HYPOTHESIS: There is wide variability in AMP use for ACS management in Asia.
METHODS: EPICOR Asia (NCT01361386) is a prospective observational study of patients discharged after hospitalization for an ACS in eight countries/regions in Asia, followed up for 2 years. Here, we describe AMPs used and present an exploratory analysis of characteristics and outcomes in patients who received DAPT for ≤12 months post discharge compared with >12 months.
RESULTS: Data were available for 12 922 patients; of 11 639 patients discharged on DAPT, 2364 (20.3%) received DAPT for ≤12 months and 9275 (79.7%) for >12 months, with approximately 60% still on DAPT at 2 years. Patients who received DAPT for >12 months were more likely to be younger, obese, lower Killip class, resident in India (vs China), and to have received invasive reperfusion. Clinical event rates during year 2 of follow-up were lower in patients with DAPT >12 vs ≤12 months, but no causal association can be implied in this non-randomized study.
CONCLUSIONS: Most ACS patients remained on DAPT up to 1 year, in accordance with current guidelines, and over half remained on DAPT at 2 years post discharge. Patients not on DAPT at 12 months are a higher risk group requiring careful monitoring.
Methods: All patients admitted into our centre were screened for eligibility and those who underwent surgery from September 2016 to September 2017 had a D-dimer screening after surgery, followed by an ultrasound Doppler if the former was positive. The choice of anticoagulant therapy was not influenced by this study, and observation of the use was in keeping with usual practices in our centre was done.
Results: A total number of 331 patients were recruited in this study, however, after the inclusion and exclusion criteria had been met, 320 patients remained eligible, i.e. suitable for analysis. The mean age of our patients was 46 years, with 66% being male patients. A majority of the cases in this study were cranial related, with only 5% being spine surgeries. On the multivariate analysis, the Well's score and the number of days in bed remained statistically significant, after adjusting for age group, gender, ethnicity, type of central venous access and type of DVT prophylaxis with an adjusted odd's ratio, and a confidence interval of 95%, and P < 0.05 for each.
Conclusion: Well's scoring and number of days in bed were independent factors affecting the rate of DVT in patients undergoing neurosurgical procedures in our centre.
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.