OBJECTIVE: Apply 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.
METHODS: The 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.
RESULTS: Model 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.
CONCLUSIONS: In 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.
METHODS: We did a network meta-analysis based on a systematic review of randomised controlled trials comparing fibrinolytic drugs in patients with STEMI. Several databases were searched from inception up to Feb 28, 2017. We included only randomised controlled trials that compared fibrinolytic agents as a reperfusion therapy in adult patients with STEMI, whether given alone or in combination with adjunctive antithrombotic therapy, against other fibrinolytic agents, a placebo, or no treatment. Only trials investigating agents with an approved indication of reperfusion therapy in STEMI (streptokinase, tenecteplase, alteplase, and reteplase) were included. The primary efficacy outcome was all-cause mortality within 30-35 days and the primary safety outcome was major bleeding. This study is registered with PROSPERO (CRD42016042131).
FINDINGS: A total of 40 eligible studies involving 128 071 patients treated with 12 different fibrinolytic regimens were assessed. Compared with accelerated infusion of alteplase with parenteral anticoagulants as background therapy, streptokinase and non-accelerated infusion of alteplase were significantly associated with an increased risk of all-cause mortality (risk ratio [RR] 1·14 [95% CI 1·05-1·24] for streptokinase plus parenteral anticoagulants; RR 1·26 [1·10-1·45] for non-accelerated alteplase plus parenteral anticoagulants). No significant difference in mortality risk was recorded between accelerated infusion of alteplase, tenecteplase, and reteplase with parenteral anticoagulants as background therapy. For major bleeding, a tenecteplase-based regimen tended to be associated with lower risk of bleeding compared with other regimens (RR 0·79 [95% CI 0·63-1·00]). The addition of glycoprotein IIb or IIIa inhibitors to fibrinolytic therapy increased the risk of major bleeding by 1·27-8·82-times compared with accelerated infusion alteplase plus parenteral anticoagulants (RR 1·47 [95% CI 1·10-1·98] for tenecteplase plus parenteral anticoagulants plus glycoprotein inhibitors; RR 1·88 [1·24-2·86] for reteplase plus parenteral anticoagulants plus glycoprotein inhibitors).
INTERPRETATION: Significant differences exist among various fibrinolytic regimens as reperfusion therapy in STEMI and alteplase (accelerated infusion), tenecteplase, and reteplase should be considered over streptokinase and non-accelerated infusion of alteplase. The addition of glycoprotein IIb or IIIa inhibitors to fibrinolytic therapy should be discouraged.
FUNDING: None.
METHODS: Hospital admissions for selected diagnoses between 1 February 2021 and 30 September 2021 were linked to the national COVID-19 immunisation register. We conducted self-controlled case-series study by identifying individuals who received COVID-19 vaccine and diagnosis of thrombocytopenia, venous thromboembolism, myocardial infarction, myocarditis/pericarditis, arrhythmia, stroke, Bell's Palsy, and convulsion/seizure. The incidence of events was assessed in risk period of 21 days postvaccination relative to the control period. We used conditional Poisson regression to calculate the incidence rate ratio (IRR) and 95% confidence interval (CI) with adjustment for calendar period.
RESULTS: There was no increase in the risk for myocarditis/pericarditis, Bell's Palsy, stroke, and myocardial infarction in the 21 days following either dose of BNT162b2, CoronaVac, and ChAdOx1 vaccines. A small increased risk of venous thromboembolism (IRR 1.24; 95% CI 1.02, 1.49), arrhythmia (IRR 1.16, 95% CI 1.07, 1.26), and convulsion/seizure (IRR 1.26; 95% CI 1.07, 1.48) was observed among BNT162b2 recipients. No association between CoronaVac vaccine was found with all events except arrhythmia (IRR 1.15; 95% CI 1.01, 1.30). ChAdOx1 vaccine was associated with an increased risk of thrombocytopenia (IRR 2.67; 95% CI 1.21, 5.89) and venous thromboembolism (IRR 2.22; 95% CI 1.17, 4.21).
CONCLUSION: This study shows acceptable safety profiles of COVID-19 vaccines among recipients of BNT162b2, CoronaVac, and ChAdOx1 vaccines. This information can be used together with effectiveness data for risk-benefit analysis of the vaccination program. Further surveillance with more data is required to assess AESIs following COVID-19 vaccination in short- and long-term.
RESULTS: From 1988 to 1997, 13,048 myocardial infarct events were diagnosed with 3367 deaths. There was a 39.1% decline in mortality, with an average decline of 6.5% per year [95% confidence intervals (CI), -3.9% to -9.1%]. However, the decline in incidence was only 20.8% with an average decline of 2.4% per year (95% CI, -6.6% to -1.2%). The highest incidence and mortality rates for both genders were seen in the Indians, followed by the Malays and the Chinese.
CONCLUSION: Over 10 years, from 1988 to 1997, we documented a significant fall in mortality from MI in Singapore. There was a smaller decline in the incidence of infarction. Singapore implemented a National Healthy Lifestyle Programme in 1992 as a 10-year effort. The disparity in the incidence and mortality may suggest that a more dramatic and immediate impact has taken place in mortality through therapeutic programmes; primary preventive programmes would be more difficult to evaluate and have a more gradual impact. Only with continual accurate data collection through the whole country, over a much longer period, can the relative value of preventive and therapeutic programmes in coronary heart disease be assessed.
Design: Case report.
Conclusion: Acquired injury to the right retro-splenial region can result in a specific variant of topographical disorientation known as heading disorientation that may present as an atypical transient ischaemic attack-like symptom heralding acute cerebral infarction.