Predicting two-year survival versus non-survival after first myocardial infarction using machine learning and Swedish national register data

Abstract

BackgroundMachine learning algorithms hold potential for improved prediction of all-cause mortality in cardiovascular patients, yet have not previously been developed with high-quality population data. This study compared four popular machine learning algorithms trained on unselected, nation-wide population data from Sweden to solve the binary classification problem of predicting survival versus non-survival 2 years after first myocardial infarction (MI).MethodsThis prospective national registry study for prognostic accuracy validation of predictive models used data from 51,943 complete first MI cases as registered during 6 years (2006–2011) in the national quality register SWEDEHEART/RIKS-HIA (90% coverage of all MIs in Sweden) with follow-up in the Cause of Death register (> 99% coverage). Primary outcome was AUROC (C-statistic) performance of each model on the untouched test set (40% of cases) after model development on the training set (60% of cases) with the full (39) predictor set. Model AUROCs were bootstrapped and compared, correcting the P-values for multiple comparisons with the Bonferroni method. Secondary outcomes were derived when varying sample size (1–100% of total) and predictor sets (39, 10, and 5) for each model. Analyses were repeated on 79,869 completed cases after multivariable imputation of predictors.ResultsA Support Vector Machine with a radial basis kernel developed on 39 predictors had the highest complete cases performance on the test set (AUROC = 0.845, PPV = 0.280, NPV = 0.966) outperforming Boosted C5.0 (0.845 vs. 0.841, P = 0.028) but not significantly higher than Logistic Regression or Random Forest. Models converged to the point of algorithm indifference with increased sample size and predictors. Using the top five predictors also produced good classifiers. Imputed analyses had slightly higher performance.ConclusionsImproved mortality prediction at hospital discharge after first MI is important for identifying high-risk individuals eligible for intensified treatment and care. All models performed accurately and similarly and because of the superior national coverage, the best model can potentially be used to better differentiate new patients, allowing for improved targeting of limited resources. Future research should focus on further model development and investigate possibilities for implementation.Electronic supplementary materialThe online version of this article (doi:10.1186/s12911-017-0500-y) contains supplementary material, which is available to authorized users.

The tree-species-specific effect of forest bathing on perceived anxiety alleviation of young-adults in urban forests

“…Wilcoxon Score Rank Sum test was employed to compare the difference of scores among forests with different tree species. The significance was adjusted to be P ≤ 0.0167 instead of P ≤ 0.05 by the Bonferroni correction in response to three couples of comparisons (Chi et al 2017, Wallert et al 2017 The demographic characteristics of participants in urban forests dominated by three tree species Table 2 Note. Abbreviations: Details on the questionnaires used in the study Table 3 mographic data in order to detect the effect of the body trait characteristic on their anxiety-state change.…”

Predicting Sudden Deaths Following Myocardial Infarction in Malaysia Using Machine Learning Classifiers

“…To determine which model and algorithm produced better mortality prediction, we measured the performance of the models. The performance of the machine learning prediction is usually compared based on the accuracy [5-6, 8, 12-13, 15], precision [5,13,15], recall [5,8,13,15], and area under the ROC curve (AUC) [6,8,[10][11][13][14]. The performance for each model is recorded in Table 3 and compared.…”

“…The most commonly used machine learning algorithms for predicting the mortality of patients are k-Nearest Neighbors (kNN), Naïve Bayes (NB), Bayesian Network (BN), Neural Network (NN), Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR). Table 1 shows past studies on mortality prediction using various machine learning algorithms [5][6][7][8][9][10][11][12][13][14][15]. Machine learning requires a large set of data to increase the accuracy and reliability of the mortality predictions.…”

Using Artificial Intelligence to Manage Thrombosis Research, Diagnosis, and Clinical Management

“…There are several studies utilizing the AI approach to develop predictive models for MI. [24][25][26][27][28][29][30][31][32] Recently, a group developed an ANN model to predict non-ST elevation myocardial infarction (NSTEMI) patients. 24 The model was trained for several risk attributes such as cardiac risk factor, systolic blood pressure, hemoglobin, corrected QT interval (QTc), PR interval, aspartate aminotransferase, alanine aminotransferase, and cardiac troponin that are independently associated with stable NSTEMI.…”