Dataset Information

Machine learning enhances the performance of short and long-term mortality prediction model in non-ST-segment elevation myocardial infarction.

ABSTRACT: Machine learning (ML) has been suggested to improve the performance of prediction models. Nevertheless, research on predicting the risk in patients with acute myocardial infarction (AMI) has been limited and showed inconsistency in the performance of ML models versus traditional models (TMs). This study developed ML-based models (logistic regression with regularization, random forest, support vector machine, and extreme gradient boosting) and compared their performance in predicting the short- and long-term mortality of patients with AMI with those of TMs with comparable predictors. The endpoints were the in-hospital mortality of 14,183 participants and the three- and 12-month mortality in patients who survived at discharge. The performance of the ML models in predicting the mortality of patients with an ST-segment elevation myocardial infarction (STEMI) was comparable to the TMs. In contrast, the areas under the curves (AUC) of the ML models for non-STEMI (NSTEMI) in predicting the in-hospital, 3-month, and 12-month mortality were 0.889, 0.849, and 0.860, respectively, which were superior to the TMs, which had corresponding AUCs of 0.873, 0.795, and 0.808. Overall, the performance of the predictive model could be improved, particularly for long-term mortality in NSTEMI, from the ML algorithm rather than using more clinical predictors.

SUBMITTER: Lee W

PROVIDER: S-EPMC8213755 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundConventional risk score for predicting short and long-term mortality following an ST-segment elevation myocardial infarction (STEMI) is often not population specific.ObjectiveApply machine learning for the prediction and identification of factors associated with short and long-term mortality in Asian STEMI patients and compare with a conventional risk score.MethodsThe National Cardiovascular Disease Database for Malaysia registry, of a multi-ethnic, heterogeneous Asian population was used for in-hospital (6299 patients), 30-days (3130 patients), and 1-year (2939 patients) model development. 50 variables were considered. Mortality prediction was analysed using feature selection methods with machine learning algorithms and compared to Thrombolysis in Myocardial Infarction (TIMI) score. Invasive management of varying degrees was selected as important variables that improved mortality prediction.ResultsModel performance using a complete and reduced variable produced an area under the receiver operating characteristic curve (AUC) from 0.73 to 0.90. The best machine learning model for in-hospital, 30 days, and 1-year outperformed TIMI risk score (AUC = 0.88, 95% CI: 0.846-0.910; vs AUC = 0.81, 95% CI:0.772-0.845, AUC = 0.90, 95% CI: 0.870-0.935; vs AUC = 0.80, 95% CI: 0.746-0.838, AUC = 0.84, 95% CI: 0.798-0.872; vs AUC = 0.76, 95% CI: 0.715-0.802, p < 0.0001 for all). TIMI score underestimates patients' risk of mortality. 90% of non-survival patients are classified as high risk (>50%) by machine learning algorithm compared to 10-30% non-survival patients by TIMI. Common predictors identified for short- and long-term mortality were age, heart rate, Killip class, fasting blood glucose, prior primary PCI or pharmaco-invasive therapy and diuretics. The final algorithm was converted into an online tool with a database for continuous data archiving for algorithm validation.ConclusionsIn a multi-ethnic population, patients with STEMI were better classified using the machine learning method compared to TIMI scoring. Machine learning allows for the identification of distinct factors in individual Asian populations for better mortality prediction. Ongoing continuous testing and validation will allow for better risk stratification and potentially alter management and outcomes in the future.

Project description:ImportanceChallenges to improving ST-segment elevation myocardial infarction (STEMI) care are formidable in low- to middle-income countries because of several system-level factors.ObjectiveTo examine access to reperfusion and percutaneous coronary intervention (PCI) during STEMI using a hub-and-spoke model.Design, setting, and participantsThis multicenter, prospective, observational study of a quality improvement program studied 2420 patients 20 years or older with symptoms or signs consistent with STEMI at primary care clinics, small hospitals, and PCI hospitals in the southern state of Tamil Nadu in India. Data were collected from the 4 clusters before implementation of the program (preimplementation data). We required a minimum of 12 weeks for the preimplementation data with the period extending from August 7, 2012, through January 5, 2013. The program was then implemented in a sequential manner across the 4 clusters, and data were collected in the same manner (postimplementation data) from June 12, 2013, through June 24, 2014, for a mean 32-week period.ExposuresCreation of an integrated, regional quality improvement program that linked the 35 spoke health care centers to the 4 large PCI hub hospitals and leveraged recent developments in public health insurance schemes, emergency medical services, and health information technology.Main outcomes and measuresPrimary outcomes focused on the proportion of patients undergoing reperfusion, timely reperfusion, and postfibrinolysis angiography and PCI. Secondary outcomes were in-hospital and 1-year mortality.ResultsA total of 2420 patients with STEMI (2034 men [84.0%] and 386 women [16.0%]; mean [SD] age, 54.7 [12.2] years) (898 in the preimplementation phase and 1522 in the postimplementation phase) were enrolled, with 1053 patients (43.5%) from the spoke health care centers. Missing data were common for systolic blood pressure (213 [8.8%]), heart rate (223 [9.2%]), and anterior MI location (279 [11.5%]). Overall reperfusion use and times to reperfusion were similar (795 [88.5%] vs 1372 [90.1%]; P = .21). Coronary angiography (314 [35.0%] vs 925 [60.8%]; P < .001) and PCI (265 [29.5%] vs 707 [46.5%]; P < .001) were more commonly performed during the postimplementation phase. In-hospital mortality was not different (52 [5.8%] vs 85 [5.6%]; P = .83), but 1-year mortality was lower in the postimplementation phase (134 [17.6%] vs 179 [14.2%]; P = .04), and this difference remained consistent after multivariable adjustment (adjusted odds ratio, 0.76; 95% CI, 0.58-0.98; P = .04).Conclusions and relevanceA hub-and-spoke model in South India improved STEMI care through greater use of PCI and may improve 1-year mortality. This model may serve as an example for developing STEMI systems of care in other low- to middle-income countries.

Project description:BackgroundMachine learning (ML) risk prediction models, although much more accurate than traditional statistical methods, are inconvenient to use in clinical practice due to their nontransparency and requirement of a large number of input variables.ObjectiveWe aimed to develop a precise, explainable, and flexible ML model to predict the risk of in-hospital mortality in patients with ST-segment elevation myocardial infarction (STEMI).MethodsThis study recruited 18,744 patients enrolled in the 2013 China Acute Myocardial Infarction (CAMI) registry and 12,018 patients from the China Patient-Centered Evaluative Assessment of Cardiac Events (PEACE)-Retrospective Acute Myocardial Infarction Study. The Extreme Gradient Boosting (XGBoost) model was derived from 9616 patients in the CAMI registry (2014, 89 variables) with 5-fold cross-validation and validated on both the 9125 patients in the CAMI registry (89 variables) and the independent China PEACE cohort (10 variables). The Shapley Additive Explanations (SHAP) approach was employed to interpret the complex relationships embedded in the proposed model.ResultsIn the XGBoost model for predicting all-cause in-hospital mortality, the variables with the top 8 most important scores were age, left ventricular ejection fraction, Killip class, heart rate, creatinine, blood glucose, white blood cell count, and use of angiotensin-converting enzyme inhibitors (ACEIs) and angiotensin II receptor blockers (ARBs). The area under the curve (AUC) on the CAMI validation set was 0.896 (95% CI 0.884-0.909), significantly higher than the previous models. The AUC for the Global Registry of Acute Coronary Events (GRACE) model was 0.809 (95% CI 0.790-0.828), and for the TIMI model, it was 0.782 (95% CI 0.763-0.800). Despite the China PEACE validation set only having 10 available variables, the AUC reached 0.840 (0.829-0.852), showing a substantial improvement to the GRACE (0.762, 95% CI 0.748-0.776) and TIMI (0.789, 95% CI 0.776-0.803) scores. Several novel and nonlinear relationships were discovered between patients' characteristics and in-hospital mortality, including a U-shape pattern of high-density lipoprotein cholesterol (HDL-C).ConclusionsThe proposed ML risk prediction model was highly accurate in predicting in-hospital mortality. Its flexible and explainable characteristics make the model convenient to use in clinical practice and could help guide patient management.Trial registrationClinicalTrials.gov NCT01874691; https://clinicaltrials.gov/study/NCT01874691.

Dataset Information

Machine learning enhances the performance of short and long-term mortality prediction model in non-ST-segment elevation myocardial infarction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets