No abstract

No abstract

Background Risk stratification in ST-elevation myocardial infarction (STEMI) that is population-specific is essential. Conventional risk stratification methods such Thrombolysis in Myocardial Infarction (TIMI) score is used to evaluate the risk associated with the acute coronary syndrome (ACS) which are derived from Western Caucasian cohort with a limited participant from the Asian region. In Malaysia, multi-ethnic developing country, patients presenting with STEMI are younger, have a much higher prevalence of diabetes, hypertension and renal failure, and present later to medical care than their western counterparts. Purpose We aim to investigate the predictors, predict mortality and develop a risk stratification tool for short and long term mortality in multi-ethnic STEMI patients using machine learning (ML) method. Methods We created three separate mortality prediction models using support vector machine (SVM) to identify predictors and predict mortality for in-hospital, 30-days and 1-year for STEMI patients. We used registry data from the National Cardiovascular Disease Database of 6299 patient's data for in-hospital, 3130 for 30-days and 2939 for 1-year for ML model development. Fifty parameters including demographics, cardiovascular risk, medications and clinical variables were utilised for training the models. The Area under the curve (AUC) was used as the primary performance evaluation metric. All models were validated against conventional method TIMI and tested using testing data. SVM variable importance method were used to select and rank important variables. We converted the final algorithm into an online tool with a database for continuous algorithm validation. We implemented the online calculator in selected hospitals for further testing using prospective patients data. Results The calculator is available at http://myheartstemi.uitm.edu.my. The calculator outperforms TIMI on testing data for in-hospital (15 predictors) (AUC=0.88 vs 0.81), 30 days (12 predictors) (AUC=0.90 vs 0.80) and 1-year (13 predictors) (AUC=0.84 vs 0.76). Common predictors for in-hospital, 30 days and 1-year mortality model identified in this study are; age, heart rate, Killip class, fasting blood glucose and diuretics. Invasive and less invasive treatments such as PCI pharmacotherapy drugs are also selected as important variables that improve mortality prediction. Our results also suggest that TIMI score underestimates patients risk of mortality. 90% of non-survival patients are classified as high risk (>30%) by the calculator compared 10–30% non-survival patients by TIMI. Conclusions In the multi-ethnicity population, patients with STEMI are better classified using ML method compared to the TIMI score. ML allows identification of distinct factors in unique ASIAN population for better mortality prediction. Availability of population-specific calculator and continuous testing and validation allows better risk stratification. Machine learning and TIMI performance Funding Acknowledgement Type of funding source: Public Institution(s). Main funding source(s): University of Malaya Grant

Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): TECHNOLOGY DEVELOPMENT FUND 1 Background Diabetes has become a major public health concern in Asia. In Malaysia, the prevalence of diabetes has escalated in adults above the age of 18, affecting 3.9  million individuals. Patients with diabetes and coronary heart disease have worse outcomes, compared with patients without diabetes who have coronary heart disease. Conventional Risk scores such as TIMI and GRACE were derived from a Western Caucasian cohort with limited data from  Asian countries, despite Asia hosting 60% of the world’s population. Purpose It is important to recognize the significant features associated with in-hospital mortality risk that is population-specific in Asian diabetes patients with STEMI to achieve a reliable and effective clinical diagnosis and improved outcome. Electronic health records contain large amounts of information on patients’ medical history and are becoming invaluable research tools that could be applied to cardiovascular disease risk prediction through machine learning (ML) algorithms. With the current success of ML  over conventional methods in STEMI mortality prediction, we aim to develop ML algorithms for in-hospital risk mortality in Asian patients diagnosed with DM that can be adopted for clinical predictions Methods We used registry data from the Malaysian National Cardiovascular Disease Database of 5783 patients diagnosed with DM from 2006 to 2016. Fifty parameters including demographics, cardiovascular risk, medications and clinical variables were considered. Four machine learning (ML) algorithms were constructed using a 70% registry dataset; Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Booster (XGB) and Logistic Regression (LR). Feature selections were done based on ML algorithms feature importance combined with Sequential Backward Selection (SBS). The area under the curve (AUC)  was used as the performance evaluation metric. All algorithms were validated using a 30 % validation dataset and compared to the conventional TIMI risk score for STEMI. Results The best model SVM (AUC = 0.90) outperformed other ML algorithms (Figure 1) and TIMI risk score (AUC = 0.83). The best SVM model consists of 11 predictors which are Killip class, fasting blood glucose, age, systolic blood pressure, heart rate, ACE inhibitor, beta-blocker, total cholesterol, diastolic blood pressure, lower density lipoprotein, and diuretic (Figure 2). Common predictors of SVM and TIMI risk score are Killip class, age, systolic blood pressure, and heart rate. We have shown that the population-specific data mining approach for the prediction of diabetes patients’ mortality post-STEMI outperformed conventional TIMI risk score. Conclusion In the Asian multiethnic population, combination of ML approaches with features selection demonstrated promising outcomes in patients with DM that may be used for better patient prognostic than the conventional method. Abstract Figure 1: ML Best Model Performance  Abstract Figure 2: Selected Predictors for ML

No abstract