble learning random forest (RF) model, the Naive Bayes (NB) model and the rule-based projective adaptive resonance theory (PART) model. These models were compared to one another and to two conventional validated risk scores; the Global Registry of Acute Coronary Events (GRACE) risk score and Thrombolysis in Myocardial Infarction (TIMI) risk score. Out of the 500 patients included in our study, 164 (32.8%) patients presented with unstable angina, 148 (29.6%) patients with non-ST-elevation myocardial infarction (NSTEMI) and 188 (37.6%) patients were having ST-elevation myocardial infarction (STEMI). 64 (12.8%) patients died in-hospital and the rest survived. Performance of prediction models was measured in an area under the receiver operating characteristic curve (AUC) ranged from 0.83 to 0.93 using all available variables compared to the GRACE score (0.9 SD 0.05) and the TIMI score (0.75 SD 0.02). Using QTc as a stand-alone variable yielded (0.67 SD 0.02) with a cutoff value 450 using Bazett's formula, whereas using QTc in addition to other variables of personal and clinical data and other ECG variables, the result was 0.8 SD 0.04. Results of RF and NB models were almost the same, but PART model yielded the least results. There was no significant difference of AUC values after replacing the missing values and applying class balancer.

CONCLUSIONS

The proposed method can effectively predict patients at high risk of in-hospital mortality early in the setting of ACS using only clinical and ECG data. Prolonged QTc interval can be used as a risk predictor of in-hospital mortality in ACS patients.

Temporal trends of in-hospital mortality and its determinants following percutaneous coronary intervention in patients with acute coronary syndrome in England and Wales: A population-based study between 2006 and 2021

BACKGROUND

There is limited data around drivers of changes in mortality over time. We aimed to examine the temporal changes in mortality and understand its determinants over time.

METHODS

743,149 PCI procedures for patients from the British Cardiovascular Intervention Society (BCIS) database who were aged between 18 and 100 years and underwent Percutaneous Coronary Intervention (PCI) for Acute Coronary Syndrome (ACS) in England and Wales between 2006 and 2021 were included. We decomposed the contributing factors to the difference in the observed mortality proportions between 2006 and 2021 using Fairlie decomposition method. Multiple imputation was used to address missing data.

RESULTS

Overall, there was an increase in the mortality proportion over time, from 1.7% (95% CI: 1.5% to 1.9%) in 2006 to 3.1% (95% CI: 3.0% to 3.2%) in 2021. 61.2% of this difference was explained by the variables included in the model. ACS subtypes (percentage contribution: 14.67%; 95% CI: 5.76% to 23.59%) and medical history (percentage contribution: 13.50%; 95% CI: 4.33% to 22.67%) were the strongest contributors to the difference in the observed mortality proportions between 2006 and 2021. Also, there were different drivers to mortality changes between different time periods. Specifically, ACS subtypes and severity of presentation were amongst the strongest contributors between 2006 and 2012 while access site and demographics were the strongest contributors between 2012 and 2021.

CONCLUSIONS

Patient factors and the move towards ST-elevated myocardial infarction (STEMI) PCI have driven the short-term mortality changes following PCI for ACS the most.

AI in interventional cardiology: Innovations and challenges

Artificial Intelligence (AI) permeates all areas of our lives. Even now, we all use AI algorithms in our daily activities, and medicine is no exception. The potential of AI technology is hard to overestimate; AI has already proven its effectiveness in many fields of science and technology. A vast number of methods have been proposed and are being implemented in various areas of medicine, including interventional cardiology. A hallmark of this discipline is the extensive use of visualization techniques not only for diagnosis but also for the treatment of patients with coronary heart disease. The implementation of instrumental AI will reduce costs, in a broad sense. In this article, we provide an overview of AI research in interventional cardiology, practical applications, as well as the problems hindering the widespread use of neural network technologies in interventional cardiology.

Mid- to long-term efficacy and safety of stem cell therapy for acute myocardial infarction: a systematic review and meta-analysis

BACKGROUND

This comprehensive systematic review and meta-analysis investigated the mid- to long-term efficacy and safety of stem cell therapy in patients with acute myocardial infarction (AMI).

METHODS

The study encompassed 79 randomized controlled trials with 7103 patients, rendering it the most up-to-date and extensive analysis in this field. This study specifically focused on the impact of stem cell therapy on left ventricular ejection fraction (LVEF), major adverse cardiac events (MACE), and infarct size.

RESULTS

Stem cell therapy significantly improved LVEF at 6, 12, 24, and 36 months post-transplantation compared to control values, indicating its potential for long-term cardiac function enhancement. A trend toward reduced MACE occurrence was observed in the intervention groups, suggesting the potential of stem cell therapy to lower the risk of cardiovascular death, reinfarction, and stroke. Significant LVEF improvements were associated with long cell culture durations exceeding 1 week, particularly when combined with high injected cell quantities (at least 108 cells). No significant reduction in infarct size was observed.

CONCLUSIONS

This review highlights the potential of stem cell therapy as a promising therapeutic approach for patients with AMI, offering sustained LVEF improvement and a potential reduction in MACE risk. However, further research is required to optimize cell culture techniques, determine the optimal timing and dosage, and investigate procedural variations to maximize the efficacy and safety of stem cell therapy in this context.

Accuracy of machine learning in predicting outcomes post-percutaneous coronary intervention: a systematic review

Background

Recent studies have shown potential in introducing machine learning (ML) algorithms to predict outcomes post-percutaneous coronary intervention (PCI).

Aims

We aimed to critically appraise current ML models' effectiveness as clinical tools to predict outcomes post-PCI.

Methods

Searches of four databases were conducted for articles published from the database inception date to 29 May 2021. Studies using ML to predict outcomes post-PCI were included. For individual post-PCI outcomes, measures of diagnostic accuracy were extracted. An adapted checklist comprising existing frameworks for new risk markers, diagnostic accuracy, prognostic tools and ML was used to critically appraise the included studies along the stages of the translational pathway: development, validation, and impact. Quality of training data and methods of dealing with missing data were evaluated.

Results

Twelve cohorts from 11 studies were included with a total of 4,943,425 patients. ML models performed with high diagnostic accuracy. However, there are concerns over the development of the ML models. Methods of dealing with missing data were problematic. Four studies did not discuss how missing data were handled. One study removed patients if any of the predictor variable data points were missing. Moreover, at the validation stage, only three studies externally validated the models presented. There could be concerns over the applicability of these models. None of the studies discussed the cost-effectiveness of implementing the models.

Conclusions

ML models show promise as a useful clinical adjunct to traditional risk stratification scores in predicting outcomes post-PCI. However, significant challenges need to be addressed before ML can be integrated into clinical practice.

Critical appraisal and assessment of bias among studies evaluating risk prediction models for in-hospital and 30-day mortality after percutaneous coronary intervention: a systematic review

OBJECTIVE

We systematically assessed prediction models for the risk of in-hospital and 30-day mortality in post-percutaneous coronary intervention (PCI) patients.

DESIGN

Systematic review and narrative synthesis.

DATA SOURCES

Searched PubMed, Web of Science, Embase, Cochrane Library, CINAHL, CNKI, Wanfang Database, VIP Database and SinoMed for literature up to 31 August 2023.

ELIGIBILITY CRITERIA

The included literature consists of studies in Chinese or English involving PCI patients aged ≥18 years. These studies aim to develop risk prediction models and include designs such as cohort studies, case-control studies, cross-sectional studies or randomised controlled trials. Each prediction model must contain at least two predictors. Exclusion criteria encompass models that include outcomes other than death post-PCI, literature lacking essential details on study design, model construction and statistical analysis, models based on virtual datasets, and publications such as conference abstracts, grey literature, informal publications, duplicate publications, dissertations, reviews or case reports. We also exclude studies focusing on the localisation applicability of the model or comparative effectiveness.

DATA EXTRACTION AND SYNTHESIS

Two independent teams of researchers developed standardised data extraction forms based on CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies to extract and cross-verify data. They used Prediction model Risk Of Bias Assessment Tool (PROBAST) to assess the risk of bias and applicability of the model development or validation studies included in this review.

RESULTS

This review included 28 studies with 38 prediction models, showing area under the curve values ranging from 0.81 to 0.987. One study had an unclear risk of bias, while 27 studies had a high risk of bias, primarily in the area of statistical analysis. The models constructed in 25 studies lacked clinical applicability, with 21 of these studies including intraoperative or postoperative predictors.

CONCLUSION

The development of in-hospital and 30-day mortality prediction models for post-PCI patients is in its early stages. Emphasising clinical applicability and predictive stability is vital. Future research should follow PROBAST's low risk-of-bias guidelines, prioritising external validation for existing models to ensure reliable and widely applicable clinical predictions.

PROSPERO REGISTRATION NUMBER

CRD42023477272.

Development and validation of a machine learning-based readmission risk prediction model for non-ST elevation myocardial infarction patients after percutaneous coronary intervention

To investigate the factors that influence readmissions in patients with acute non-ST elevation myocardial infarction (NSTEMI) after percutaneous coronary intervention (PCI) by using multiple machine learning (ML) methods to establish a predictive model. In this study, 1576 NSTEMI patients who were hospitalized at the Affiliated Hospital of North Sichuan Medical College were selected as the research subjects. They were divided into two groups: the readmitted group and the non-readmitted group. The division was based on whether the patients experienced complications or another incident of myocardial infarction within one year after undergoing PCI. Common variables selected by univariate and multivariate logistic regression, LASSO regression, and random forest were used as independent influencing factors for NSTEMI patients' readmissions after PCI. Six different ML models were constructed using these common variables. The area under the ROC curve, accuracy, sensitivity, and specificity were used to evaluate the performance of the six ML models. Finally, the optimal model was selected, and a nomogram was created to visually represent its clinical effectiveness. Three different methods were used to select seven representative common variables. These variables were then utilized to construct six different ML models, which were subsequently compared. The findings indicated that the LR model exhibited the most optimal performance in terms of AUC, accuracy, sensitivity, and specificity. The outcome, admission mode (walking and non-walking), communication ability, CRP, TC, HDL, and LDL were identified as independent predicators of readmissions in NSTEMI patients after PCI. The prediction model constructed by the LR algorithm was the best. The established column graph model established proved to be effective in identifying high-risk groups with high accuracy and differentiation. It holds a specific predictive value for the occurrence of readmissions after direct PCI in NSTEMI patients.

Contemporary Risk Models for In-Hospital and 30-Day Mortality After Percutaneous Coronary Intervention

PURPOSE OF REVIEW

Risk models for mortality after percutaneous coronary intervention (PCI) are underutilized in clinical practice though they may be useful during informed consent, risk mitigation planning, and risk adjustment of hospital and operator outcomes. This review analyzed contemporary risk models for in-hospital and 30-day mortality after PCI.

RECENT FINDINGS

We reviewed eight contemporary risk models. Age, sex, hemodynamic status, acute coronary syndrome type, heart failure, and kidney disease were consistently found to be independent risk factors for mortality. These models provided good discrimination (C-statistic 0.85-0.95) for both pre-catheterization and comprehensive risk models that included anatomic variables. There are several excellent models for PCI mortality risk prediction. Choice of the model will depend on the use case and population, though the CathPCI model should be the default for in-hospital mortality risk prediction in the United States. Future interventions should focus on the integration of risk prediction into clinical care.

Temporal Relationship-Aware Treadmill Exercise Test Analysis Network for Coronary Artery Disease Diagnosis

The treadmill exercise test (TET) serves as a non-invasive method for the diagnosis of coronary artery disease (CAD). Despite its widespread use, TET reports are susceptible to external influences, heightening the risk of misdiagnosis and underdiagnosis. In this paper, we propose a novel automatic CAD diagnosis approach. The proposed approach introduces a customized preprocessing method to obtain clear electrocardiograms (ECGs) from individual TET reports. Additionally, it presents TETDiaNet, a novel neural network designed to explore the temporal relationships within TET ECGs. Central to TETDiaNet is the TETDia block, which mimics clinicians' diagnostic processes to extract essential diagnostic information. This block encompasses an intra-state contextual learning module and an inter-state contextual learning module, modeling the temporal relationships within a single state and between states, respectively. These two modules help the TETDia block to capture effective diagnosis information by exploring the temporal relationships within TET ECGs. Furthermore, we establish a new TET dataset named TET4CAD for CAD diagnosis. It contains simplified TET reports for 192 CAD patients and 224 non-CAD patients, and each patient undergoes coronary angiography for labeling. Experimental results on TET4CAD underscore the superior performance of the proposed approach, highlighting the discriminative value of the temporal relationships within TET ECGs for CAD diagnosis.

1-Year Mortality Prediction through Artificial Intelligence Using Hemodynamic Trace Analysis among Patients with ST Elevation Myocardial Infarction

Background and Objectives: Patients presenting with ST Elevation Myocardial Infarction (STEMI) due to occlusive coronary arteries remain at a higher risk of excess morbidity and mortality despite being treated with primary percutaneous coronary intervention (PPCI). Identifying high-risk patients is prudent so that close monitoring and timely interventions can improve outcomes. Materials and Methods: A cohort of 605 STEMI patients [64.2 ± 13.2 years, 432 (71.41%) males] treated with PPCI were recruited. Their arterial pressure (AP) wave recorded throughout the PPCI procedure was analyzed to extract features to predict 1-year mortality. After denoising and extracting features, we developed two distinct feature selection strategies. The first strategy uses linear discriminant analysis (LDA), and the second employs principal component analysis (PCA), with each method selecting the top five features. Then, three machine learning algorithms were employed: LDA, K-nearest neighbor (KNN), and support vector machine (SVM). Results: The performance of these algorithms, measured by the area under the curve (AUC), ranged from 0.73 to 0.77, with accuracy, specificity, and sensitivity ranging between 68% and 73%. Moreover, we extended the analysis by incorporating demographics, risk factors, and catheterization information. This significantly improved the overall accuracy and specificity to more than 76% while maintaining the same level of sensitivity. This resulted in an AUC greater than 0.80 for most models. Conclusions: Machine learning algorithms analyzing hemodynamic traces in STEMI patients identify high-risk patients at risk of mortality.

Merging machine learning and patient preference: a novel tool for risk prediction of percutaneous coronary interventions

BACKGROUND AND AIMS

Predicting personalized risk for adverse events following percutaneous coronary intervention (PCI) remains critical in weighing treatment options, employing risk mitigation strategies, and enhancing shared decision-making. This study aimed to employ machine learning models using pre-procedural variables to accurately predict common post-PCI complications.

METHODS

A group of 66 adults underwent a semiquantitative survey assessing a preferred list of outcomes and model display. The machine learning cohort included 107 793 patients undergoing PCI procedures performed at 48 hospitals in Michigan between 1 April 2018 and 31 December 2021 in the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2) registry separated into training and validation cohorts. External validation was conducted in the Cardiac Care Outcomes Assessment Program database of 56 583 procedures in 33 hospitals in Washington.

RESULTS

Overall rate of in-hospital mortality was 1.85% (n = 1999), acute kidney injury 2.51% (n = 2519), new-onset dialysis 0.44% (n = 462), stroke 0.41% (n = 447), major bleeding 0.89% (n = 942), and transfusion 2.41% (n = 2592). The model demonstrated robust discrimination and calibration for mortality {area under the receiver-operating characteristic curve [AUC]: 0.930 [95% confidence interval (CI) 0.920-0.940]}, acute kidney injury [AUC: 0.893 (95% CI 0.883-0.903)], dialysis [AUC: 0.951 (95% CI 0.939-0.964)], stroke [AUC: 0.751 (95%CI 0.714-0.787)], transfusion [AUC: 0.917 (95% CI 0.907-0.925)], and major bleeding [AUC: 0.887 (95% CI 0.870-0.905)]. Similar discrimination was noted in the external validation population. Survey subjects preferred a comprehensive list of individually reported post-procedure outcomes.

CONCLUSIONS

Using common pre-procedural risk factors, the BMC2 machine learning models accurately predict post-PCI outcomes. Utilizing patient feedback, the BMC2 models employ a patient-centred tool to clearly display risks to patients and providers (https://shiny.bmc2.org/pci-prediction/). Enhanced risk prediction prior to PCI could help inform treatment selection and shared decision-making discussions.

Data analytics approach for short- and long-term mortality prediction following acute non-ST-elevation myocardial infarction (NSTEMI) and Unstable Angina (UA) in Asians

BACKGROUND

Traditional risk assessment tools often lack accuracy when predicting the short- and long-term mortality following a non-ST-segment elevation myocardial infarction (NSTEMI) or Unstable Angina (UA) in specific population.

OBJECTIVE

To employ machine learning (ML) and stacked ensemble learning (EL) methods in predicting short- and long-term mortality in Asian patients diagnosed with NSTEMI/UA and to identify the associated features, subsequently evaluating these findings against established risk scores.

METHODS

We analyzed data from the National Cardiovascular Disease Database for Malaysia (2006-2019), representing a diverse NSTEMI/UA Asian cohort. Algorithm development utilized in-hospital records of 9,518 patients, 30-day data from 7,133 patients, and 1-year data from 7,031 patients. This study utilized 39 features, including demographic, cardiovascular risk, medication, and clinical features. In the development of the stacked EL model, four base learner algorithms were employed: eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest (RF), with the Generalized Linear Model (GLM) serving as the meta learner. Significant features were chosen and ranked using ML feature importance with backward elimination. The predictive performance of the algorithms was assessed using the area under the curve (AUC) as a metric. Validation of the algorithms was conducted against the TIMI for NSTEMI/UA using a separate validation dataset, and the net reclassification index (NRI) was subsequently determined.

RESULTS

Using both complete and reduced features, the algorithm performance achieved an AUC ranging from 0.73 to 0.89. The top-performing ML algorithm consistently surpassed the TIMI risk score for in-hospital, 30-day, and 1-year predictions (with AUC values of 0.88, 0.88, and 0.81, respectively, all p < 0.001), while the TIMI scores registered significantly lower at 0.55, 0.54, and 0.61. This suggests the TIMI score tends to underestimate patient mortality risk. The net reclassification index (NRI) of the best ML algorithm for NSTEMI/UA patients across these periods yielded an NRI between 40-60% (p < 0.001) relative to the TIMI NSTEMI/UA risk score. Key features identified for both short- and long-term mortality included age, Killip class, heart rate, and Low-Molecular-Weight Heparin (LMWH) administration.

CONCLUSIONS

In a broad multi-ethnic population, ML approaches outperformed conventional TIMI scoring in classifying patients with NSTEMI and UA. ML allows for the precise identification of unique characteristics within individual Asian populations, improving the accuracy of mortality predictions. Continuous development, testing, and validation of these ML algorithms holds the promise of enhanced risk stratification, thereby revolutionizing future management strategies and patient outcomes.

Artificial Intelligence-Based Clinical Decision Support Systems in Cardiovascular Diseases

Despite all the advancements in science, medical knowledge, healthcare, and the healthcare industry, cardiovascular disease (CVD) remains the leading cause of morbidity and mortality worldwide. The main reasons are the inadequacy of preventive health services and delays in diagnosis due to the increasing population, the failure of physicians to apply guide-based treatments, the lack of continuous patient follow-up, and the low compliance of patients with doctors' recommendations. Artificial intelligence (AI)-based clinical decision support systems (CDSSs) are systems that support complex decision-making processes by using AI techniques such as data analysis, foresight, and optimization. Artificial intelligence-based CDSSs play an important role in patient care by providing more accurate and personalized information to healthcare professionals in risk assessment, diagnosis, treatment optimization, and monitoring and early warning of CVD. These are just some examples, and the use of AI for CVD decision support systems is rapidly evolving. However, for these systems to be fully reliable and effective, they need to be trained with accurate data and carefully evaluated by medical professionals.

Predicting target lesion failure following percutaneous coronary intervention through machine learning risk assessment models

Aims

Central to the practice of precision medicine in percutaneous coronary intervention (PCI) is a risk-stratification tool to predict outcomes following the procedure. This study is intended to assess machine learning (ML)-based risk models to predict clinically relevant outcomes in PCI and to support individualized clinical decision-making in this setting.

Methods and results

Five different ML models [gradient boosting classifier (GBC), linear discrimination analysis, Naïve Bayes, logistic regression, and K-nearest neighbours algorithm) for the prediction of 1-year target lesion failure (TLF) were trained on an extensive data set of 35 389 patients undergoing PCI and enrolled in the global, all-comers e-ULTIMASTER registry. The data set was split into a training (80%) and a test set (20%). Twenty-three patient and procedural characteristics were used as predictive variables. The models were compared for discrimination according to the area under the receiver operating characteristic curve (AUC) and for calibration. The GBC model showed the best discriminative ability with an AUC of 0.72 (95% confidence interval 0.69-0.75) for 1-year TLF on the test set. The discriminative ability of the GBC model for the components of TLF was highest for cardiac death with an AUC of 0.82, followed by target vessel myocardial infarction with an AUC of 0.75 and clinically driven target lesion revascularization with an AUC of 0.68. The calibration was fair until the highest risk deciles showed an underestimation of the risk.

Conclusion

Machine learning-derived predictive models provide a reasonably accurate prediction of 1-year TLF in patients undergoing PCI. A prospective evaluation of the predictive score is warranted.

Registration

Clinicaltrial.gov identifier is NCT02188355.

Development and validation of a predictive models for predicting the cardiac events within one year for patients underwent percutaneous coronary intervention procedure at IJN

PURPOSE

Percutaneous coronary intervention (PCI) is a common treatment modality for coronary artery disease. Accurate prediction of patients at risk for complications and hospital readmission after PCI could improve the overall clinical management. We aimed to develop and validate predictive models to predict any cardiac event within a year post PCI procedure.

METHODS

This is a retrospective cohort study utilizing data from the National Cardiovascular Disease (NCVD)-PCI registry. The data collected (N = 28,007) were split into training set (n = 24,409) and testing set (n = 3598). Four predictive models (logistic regression [LR], random forest method, support vector machine [SVM], and artificial neural network) were developed and validated. The outcome on risk prediction were compared.

RESULTS

The demographic and clinical features of patients in the training and testing cohorts were similar. Patients had mean age ± standard deviation of 58.15 ± 10.13 years at admission with a male majority (82.66%). In over half of the procedures (50.61%), patients had chronic stable angina. Within 1 year of follow up mortality, target vessel revascularization (TVR), and composite event of mortality and TVR were 3.92%, 9.48%, and 12.98% respectively. LR was the best model in predicting mortality event within 1-year post-PCI (AUC: 0.820). SVM had the highest discrimination power for both TVR event (AUC: 0.720) and composite event of mortality and TVR (AUC: 0.720).

CONCLUSIONS

This study successfully identified optimal prediction models with the good discriminatory ability for mortality outcome and good discrimination ability for TVR and composite event of mortality and TVR with a simple machine learning framework.

Machine learning algorithms to automate differentiating cardiac amyloidosis from hypertrophic cardiomyopathy

Cardiac amyloidosis has a poor prognosis, and high mortality and is often misdiagnosed as hypertrophic cardiomyopathy, leading to delayed diagnosis. Machine learning combined with speckle tracking echocardiography was proposed to automate differentiating two conditions. A total of 74 patients with pathologically confirmed monoclonal immunoglobulin light chain cardiac amyloidosis and 64 patients with hypertrophic cardiomyopathy were enrolled from June 2015 to November 2018. Machine learning models utilizing traditional and advanced algorithms were established and determined the most significant predictors. The performance was evaluated by the receiver operating characteristic curve (ROC) and the area under the curve (AUC). With clinical and echocardiography data, all models showed great discriminative performance (AUC > 0.9). Compared with logistic regression (AUC 0.91), machine learning such as support vector machine (AUC 0.95, p = 0.477), random forest (AUC 0.97, p = 0.301) and gradient boosting machine (AUC 0.98, p = 0.230) demonstrated similar capability to distinguish cardiac amyloidosis and hypertrophic cardiomyopathy. With speckle tracking echocardiography, the predictive performance of the voting model was similar to that of LightGBM (AUC was 0.86 for both), while the AUC of XGBoost was slightly lower (AUC 0.84). In fivefold cross-validation, the voting model was more robust globally and superior to the single model in some test sets. Data-driven machine learning had shown admirable performance in differentiating two conditions and could automatically integrate abundant variables to identify the most discriminating predictors without making preassumptions. In the era of big data, automated machine learning will help to identify patients with cardiac amyloidosis and timely and effectively intervene, thus improving the outcome.

Development of a novel tool: a nomogram for predicting in-hospital mortality of patients in intensive care unit after percutaneous coronary intervention

BACKGROUNDS

Increased risk of in-hospital mortality is critical to guide medical decisions and it played a central role in intensive care unit (ICU) with high risk of in-hospital mortality after primary percutaneous coronary intervention (PCI). At present，most predicting tools for in-hospital mortality after PCI were based on the results of coronary angiography, echocardiography, and laboratory results which are difficult to obtain at admission. The difficulty of using these tools limit their clinical application. This study aimed to develop a clinical prognostic nomogram to predict the in-hospital mortality of patients in ICU after PCI.

METHODS

We extracted data from a public database named the Medical Information Mart for Intensive Care (MIMIC III). Adult patients with coronary artery stent insertion were included. They were divided into two groups according to the primary outcome (death in hospital or survive). All patients were randomly divided into training set and validation set randomly at a ratio of 6:4. Least absolute shrinkage and selection operator (LASSO) regression was performed in the training set to select optimal variables to predict the in-hospital mortality of patients in ICU after PCI. The multivariate logistical analysis was performed to develop a nomogram. Finally, the predictive efficiency of the nomogram was assessed by area under the receiver operating characteristic curve (AUROC)，integrated discrimination improvement (IDI), and net reclassification improvement (NRI), and clinical net benefit was assessed by Decision curve analysis (DCA).

RESULTS

A total of 2160 patients were recruited in this study. By using LASSO, 17 variables were finally included. We used multivariate logistic regression to construct a prediction model which was presented in the form of a nomogram. The calibration plot of the nomogram revealed good fit in the training set and validation set. Compared with the sequential organ failure assessment (SOFA) and scale for the assessment of positive symptoms II (SAPS II) scores, the nomogram exhibited better AUROC of 0.907 (95% confidence interval [CI] was 0.880-0.933, p <  0.001) and 0.901 (95% CI was 0.865-0.936, P <  0.001) in the training set and validation set, respectively. In addition, DCA of the nomogram showed that it could achieve good net benefit in the clinic.

CONCLUSIONS

A new nomogram was constructed, and it presented excellent performance in predicting in-hospital mortality of patients in ICU after PCI.

Machine learning for prediction of bleeding in acute myocardial infarction patients after percutaneous coronary intervention

Background

Prediction of bleeding is critical for acute myocardial infarction (AMI) patients after percutaneous coronary intervention (PCI). Machine learning methods can automatically select the combination of the important features and learn their underlying relationship with the outcome.

Objectives

We aimed to evaluate the predictive value of machine learning methods to predict in-hospital bleeding for AMI patients.

Design

We used data from the multicenter China Acute Myocardial Infarction (CAMI) registry. The cohort was randomly partitioned into derivation set (50%) and validation set (50%). We applied a state-of-art machine learning algorithm, eXtreme Gradient Boosting (XGBoost), to automatically select features from 98 candidate variables and developed a risk prediction model to predict in-hospital bleeding (Bleeding Academic Research Consortium [BARC] 3 or 5 definition).

Results

A total of 16,736 AMI patients who underwent PCI were finally enrolled. 45 features were automatically selected and were used to construct the prediction model. The developed XGBoost model showed ideal prediction results. The area under the receiver-operating characteristic curve (AUROC) on the derivation data set was 0.941 (95% CI = 0.909-0.973, p < 0.001); the AUROC on the validation set was 0.837 (95% CI = 0.772-0.903, p < 0.001), which was better than the CRUSADE score (AUROC: 0.741; 95% CI = 0.654-0.828, p < 0.001) and ACUITY-HORIZONS score (AUROC: 0.731; 95% CI = 0.641-0.820, p < 0.001). We also developed an online calculator with 12 most important variables (http://101.89.95.81:8260/), and AUROC still reached 0.809 on the validation set.

Conclusion

For the first time, we developed the CAMI bleeding model using machine learning methods for AMI patients after PCI.

Trial registration

NCT01874691. Registered 11 Jun 2013.

Forewarned Is Forearmed: Machine Learning Algorithms for the Prediction of Catheter-Induced Coronary and Aortic Injuries

Catheter-induced dissections (CID) of coronary arteries and/or the aorta are among the most dangerous complications of percutaneous coronary procedures, yet the data on their risk factors are anecdotal. Logistic regression and five more advanced machine learning techniques were applied to determine the most significant predictors of dissection. Model performance comparison and feature importance ranking were evaluated. We identified 124 cases of CID in electronic databases containing 84,223 records of diagnostic and interventional coronary procedures from the years 2000-2022. Based on the f1-score, Extreme Gradient Boosting (XGBoost) was found to have the optimal balance between positive predictive value (precision) and sensitivity (recall). As by the XGBoost, the strongest predictors were the use of a guiding catheter (angioplasty), small/stenotic ostium, radial access, hypertension, acute myocardial infarction, prior angioplasty, female gender, chronic renal failure, atypical coronary origin, and chronic obstructive pulmonary disease. Risk prediction can be bolstered with machine learning algorithms and provide valuable clinical decision support. Based on the proposed model, a profile of 'a perfect dissection candidate' can be defined. In patients with 'a clustering' of dissection predictors, a less aggressive catheter and/or modification of the access site should be considered.

Use of machine learning models to predict in-hospital mortality in patients with acute coronary syndrome

BACKGROUND

Cardiovascular diseases are a significant health burden with the prevalence increasing worldwide. Thus, a highly accurate assessment and prediction of death risk are crucial to meet the clinical demand. This study sought to develop and validate a model to predict in-hospital mortality among patients with the acute coronary syndrome (ACS) using nonlinear algorithms.

METHODS

A total of 2414 ACS patients were enrolled in this study. All samples were divided into five groups for cross-validation. The logistic regression (LR) model and XGboost model were applied to predict in-hospital mortality. The results of two models were compared between the variable set by the global registry of acute coronary events (GRACE) score and the selected variable set.

RESULTS

The in-hospital mortality rate was 3.5% in the dataset. Model performance on the selected variable set was better than that on GRACE variables: a 3% increase in area under the receiver operating characteristic (ROC) curve (AUC) for LR and 1.3% for XGBoost. The AUC of XGBoost is 0.913 (95% confidence interval [CI]: 0.910-0.916), demonstrating a better discrimination ability than LR (AUC = 0.904, 95% CI: 0.902-0.905) on the selected variable set. Almost perfect calibration was found in XGBoost (slope of predicted to observed events, 1.08; intercept, -0.103; p < .001).

CONCLUSIONS

XGboost modeling, an advanced machine learning algorithm, identifies new variables and provides high accuracy for the prediction of in-hospital mortality in ACS patients.

Machine learning model identifies aggressive acute pancreatitis within 48 h of admission: a large retrospective study

BACKGROUND

Acute pancreatitis (AP) with critical illness is linked to increased morbidity and mortality. Current risk scores to identify high-risk AP patients have certain limitations.

OBJECTIVE

To develop and validate a machine learning tool within 48 h after admission for predicting which patients with AP will develop critical illness based on ubiquitously available clinical, laboratory, and radiologic variables.

METHODS

5460 AP patients were enrolled. Clinical, laboratory, and imaging variables were collected within 48 h after hospital admission. Least Absolute Shrinkage Selection Operator with bootstrap method was employed to select the most informative variables. Five different machine learning models were constructed to predictive likelihood of critical illness, and the optimal model (APCU) was selected. External cohort was used to validate APCU. APCU and other risk scores were compared using multivariate analysis. Models were evaluated by area under the curve (AUC). The decision curve analysis was employed to evaluate the standardized net benefit.

RESULTS

Xgboost was constructed and selected as APCU, involving age, comorbid disease, mental status, pulmonary infiltrates, procalcitonin (PCT), neutrophil percentage (Neu%), ALT/AST, ratio of albumin and globulin, cholinesterase, Urea, Glu, AST and serum total cholesterol. The APCU performed excellently in discriminating AP risk in internal cohort (AUC = 0.95) and external cohort (AUC = 0.873). The APCU was significant for biliogenic AP (OR = 4.25 [2.08-8.72], P < 0.001), alcoholic AP (OR = 3.60 [1.67-7.72], P = 0.001), hyperlipidemic AP (OR = 2.63 [1.28-5.37], P = 0.008) and tumor AP (OR = 4.57 [2.14-9.72], P < 0.001). APCU yielded the highest clinical net benefit, comparatively.

CONCLUSION

Machine learning tool based on ubiquitously available clinical variables accurately predicts the development of AP, optimizing the management of AP.

Machine learning predicting mortality in sarcoidosis patients admitted for acute heart failure

Background

Sarcoidosis with cardiac involvement, although rare, has a worse prognosis than sarcoidosis involving other organ systems.

Objective

We used a large dataset to train machine learning models to predict in-hospital mortality among sarcoidosis patients admitted with heart failure (HF).

Method

Utilizing the National Inpatient Sample, we identified 4659 patients hospitalized with a primary diagnosis of HF. In this cohort, we identified patients with a secondary diagnosis of sarcoidosis using International Statistical Classification of Disease, Tenth Revision (ICD-10) codes. Patients were separated into a training group and a testing group in a 7:3 ratio. Least absolute shrinkage and selection operator regression was used to select variables to prevent model overfitting or underfitting. For machine learning models, logistic regression, random forest, and XGBoosting were applied in the training group. Parameters in each of the models were tuned using the GridSearchCV function. After training, all models were further validated in the testing group. Models were then evaluated using the area under curve (AUC) score, sensitivity, and specificity.

Results

A total of 2.3% of sarcoidosis patients died in HF admission. Our machine learning model analysis found the RF model to have the highest AUC score and sensitivity. Feature analysis found that comorbid arrhythmias and fluid electrolyte disorders were the strongest factors in predicting in-hospital mortality.

Conclusion

Machine learning methods can be useful in identifying predictors of in-hospital mortality in a given dataset.

Predictors of one-year outcome after cardiac re-transplantation: Machine learning analysis

BACKGROUND

As cardiac re-transplantation is associated with inferior outcomes compared with primary transplantation, allocating scarce resources to appropriate re-transplant candidates is important. The aim of this study is to elucidate the factors associated with 1-year mortality in cardiac re-transplantation using the random forests algorithm for survival analysis.

METHODS

We retrospectively reviewed the United Network for Organ Sharing registry and identified all adult (>17 years old) recipients who underwent cardiac re-transplantation between January 2000 and March 2020. The random forest algorithm on Cox modeling was used to calculate the variable importance (VIMP) of independent variables for contributing to one-year mortality.

RESULTS

A total of 1294 patients underwent cardiac re-transplantation. Of these, 137 patients were re-transplanted within one year of their first transplant, while 1157 patients were re-transplanted more than one year after their first transplant. One-year mortality was significantly higher for patients receiving early transplantation compared with those receiving late transplantation (Early 40.6% vs. Late 13.6%, log-rank P<0.001). Machine learning analysis showed that total bilirubin (>2 mg/dl) (VIMP, 2.99%) was an independent predictor of one-year mortality after early re-transplant. High BMI (>30.0 kg/m2) (VIMP, 1.43%) and ventilator dependence (VIMP, 1.47%) were independent predictors of one-year mortality for the late re-transplantation group.

CONCLUSION

Machine learning showed that optimal one-year survival following cardiac re-transplantation was significantly related to liver function in early re-transplantation, and to obesity and preoperative ventilator dependence in late re-transplantation. This article is protected by copyright. All rights reserved.

Machine learning to predict no reflow and in-hospital mortality in patients with ST-segment elevation myocardial infarction that underwent primary percutaneous coronary intervention

BACKGROUND

The machine learning algorithm (MLA) was implemented to establish an optimal model to predict the no reflow (NR) process and in-hospital death that occurred in ST-elevation myocardial infarction (STEMI) patients who underwent primary percutaneous coronary intervention (pPCI).

METHODS

The data were obtained retrospectively from 854 STEMI patients who underwent pPCI. MLA was applied to predict the potential NR phenomenon and confirm the in-hospital mortality. A random sampling method was used to split the data into the training (66.7%) and testing (33.3%) sets. The final results were an average of 10 repeated procedures. The area under the curve (AUC) and the associated 95% confidence intervals (CIs) of the receiver operator characteristic were measured.

RESULTS

A random forest algorithm (RAN) had optimal discrimination for the NR phenomenon with an AUC of 0.7891 (95% CI: 0.7093-0.8688) compared with 0.6437 (95% CI: 0.5506-0.7368) for the decision tree (CTREE), 0.7488 (95% CI: 0.6613-0.8363) for the support vector machine (SVM), and 0.681 (95% CI: 0.5767-0.7854) for the neural network algorithm (NNET). The optimal RAN AUC for in-hospital mortality was 0.9273 (95% CI: 0.8819-0.9728), for SVM, 0.8935 (95% CI: 0.826-0.9611); NNET, 0.7756 (95% CI: 0.6559-0.8952); and CTREE, 0.7885 (95% CI: 0.6738-0.9033).

CONCLUSIONS

The MLA had a relatively higher performance when evaluating the NR risk and in-hospital mortality in patients with STEMI who underwent pPCI and could be utilized in clinical decision making.

Machine learning models for prediction of adverse events after percutaneous coronary intervention

An accurate prediction of major adverse events after percutaneous coronary intervention (PCI) improves clinical decisions and specific interventions. To determine whether machine learning (ML) techniques predict peri-PCI adverse events [acute kidney injury (AKI), bleeding, and in-hospital mortality] with better discrimination or calibration than the National Cardiovascular Data Registry (NCDR-CathPCI) risk scores, we developed logistic regression and gradient descent boosting (XGBoost) models for each outcome using data from a prospective, all-comer, multicenter registry that enrolled consecutive coronary artery disease patients undergoing PCI in Japan between 2008 and 2020. The NCDR-CathPCI risk scores demonstrated good discrimination for each outcome (C-statistics of 0.82, 0.76, and 0.95 for AKI, bleeding, and in-hospital mortality) with considerable calibration. Compared with the NCDR-CathPCI risk scores, the XGBoost models modestly improved discrimination for AKI and bleeding (C-statistics of 0.84 in AKI, and 0.79 in bleeding) but not for in-hospital mortality (C-statistics of 0.96). The calibration plot demonstrated that the XGBoost model overestimated the risk for in-hospital mortality in low-risk patients. All of the original NCDR-CathPCI risk scores for adverse periprocedural events showed adequate discrimination and calibration within our cohort. When using the ML-based technique, however, the improvement in the overall risk prediction was minimal.

The path from big data analytics capabilities to value in hospitals: a scoping review

BACKGROUND

As the uptake of health information technologies increased, most healthcare organizations have become producers of big data. A growing number of hospitals are investing in the development of big data analytics (BDA) capabilities. If the promises associated with these capabilities are high, how hospitals create value from it remains unclear. The present study undertakes a scoping review of existing research on BDA use in hospitals to describe the path from BDA capabilities (BDAC) to value and its associated challenges.

METHODS

This scoping review was conducted following Arksey and O'Malley's 5 stages framework. A systematic search strategy was adopted to identify relevant articles in Scopus and Web of Science. Data charting and extraction were performed following an analytical framework that builds on the resource-based view of the firm to describe the path from BDA capabilities to value in hospitals.

RESULTS

Of 1,478 articles identified, 94 were included. Most of them are experimental research (n=69) published in medical (n=66) or computer science journals (n=28). The main value targets associated with the use of BDA are improving the quality of decision-making (n=56) and driving innovation (n=52) which apply mainly to care (n=67) and administrative (n=48) activities. To reach these targets, hospitals need to adequately combine BDA capabilities and value creation mechanisms (VCM) to enable knowledge generation and drive its assimilation. Benefits are endpoints of the value creation process. They are expected in all articles but realized in a few instances only (n=19).

CONCLUSIONS

This review confirms the value creation potential of BDA solutions in hospitals. It also shows the organizational challenges that prevent hospitals from generating actual benefits from BDAC-building efforts. The configuring of strategies, technologies and organizational capabilities underlying the development of value-creating BDA solutions should become a priority area for research, with focus on the mechanisms that can drive the alignment of BDA and organizational strategies, and the development of organizational capabilities to support knowledge generation and assimilation.

Current and Future Applications of Artificial Intelligence in Coronary Artery Disease

Cardiovascular diseases (CVDs) carry significant morbidity and mortality and are associated with substantial economic burden on healthcare systems around the world. Coronary artery disease, as one disease entity under the CVDs umbrella, had a prevalence of 7.2% among adults in the United States and incurred a financial burden of 360 billion US dollars in the years 2016–2017. The introduction of artificial intelligence (AI) and machine learning over the last two decades has unlocked new dimensions in the field of cardiovascular medicine. From automatic interpretations of heart rhythm disorders via smartwatches, to assisting in complex decision-making, AI has quickly expanded its realms in medicine and has demonstrated itself as a promising tool in helping clinicians guide treatment decisions. Understanding complex genetic interactions and developing clinical risk prediction models, advanced cardiac imaging, and improving mortality outcomes are just a few areas where AI has been applied in the domain of coronary artery disease. Through this review, we sought to summarize the advances in AI relating to coronary artery disease, current limitations, and future perspectives.

Anemia is associated with increased risk of contrast‑induced acute kidney injury: A Systematic Review and Meta-analysis

Previous studies have identified numerous risk factors of contrast-induced acute kidney injury (CI-AKI) in patients undergoing coronary angiography. However, the association between anemia and CI-AKI remains conflicting. Thus, we conducted a meta-analysis to further clarify the relationship between anemia and CI-AKI. PubMed, EMBASE and Web of Science were systematically searched from inception to June 2020 to identify eligible studies. The pooled odds ratios (ORs) with 95% confidence intervals (CIs) were used to estimate the correlation between anemia and CI-AKI. The potential publication bias was estimated using funnel plot and Begg's test. A total of 13 studies (five case-control studies and eight cohort studies) comprising 27,135 patients were included. The pooled results showed that anemia was a significant risk factor of CI-AKI (OR, 1.82; 95% CI, 1.27-2.61). Moreover, the results of subgroup analyses and sensitivity analyses were basically consistent with the overall pooled result. Funnel plot and Begg's test indicated that there existed potential publication bias, but the result of trim and filled analysis showed that the pooled results kept stable after adding 'missing' studies. This meta-analysis suggested that anemia may be correlated with an increased incidence of CI-AKI in patients undergoing coronary angiography. However, our conclusions should be interpreted with caution due to some limitations. Therefore, further high-quality trials should be conducted to confirm our findings.

Application of machine learning to predict the occurrence of arrhythmia after acute myocardial infarction

Background

Early identification of the occurrence of arrhythmia in patients with acute myocardial infarction plays an essential role in clinical decision-making. The present study attempted to use machine learning (ML) methods to build predictive models of arrhythmia after acute myocardial infarction (AMI).

Methods

A total of 2084 patients with acute myocardial infarction were enrolled in this study. (All data is available on Github: https://github.com/wangsuhuai/AMI-database1.git). The primary outcome is whether tachyarrhythmia occurred during admission containing atrial arrhythmia, ventricular arrhythmia, and supraventricular tachycardia. All data is randomly divided into a training set (80%) and an internal testing set (20%). Apply three machine learning algorithms: decision tree, random forest (RF), and artificial neural network (ANN) to learn the training set to build a model, then use the testing set to evaluate the prediction performance, and compare it with the model built by the Global Registry of Acute Coronary Events (GRACE) risk variable set.

Results

Three ML models predict the occurrence of tachyarrhythmias after AMI. After variable selection, the artificial neural network (ANN) model has reached the highest accuracy rate, which is better than the model constructed using the Grace variable set. After applying SHapley Additive exPlanations (SHAP) to make the model interpretable, the most important features are abnormal wall motion, lesion location, bundle branch block, age, and heart rate. Among them, RBBB (odds ratio [OR]: 4.21; 95% confidence interval [CI]: 2.42–7.02), ≥ 2 ventricular walls motion abnormal (OR: 3.26; 95% CI: 2.01–4.36) and right coronary artery occlusion (OR: 3.00; 95% CI: 1.98–4.56) are significant factors related to arrhythmia after AMI.

Conclusions

We used advanced machine learning methods to build prediction models for tachyarrhythmia after AMI for the first time (especially the ANN model that has the best performance). The current study can supplement the current AMI risk score, provide a reliable evaluation method for the clinic, and broaden the new horizons of ML and clinical research.

Trial registration Clinical Trial Registry No.: ChiCTR2100041960.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-021-01667-8.

Prediction of all-cause mortality in coronary artery disease patients with atrial fibrillation based on machine learning models

BACKGROUND

Machine learning (ML) can include more diverse and more complex variables to construct models. This study aimed to develop models based on ML methods to predict the all-cause mortality in coronary artery disease (CAD) patients with atrial fibrillation (AF).

METHODS

A total of 2037 CAD patients with AF were included in this study. Three ML methods were used, including the regularization logistic regression, random forest, and support vector machines. The fivefold cross-validation was used to evaluate model performance. The performance was quantified by calculating the area under the curve (AUC) with 95% confidence intervals (CI), sensitivity, specificity, and accuracy.

RESULTS

After univariate analysis, 24 variables with statistical differences were included into the models. The AUC of regularization logistic regression model, random forest model, and support vector machines model was 0.732 (95% CI 0.649-0.816), 0.728 (95% CI 0.642-0.813), and 0.712 (95% CI 0.630-0.794), respectively. The regularization logistic regression model presented the highest AUC value (0.732 vs 0.728 vs 0.712), specificity (0.699 vs 0.663 vs 0.668), and accuracy (0.936 vs 0.935 vs 0.935) among the three models. However, no statistical differences were observed in the receiver operating characteristic (ROC) curve of the three models (all P > 0.05).

CONCLUSION

Combining the performance of all aspects of the models, the regularization logistic regression model was recommended to be used in clinical practice.

The risk score for in-hospital mortality in patients with ST-segment elevation myocardial infarction

Aim    To develop a scale (score system) for predicting the individual risk of in-hospital death in patients with ST segment elevation acute myocardial infarction (STEMI) with an account of results of percutaneous coronary intervention (PCI).Material and methods    The analysis used data of 1 649 sequential patients with STEMI included into the hospital registry of PCI from 2006 through 2017. To test the model predictability, the original sample was divided into two groups: a training group consisting of 1150 (70 %) patients and a test group consisting of 499 (30 %) patients. The training sample was used for computing an individual score. To this purpose, β-coefficients of each variable obtained at the last stage of the multivariate logistic regression model were subjected to linear transformation. The scale was verified using the test sample.Results    Seven independent predictors of in-hospital death were determined: age ≥65 years, acute heart failure (Killip class III-IV), total myocardial ischemia time ≥180 min, anterior localization of myocardial infarction, failure of PCI, SYNTAX scale score ≥16, glycemia on admission ≥7.78 mmol/l for patients without a history of diabetes mellitus and ≥14.35 mmol/l for patients with a history of diabetes mellitus. The contribution of each value to the risk of in-hospital death was ranked from 0 to 7. A threshold total score of 10 was determined; a score ≥10 corresponded to a high probability of in-hospital death (18.2 %). In the training sample, the sensitivity was 81 %, the specificity was 80.6 %, and the area under the curve (AUC) was 0.902. In the test sample, the sensitivity was 96.2 %, the specificity was 83.3 %, and the AUC was 0.924.Conclusion    The developed scale has a good predictive accuracy in identifying patients with acute STEMI who have a high risk of fatal outcome at the hospital stage.

Heart, Eye, and Artificial Intelligence: A Review

Heart disease continues to be the leading cause of death in the USA. Deep learning-based artificial intelligence (AI) methods have become increasingly common in studying the various factors involved in cardiovascular disease. The usage of retinal scanning techniques to diagnose retinal diseases, such as diabetic retinopathy, age-related macular degeneration, glaucoma and others, using fundus photographs and optical coherence tomography angiography (OCTA) has been extensively documented. Researchers are now looking to combine the power of AI with the non-invasive ease of retinal scanning to examine the workings of the heart and predict changes in the macrovasculature based on microvascular features and function. In this review, we summarize the current state of the field in using retinal imaging to diagnose cardiovascular issues and other diseases.

Prediction of Genotype Positivity in Patients With Hypertrophic Cardiomyopathy Using Machine Learning

BACKGROUND

Genetic testing can determine family screening strategies and has prognostic and diagnostic value in hypertrophic cardiomyopathy (HCM). However, it can also pose a significant psychosocial burden. Conventional scoring systems offer modest ability to predict genotype positivity. The aim of our study was to develop a novel prediction model for genotype positivity in patients with HCM by applying machine learning (ML) algorithms.

METHODS

We constructed 3 ML models using readily available clinical and cardiac imaging data of 102 patients from Columbia University with HCM who had undergone genetic testing (the training set). We validated model performance on 76 patients with HCM from Massachusetts General Hospital (the test set). Within the test set, we compared the area under the receiver operating characteristic curves (AUROCs) for the ML models against the AUROCs generated by the Toronto HCM Genotype Score (the Toronto score) and Mayo HCM Genotype Predictor (the Mayo score) using the Delong test and net reclassification improvement.

RESULTS

Overall, 63 of the 178 patients (35%) were genotype positive. The random forest ML model developed in the training set demonstrated an AUROC of 0.92 (95% CI, 0.85-0.99) in predicting genotype positivity in the test set, significantly outperforming the Toronto score (AUROC, 0.77 [95% CI, 0.65-0.90], P=0.004, net reclassification improvement: P<0.001) and the Mayo score (AUROC, 0.79 [95% CI, 0.67-0.92], P=0.01, net reclassification improvement: P=0.001). The gradient boosted decision tree ML model also achieved significant net reclassification improvement over the Toronto score (P<0.001) and the Mayo score (P=0.03), with an AUROC of 0.87 (95% CI, 0.75-0.99). Compared with the Toronto and Mayo scores, all 3 ML models had higher sensitivity, positive predictive value, and negative predictive value.

CONCLUSIONS

Our ML models demonstrated a superior ability to predict genotype positivity in patients with HCM compared with conventional scoring systems in an external validation test set.

Machine learning for subtype definition and risk prediction in heart failure, acute coronary syndromes and atrial fibrillation: systematic review of validity and clinical utility

BACKGROUND

Machine learning (ML) is increasingly used in research for subtype definition and risk prediction, particularly in cardiovascular diseases. No existing ML models are routinely used for cardiovascular disease management, and their phase of clinical utility is unknown, partly due to a lack of clear criteria. We evaluated ML for subtype definition and risk prediction in heart failure (HF), acute coronary syndromes (ACS) and atrial fibrillation (AF).

METHODS

For ML studies of subtype definition and risk prediction, we conducted a systematic review in HF, ACS and AF, using PubMed, MEDLINE and Web of Science from January 2000 until December 2019. By adapting published criteria for diagnostic and prognostic studies, we developed a seven-domain, ML-specific checklist.

RESULTS

Of 5918 studies identified, 97 were included. Across studies for subtype definition (n = 40) and risk prediction (n = 57), there was variation in data source, population size (median 606 and median 6769), clinical setting (outpatient, inpatient, different departments), number of covariates (median 19 and median 48) and ML methods. All studies were single disease, most were North American (n = 61/97) and only 14 studies combined definition and risk prediction. Subtype definition and risk prediction studies respectively had limitations in development (e.g. 15.0% and 78.9% of studies related to patient benefit; 15.0% and 15.8% had low patient selection bias), validation (12.5% and 5.3% externally validated) and impact (32.5% and 91.2% improved outcome prediction; no effectiveness or cost-effectiveness evaluations).

CONCLUSIONS

Studies of ML in HF, ACS and AF are limited by number and type of included covariates, ML methods, population size, country, clinical setting and focus on single diseases, not overlap or multimorbidity. Clinical utility and implementation rely on improvements in development, validation and impact, facilitated by simple checklists. We provide clear steps prior to safe implementation of machine learning in clinical practice for cardiovascular diseases and other disease areas.

Sex-Specific Patterns of Mortality Predictors Among Patients Undergoing Cardiac Resynchronization Therapy: A Machine Learning Approach

Background: The relative importance of variables explaining sex-related differences in outcomes is scarcely explored in patients undergoing cardiac resynchronization therapy (CRT). We sought to implement and evaluate machine learning (ML) algorithms for the prediction of 1- and 3-year all-cause mortality in CRT patients. We also aimed to assess the sex-specific differences in predictors of mortality utilizing ML. Methods: Using a retrospective registry of 2,191 CRT patients, ML models were implemented in 6 partially overlapping patient subsets (all patients, females, or males with 1- or 3-year follow-up). Each cohort was randomly split into training (80%) and test sets (20%). After hyperparameter tuning in the training sets, the best performing algorithm was evaluated in the test sets. Model discrimination was quantified using the area under the receiver-operating characteristic curves (AUC). The most important predictors were identified using the permutation feature importances method. Results: Conditional inference random forest exhibited the best performance with AUCs of 0.728 (0.645-0.802) and 0.732 (0.681-0.784) for the prediction of 1- and 3-year mortality, respectively. Etiology of heart failure, NYHA class, left ventricular ejection fraction, and QRS morphology had higher predictive power, whereas hemoglobin was less important in females compared to males. The importance of atrial fibrillation and age increased, while the importance of serum creatinine decreased from 1- to 3-year follow-up in both sexes. Conclusions: Using ML techniques in combination with easily obtainable clinical features, our models effectively predicted 1- and 3-year all-cause mortality in CRT patients. Sex-specific patterns of predictors were identified, showing a dynamic variation over time.

Machine-Learning-Based In-Hospital Mortality Prediction for Transcatheter Mitral Valve Repair in the United States

BACKGROUND

Transcatheter mitral valve repair (TMVR) utilization has increased significantly in the United States over the last years. Yet, a risk-prediction tool for adverse events has not been developed. We aimed to generate a machine-learning-based algorithm to predict in-hospital mortality after TMVR.

METHODS

Patients who underwent TMVR from 2012 through 2015 were identified using the National Inpatient Sample database. The study population was randomly divided into a training set (n = 636) and a testing set (n = 213). Prediction models for in-hospital mortality were obtained using five supervised machine-learning classifiers.

RESULTS

A total of 849 TMVRs were analyzed in our study. The overall in-hospital mortality was 3.1%. A naïve Bayes (NB) model had the best discrimination for fifteen variables, with an area under the receiver-operating curve (AUC) of 0.83 (95% CI, 0.80-0.87), compared to 0.77 for logistic regression (95% CI, 0.58-0.95), 0.73 for an artificial neural network (95% CI, 0.55-0.91), and 0.67 for both a random forest and a support-vector machine (95% CI, 0.47-0.87). History of coronary artery disease, of chronic kidney disease, and smoking were the three most significant predictors of in-hospital mortality.

CONCLUSIONS

We developed a robust machine-learning-derived model to predict in-hospital mortality in patients undergoing TMVR. This model is promising for decision-making and deserves further clinical validation.

Establishment and validation of a risk model for prediction of in-hospital mortality in patients with acute ST-elevation myocardial infarction after primary PCI

Background

Currently, how to accurately determine the patient prognosis after a percutaneous coronary intervention (PCI) remains unclear and may vary among populations, hospitals, and datasets. The aim of this study was to establish a prediction model of in-hospital mortality risk after primary PCI in patients with acute ST-elevated myocardial infarction (STEMI).

Methods

This was a multicenter, observational study of patients with acute STEMI who underwent primary PCI. The outcome was in-hospital mortality. The least absolute shrinkage and selection operator (LASSO) method was used to select the features that were the most significantly associated with the outcome. A regression model was built using the selected variables to select the significant predictors of mortality. Receiver operating characteristic (ROC) curve and decision curve analysis (DCA) were used to evaluate the performance of the nomogram.

Results

Totally, 1169 and 316 patients were enrolled in the training and validation sets, respectively. Fourteen predictors were identified by the LASSO analysis: sex, Killip classification, left main coronary artery disease (LMCAD), grading of thrombus, TIMI classification, slow flow, application of IABP, administration of β-blocker, ACEI/ARB, symptom-to-door time (SDT), symptom-to-balloon time (SBT), syntax score, left ventricular ejection fraction (LVEF), and CK-MB peak. The mortality risk prediction nomogram achieved good discrimination for in-hospital mortality (training set: C-statistic = 0.987; model calibration: P = 0.722; validation set: C-statistic = 0.984, model calibration: P = 0.669). Area under the curve (AUC) values for the training and validation sets are 0.987 (95% CI: 0.981–0.994, P = 0.003) and 0.990 (95% CI: 0.987–0.998, P = 0.007), respectively. DCA shows that the nomogram can achieve good net benefit.

Conclusions

A novel nomogram was developed and is a simple and accurate tool for predicting the risk of in-hospital mortality in patients with acute STEMI who underwent primary PCI.

A note on the interpretation of tree-based regression models

Tree-based models are a popular tool for predicting a response given a set of explanatory variables when the regression function is characterized by a certain degree of complexity. Sometimes, they are also used to identify important variables and for variable selection. We show that if the generating model contains chains of direct and indirect effects, then the typical variable importance measures suggest selecting as important mainly the background variables, which have a strong indirect effect, disregarding the variables that directly influence the response. This is attributable mainly to the variable choice in the first steps of the algorithm selecting the splitting variable and to the greedy nature of such search. This pitfall could be relevant when using tree-based algorithms for understanding the underlying generating process, for population segmentation and for causal inference.

Proposed Requirements for Cardiovascular Imaging-Related Machine Learning Evaluation (PRIME): A Checklist: Reviewed by the American College of Cardiology Healthcare Innovation Council

Machine learning (ML) has been increasingly used within cardiology, particularly in the domain of cardiovascular imaging. Due to the inherent complexity and flexibility of ML algorithms, inconsistencies in the model performance and interpretation may occur. Several review articles have been recently published that introduce the fundamental principles and clinical application of ML for cardiologists. This paper builds on these introductory principles and outlines a more comprehensive list of crucial responsibilities that need to be completed when developing ML models. This paper aims to serve as a scientific foundation to aid investigators, data scientists, authors, editors, and reviewers involved in machine learning research with the intent of uniform reporting of ML investigations. An independent multidisciplinary panel of ML experts, clinicians, and statisticians worked together to review the theoretical rationale underlying 7 sets of requirements that may reduce algorithmic errors and biases. Finally, the paper summarizes a list of reporting items as an itemized checklist that highlights steps for ensuring correct application of ML models and the consistent reporting of model specifications and results. It is expected that the rapid pace of research and development and the increased availability of real-world evidence may require periodic updates to the checklist.

Determinants of In-Hospital Mortality After Percutaneous Coronary Intervention: A Machine Learning Approach

Background

The ability to accurately predict the occurrence of in‐hospital death after percutaneous coronary intervention is important for clinical decision‐making. We sought to utilize the New York Percutaneous Coronary Intervention Reporting System in order to elucidate the determinants of in‐hospital mortality in patients undergoing percutaneous coronary intervention across New York State.

Methods and Results

We examined 479 804 patients undergoing percutaneous coronary intervention between 2004 and 2012, utilizing traditional and advanced machine learning algorithms to determine the most significant predictors of in‐hospital mortality. The entire data were randomly split into a training (80%) and a testing set (20%). Tuned hyperparameters were used to generate a trained model while the performance of the model was independently evaluated on the testing set after plotting a receiver‐operator characteristic curve and using the output measure of the area under the curve (AUC) and the associated 95% CIs. Mean age was 65.2±11.9 years and 68.5% were women. There were 2549 in‐hospital deaths within the patient population. A boosted ensemble algorithm (AdaBoost) had optimal discrimination with AUC of 0.927 (95% CI 0.923–0.929) compared with AUC of 0.913 for XGBoost (95% CI 0.906–0.919, P=0.02), AUC of 0.892 for Random Forest (95% CI 0.889–0.896, P<0.01), and AUC of 0.908 for logistic regression (95% CI 0.907–0.910, P<0.01). The 2 most significant predictors were age and ejection fraction.

Conclusions

A big data approach that utilizes advanced machine learning algorithms identifies new associations among risk factors and provides high accuracy for the prediction of in‐hospital mortality in patients undergoing percutaneous coronary intervention.

See Editorial by Garratt and Schneider