Improving 1-year mortality prediction in ACS patients using machine learning

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.

Artificial Intelligence of Arterial Doppler Waveforms to Predict Major Adverse Outcomes Among Patients Evaluated for Peripheral Artery Disease

BACKGROUND

Patients with peripheral artery disease are at increased risk for major adverse cardiac events, major adverse limb events, and all-cause death. Developing tools capable of identifying those patients with peripheral artery disease at greatest risk for major adverse events is the first step for outcome prevention. This study aimed to determine whether computer-assisted analysis of a resting Doppler waveform using deep neural networks can accurately identify patients with peripheral artery disease at greatest risk for adverse outcome events.

METHODS AND RESULTS

Consecutive patients (April 1, 2015, to December 31, 2020) undergoing ankle-brachial index testing were included. Patients were randomly allocated to training, validation, and testing subsets (60%/20%/20%). Deep neural networks were trained on resting posterior tibial arterial Doppler waveforms to predict major adverse cardiac events, major adverse limb events, and all-cause death at 5 years. Patients were then analyzed in groups based on the quartiles of each prediction score in the training set. Among 11 384 total patients, 10 437 patients met study inclusion criteria (mean age, 65.8±14.8 years; 40.6% women). The test subset included 2084 patients. During 5 years of follow-up, there were 447 deaths, 585 major adverse cardiac events, and 161 MALE events. After adjusting for age, sex, and Charlson comorbidity index, deep neural network analysis of the posterior tibial artery waveform provided independent prediction of death (hazard ratio [HR], 2.44 [95% CI, 1.78-3.34]), major adverse cardiac events (HR, 1.97 [95% CI, 1.49-2.61]), and major adverse limb events (HR, 11.03 [95% CI, 5.43-22.39]) at 5 years.

CONCLUSIONS

An artificial intelligence-enabled analysis of Doppler arterial waveforms enables identification of major adverse outcomes among patients with peripheral artery disease, which may promote early adoption and adherence of risk factor modification.

Using machine learning to predict adverse events in acute coronary syndrome: A retrospective study

BACKGROUND

Up to 30% of patients with acute coronary syndrome (ACS) die from adverse events, mainly renal failure and myocardial infarction (MI). Accurate prediction of adverse events is therefore essential to improve patient prognosis.

HYPOTHESIS

Machine learning (ML) methods can accurately identify risk factors and predict adverse events.

METHODS

A total of 5240 patients diagnosed with ACS who underwent PCI were enrolled and followed for 1 year. Support vector machine, extreme gradient boosting, adaptive boosting, K-nearest neighbors, random forest, decision tree, categorical boosting, and linear discriminant analysis (LDA) were developed with 10-fold cross-validation to predict acute kidney injury (AKI), MI during hospitalization, and all-cause mortality within 1 year. Features with mean Shapley Additive exPlanations score >0.1 were screened by XGBoost method as input for model construction. Accuracy, F1 score, area under curve (AUC), and precision/recall curve were used to evaluate the performance of the models.

RESULTS

Overall, 2.6% of patients died within 1 year, 4.2% had AKI, and 4.7% had MI during hospitalization. The LDA model was superior to the other seven ML models, with an AUC of 0.83, F1 score of 0.90, accuracy of 0.85, recall of 0.85, specificity of 0.68, and precision of 0.99 in predicting all-cause mortality. For AKI and MI, the LDA model also showed good discriminating capacity with an AUC of 0.74.

CONCLUSION

The LDA model, using easily accessible variables from in-hospital patients, showed the potential to effectively predict the risk of adverse events and mortality within 1 year in ACS patients after PCI.

Effects of SARS-COV-2 infection on outcomes in patients hospitalized for acute cardiac conditions. A prospective, multicenter cohort study (Swiss Cardiovascular SARS-CoV-2 Consortium)

Background

Although the severe acute respiratory syndrome coronavirus 2 (SARS-COV-2) causing coronavirus disease 2019 (COVID-19) primarily affects the respiratory system, the disease entity has been associated with cardiovascular complications. This study sought to assess the effect of concomitant SARS-COV-2 infection on clinical outcomes of patients hospitalized primarily for acute cardiac conditions on cardiology wards in Switzerland.

Methods

In this prospective, observational study conducted in 5 Swiss cardiology centers during the COVID-19 pandemic, patients hospitalized due to acute cardiac conditions underwent a reverse-transcriptase polymerase chain reaction test at the time of admission and were categorized as SARS-COV-2 positive (cases) or negative (controls). Patients hospitalized on cardiology wards underwent treatment for the principal acute cardiac condition according to local practice. Clinical outcomes were recorded in-hospital, at 30 days, and after 1 year and compared between cases and controls. To adjust for imbalanced baseline characteristics, a subgroup of patients derived by propensity matching was analyzed.

Results

Between March 2020 and February 2022, 538 patients were enrolled including 122 cases and 416 controls. Mean age was 68.0 ± 14.7 years, and 75% were men. Compared with controls, SARS-COV-2-positive patients more commonly presented with acute heart failure (35% vs. 17%) or major arrhythmia (31% vs. 9%), but less commonly with acute coronary syndrome (26% vs. 53%) or severe aortic stenosis (4% vs. 18%). Mortality was significantly higher in cases vs. controls in-hospital (16% vs. 1%), at 30 days (19.0% vs. 2.2%), and at 1 year (28.7% vs. 7.6%: p < 0.001 for all); this was driven primarily (up to 30 days) and exclusively (at one-year follow-up) by higher non-cardiovascular mortality, and was accompanied by a greater incidence of worsening renal function in cases vs. controls. These findings were maintained in a propensity-matched subgroup of 186 patients (93 cases and 93 controls) with balanced clinical presentation and baseline characteristics.

Conclusions

In this observational study of patients hospitalized for acute cardiac conditions, SARS-COV-2 infection at index hospitalization was associated with markedly higher all-cause and non-cardiovascular mortality throughout one-year follow-up. These findings highlight the need for effective, multifaceted management of both cardiac and non-cardiac morbidities and prolonged surveillance in patients with acute cardiac conditions complicated by SARS-COV-2 infection.

A bibliometric analysis of acute myocardial infarction in women from 2000 to 2022

Background

Plenty of publications had been written in the last several decades on acute myocardial infarction (AMI) in women. However, there are few bibliometric analyses in such field. In order to solve this problem, we attempted to examine the knowledge structure and development of research about AMI in women based on analysis of related publications.

Method

The Web of Science Core Collection was used to extract all publications regarding AMI in women, ranging from January 2000 to August 2022. Bibliometric analysis was performed using VOSviewer, Cite Space, and an online bibliometric analysis platform.

Results

A total of 14,853 publications related to AMI in women were identified from 2000 to 2022. Over the past 20 years, the United States had published the most articles in international research and participated in international cooperation the most frequently. The primary research institutions were Harvard University and University of Toronto. Circulation was the most cited journal and had an incontrovertible academic impact. 67,848 authors were identified, among which Harlan M Krumholz had the most significant number of articles and Thygesen K was co-cited most often. And the most common keywords included risk factors, disease, prognosis, mortality, criteria and algorithm.

Conclusion

The research hotspots and trends of AMI in women were identified and explored using bibliometric and visual methods. Researches about AMI in women are flourishing. Criteria and algorithms might be the focus of research in the near future, which deserved great attentions.