OBJECTIVES: This study developed a model that predicted 30-day mortality for acute myocardial infarction (AMI) and compared the SMR among 41 Malaysian public hospitals using statistical process control charts.
METHODS & RESULTS: Data from referral centres and specialist hospitals with cardiology services were analysed. Both referral centres and specialist hospitals had comparable mortality, except for Hospitals A and B, which the study considered outliers. Two-thirds of the remaining hospitals had an SMR of above one (SMR 1.05-1.51), but the indices were still within the expected variations.
CONCLUSION: The SMR coupled with a funnel plot and variable life adjusted display (VLAD) can identify hospitals with potentially higher than expected mortality rates.
OBJECTIVE: To derive a single algorithm using deep learning and machine learning for the prediction and identification of factors associated with in-hospital mortality in Asian patients with ACS and to compare performance to a conventional risk score.
METHODS: The Malaysian National Cardiovascular Disease Database (NCVD) registry, is a multi-ethnic, heterogeneous database spanning from 2006-2017. It was used for in-hospital mortality model development with 54 variables considered for patients with STEMI and Non-STEMI (NSTEMI). Mortality prediction was analyzed using feature selection methods with machine learning algorithms. Deep learning algorithm using features selected from machine learning was compared to Thrombolysis in Myocardial Infarction (TIMI) score.
RESULTS: A total of 68528 patients were included in the analysis. Deep learning models constructed using all features and selected features from machine learning resulted in higher performance than machine learning and TIMI risk score (p < 0.0001 for all). The best model in this study is the combination of features selected from the SVM algorithm with a deep learning classifier. The DL (SVM selected var) algorithm demonstrated the highest predictive performance with the least number of predictors (14 predictors) for in-hospital prediction of STEMI patients (AUC = 0.96, 95% CI: 0.95-0.96). In NSTEMI in-hospital prediction, DL (RF selected var) (AUC = 0.96, 95% CI: 0.95-0.96, reported slightly higher AUC compared to DL (SVM selected var) (AUC = 0.95, 95% CI: 0.94-0.95). There was no significant difference between DL (SVM selected var) algorithm and DL (RF selected var) algorithm (p = 0.5). When compared to the DL (SVM selected var) model, the TIMI score underestimates patients' risk of mortality. TIMI risk score correctly identified 13.08% of the high-risk patient's non-survival vs 24.7% for the DL model and 4.65% vs 19.7% of the high-risk patient's non-survival for NSTEMI. Age, heart rate, Killip class, cardiac catheterization, oral hypoglycemia use and antiarrhythmic agent were found to be common predictors of in-hospital mortality across all ML feature selection models in this study. The final algorithm was converted into an online tool with a database for continuous data archiving for prospective validation.
CONCLUSIONS: ACS patients were better classified using a combination of machine learning and deep learning in a multi-ethnic Asian population when compared to TIMI scoring. Machine learning enables the identification of distinct factors in individual Asian populations to improve mortality prediction. Continuous testing and validation will allow for better risk stratification in the future, potentially altering management and outcomes.
METHODS: Medline and Embase were searched for articles reporting outcomes of ACS patients stratified by SES using a multidimensional index, comprising at least 2 of the following components: Income, Education and Employment. A comparative meta-analysis was conducted using random-effects models to estimate the risk ratio of all-cause mortality in low SES vs high SES populations, stratified according to geographical region, study year, follow-up duration and SES index.
RESULTS: A total of 29 studies comprising of 301,340 individuals were included, of whom 43.7% were classified as low SES. While patients of both SES groups had similar cardiovascular risk profiles, ACS patients of low SES had significantly higher risk of all-cause mortality (adjusted HR:1.19, 95%CI: 1.10-1.1.29, p
METHODS: We conducted a systematic review and meta-analysis of prospective observational studies that have investigated the relationship of door-to-balloon delay and clinical outcomes. The main outcomes include mortality and heart failure.
RESULTS: 32 studies involving 299 320 patients contained adequate data for quantitative reporting. Patients with ST-elevation MI who experienced longer (>90 min) door-to-balloon delay had a higher risk of short-term mortality (pooled OR 1.52, 95% CI 1.40 to 1.65) and medium-term to long-term mortality (pooled OR 1.53, 95% CI 1.13 to 2.06). A non-linear time-risk relation was observed (P=0.004 for non-linearity). The association between longer door-to-balloon delay and short-term mortality differed between those presented early and late after symptom onset (Cochran's Q 3.88, P value 0.049) with a stronger relationship among those with shorter prehospital delays.
CONCLUSION: Longer door-to-balloon delay in primary percutaneous coronary intervention for ST-elevation MI is related to higher risk of adverse outcomes. Prehospital delays modified this effect. The non-linearity of the time-risk relation might explain the lack of population effect despite an improved door-to-balloon time in the USA.
CLINICAL TRIAL REGISTRATION: PROSPERO (CRD42015026069).