METHODS: Revascularised acute myocardial infarction patients with normal left ventricular (LV) systolic function on TTE were assessed by 1.5T CMR. Acute regional diastolic wall motion abnormalities, global diastolic function measurements, acute segmental damage fraction with LGE and mean segmental pre-contrast T1 values were assessed on matching short axis slices.

RESULTS: Forty-four patients were analysed. Mean LVEF was 62.1±9.4%. No difference between NSTEMI (22/44) and STEMI in mean pre-contrast T1 values of infarcted (1025.0±109.2 vs 1011.0±81.6ms, p=0.70), adjacent (948.3±45.3 vs 941.1±46.6ms, p=0.70) and remote (888.8±52.8 vs 881.2±54.5ms, p=0.66) segments was detected. There was no correlation between pre-contrast T1 of infarcted segments with global diastolic dysfunction (E/A, r(2)=0.216, p=0.06; S/D, r(2)=0.243, p=0.053; E/E', r(2)=0.240, p=0.072), but there was significantly positive, moderate correlation with circumferential diastolic strain rate, (r(2)=0.579, p<0.01) with excellent agreement and reproducibility.

CLINICAL PRESENTATION AND INTERVENTION: A 41-year-old man with previous bilateral pheochromocytoma presented with chest pain. He was suffering from cardiac failure and persistent hypotension requiring an inotrope. Cardiac markers, an electrocardiogram and an echocardiogram confirmed acute myocardial infarct with poor ejection fraction and global hypokinesia. An (18)F-fluorodeoxyglucose PET/CT scan showed progressive left suprarenal and organ of Zuckerkandl pheochromocytomas. Blood pressure stabilisation proved challenging but was achieved by titrating an incremental dose of α-blocker against a tapering inotropic dose.

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.

MAIN METHODS: Male Sprague-Dawley rats were fed with either normal diet or high-fat diet for 8weeks. Firstly, OB rats were divided into (1) OB and (2) OB+R (100mg/kg, p.o, 28days). Then, OB rats were subjected to MI (ISO, 85mg/kg, s.c, 2days) and divided into three groups: (1) OB+MI, (2) OB+MI+R and (3) OB+MI+enalapril for another 4weeks.

KEY FINDINGS: Roselle ameliorated OB and OB+MI's cardiac systolic dysfunction and reduced cardiac hypertrophy and fibrosis. The increased oxidative markers and decreased antioxidant enzymes in OB and OB+MI groups were all attenuated by roselle.