Ensemble machine learning for predicting in-hospital mortality in Asian women with ST-elevation myocardial infarction (STEMI).

The accurate prediction of in-hospital mortality in Asian women after ST-Elevation Myocardial Infarction (STEMI) remains a crucial issue in medical research. Existing models frequently neglect this demographic's particular attributes, resulting in poor treatment outcomes. This study aims to improve the prediction of in-hospital mortality in multi-ethnic Asian women with STEMI by employing both base and ensemble machine learning (ML) models. We centred on the development of demographic-specific models using data from the Malaysian National Cardiovascular Disease Database spanning 2006 to 2016. Through a careful iterative feature selection approach that included feature importance and sequential backward elimination, significant variables such as systolic blood pressure, Killip class, fasting blood glucose, beta-blockers, angiotensin-converting enzyme inhibitors (ACE), and oral hypoglycemic medications were identified. The findings of our study revealed that ML models with selected features outperformed the conventional Thrombolysis in Myocardial Infarction (TIMI) Risk score, with area under the curve (AUC) ranging from 0.60 to 0.93 versus TIMI's AUC of 0.81. Remarkably, our best-performing ensemble ML model was surpassed by the base ML model, support vector machine (SVM) Linear with SVM selected features (AUC: 0.93, CI: 0.89-0.98 versus AUC: 0.91, CI: 0.87-0.96). Furthermore, the women-specific model outperformed a non-gender-specific STEMI model (AUC: 0.92, CI: 0.87-0.97). Our findings demonstrate the value of women-specific ML models over standard approaches, emphasizing the importance of continued testing and validation to improve clinical care for women with STEMI.

Data analytics approach for short- and long-term mortality prediction following acute non-ST-elevation myocardial infarction (NSTEMI) and Unstable Angina (UA) in Asians.

BACKGROUND: Traditional risk assessment tools often lack accuracy when predicting the short- and long-term mortality following a non-ST-segment elevation myocardial infarction (NSTEMI) or Unstable Angina (UA) in specific population. OBJECTIVE: To employ machine learning (ML) and stacked ensemble learning (EL) methods in predicting short- and long-term mortality in Asian patients diagnosed with NSTEMI/UA and to identify the associated features, subsequently evaluating these findings against established risk scores. METHODS: We analyzed data from the National Cardiovascular Disease Database for Malaysia (2006-2019), representing a diverse NSTEMI/UA Asian cohort. Algorithm development utilized in-hospital records of 9,518 patients, 30-day data from 7,133 patients, and 1-year data from 7,031 patients. This study utilized 39 features, including demographic, cardiovascular risk, medication, and clinical features. In the development of the stacked EL model, four base learner algorithms were employed: eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest (RF), with the Generalized Linear Model (GLM) serving as the meta learner. Significant features were chosen and ranked using ML feature importance with backward elimination. The predictive performance of the algorithms was assessed using the area under the curve (AUC) as a metric. Validation of the algorithms was conducted against the TIMI for NSTEMI/UA using a separate validation dataset, and the net reclassification index (NRI) was subsequently determined. RESULTS: Using both complete and reduced features, the algorithm performance achieved an AUC ranging from 0.73 to 0.89. The top-performing ML algorithm consistently surpassed the TIMI risk score for in-hospital, 30-day, and 1-year predictions (with AUC values of 0.88, 0.88, and 0.81, respectively, all p < 0.001), while the TIMI scores registered significantly lower at 0.55, 0.54, and 0.61. This suggests the TIMI score tends to underestimate patient mortality risk. The net reclassification index (NRI) of the best ML algorithm for NSTEMI/UA patients across these periods yielded an NRI between 40-60% (p < 0.001) relative to the TIMI NSTEMI/UA risk score. Key features identified for both short- and long-term mortality included age, Killip class, heart rate, and Low-Molecular-Weight Heparin (LMWH) administration. CONCLUSIONS: In a broad multi-ethnic population, ML approaches outperformed conventional TIMI scoring in classifying patients with NSTEMI and UA. ML allows for the precise identification of unique characteristics within individual Asian populations, improving the accuracy of mortality predictions. Continuous development, testing, and validation of these ML algorithms holds the promise of enhanced risk stratification, thereby revolutionizing future management strategies and patient outcomes.

Assessing the effect of cardiovascular disease on work productivity and financial loss among school teachers in Peninsular Malaysia: a nested case-control study.

Background: School teachers may have an increased risk of cardiovascular disease (CVD), potentially affecting their work productivity. However, limited data exists on the impact of CVD on teachers' productivity in Malaysia. Our objectives were to assess work productivity loss (absenteeism and presenteeism) as well as to determine the associated annual monetary loss among school teachers who experienced incident CVD in Peninsular Malaysia. Methods: We adopted a nested case-control design within a cohort of school teachers. Working teachers from six states of Peninsular Malaysia, and had experienced incident CVD before a right-censored date (31st December 2021) were defined as cases. Incident CVD was operationally defined as the development of non-fatal acute coronary syndrome (ACS), stroke, congestive cardiac failure, deep vein thrombosis or peripheral arterial disease before the censored date. Controls were working teachers who did not acquire an incident CVD before the similar right-censored date. All controls were randomly selected, with a ratio of one case to four controls, from among the working teachers in one of the states in Peninsular Malaysia. We used a shortened version of the Malay-validated World Health Organization-Health and Work Performance Questionnaire (WHO-HPQ) to estimate the workplace productivity effect among teachers with incident CVD (cases). The same questionnaire was distributed to teachers in a single state of Peninsular Malaysia who did not experience incident CVD (controls). Absenteeism, presenteeism and annual monetary loss were computed based on the scoring rules in the WHO-HPQ. Analysis of covariance was performed with covariate adjustment using propensity scores. The bootstrapping method was applied to obtain better estimates of marginal mean differences, along with standard errors (SE) and appropriate effect sizes. Results: We recruited 48 cases (baseline mean age = 42.4 years old, 54.2% females) and 192 randomly selected controls (baseline mean age = 36.2 years old, 99.0% females). The majority of the cases had ACS (73.9%). No significant difference was observed in absenteeism between cases and controls. The mean self-rated job performance score was lower for cases (7.63, SE = 0.21) compared to controls (8.60, SE = 0.10). Marginal mean scores of absolute presenteeism among cases (76.30) were lower (p < 0.05, eta squared = 0.075) than controls (85.97). The marginal mean annual cost of presenteeism was higher in cases (MYR 21,237.52) compared to controls (MYR 12,089.74) (p < 0.05, eta squared = 0.082). Conclusion: Absolute presenteeism was lower among school teachers who experienced incident CVD and the annual cost of presenteeism was substantial. Implementing supportive work strategies in school settings is recommended to increase absolute presenteeism, which can lead to a reduction in the annual cost of presenteeism among teachers experiencing incident CVD.

Characteristics of patients admitted with heart failure: Insights from the first Malaysian Heart Failure Registry.

AIMS: Heart failure (HF) is a growing health problem, yet there are limited data on patients with HF in Malaysia. The Malaysian Heart Failure (MY-HF) Registry aims to gain insights into the epidemiology, aetiology, management, and outcome of Malaysian patients with HF and identify areas for improvement within the national HF services. METHODS AND RESULTS: The MY-HF Registry is a 3-year prospective, observational study comprising 2717 Malaysian patients admitted for acute HF. We report the description of baseline data at admission and outcomes of index hospitalization of these patients. The mean age was 60.2 ± 13.6 years, 66.8% were male, and 34.3% had de novo HF. Collectively, 55.7% of patients presented with New York Heart Association (NYHA) Class III or IV; ischaemic heart disease was the most frequent aetiology (63.2%). Most admissions (87.3%) occurred via the emergency department, with 13.7% of patients requiring intensive care, and of these, 21.8% needed intubation. The proportion of patients receiving guideline-directed medical therapy increased at discharge (84.2% vs. 93.6%). The median length of stay (LOS) was 5 days, and in-hospital mortality was 2.9%. Predictors of LOS and/or in-hospital mortality were age, NYHA class, estimated glomerular filtration rate, and comorbid anaemia. LOS and in-hospital mortality were similar regardless of ejection fraction. CONCLUSIONS: The MY-HF Registry showed that the HF population in Malaysia is younger, predominantly male, and ischaemic-driven and has good prospects with hospitalization for optimization of treatment. These findings suggest a need to reassess current clinical practice and guide resource allocation to improve patient outcomes.

Crystalline sirolimus-coated balloon (cSCB) angioplasty in an all-comers, patient population with stable and unstable coronary artery disease including chronic total occlusions: rationale, methodology and design of the SCORE trial.

BACKGROUND: A decade ago, the iopromide-paclitaxel coated balloon (iPCB) was added to the cardiologist's toolbox to initially treat in-stent restenosis followed by the treatment of de novo coronary lesions. In the meantime, DES technologies have been substantially improved to address in-stent restenosis and thrombosis, and shortened anti-platelet therapy. Recently, sirolimus-coated balloon catheters (SCB) have emerged to provide an alternative drug to combat restenosis. METHODS: The objective of this study is to determine the safety and efficacy of a novel crystalline sirolimus-coated balloon (cSCB) technology in an unselective, international, large-scale patient population. Percutaneous coronary interventions of native stenosis, in-stent stenosis, and chronic total occlusions with the SCB in patients with stable coronary artery disease or acute coronary syndrome were included. The primary outcome variable is the target lesion failure (TLF) rate at 12 months, defined as the composite rate of target vessel myocardial infarction (TV-MI), cardiac death or ischemia-driven target lesion revascularization (TLR). The secondary outcome variables include TLF at 24 months, ischemia driven TLR at 12 and 24 months and all-cause death, cardiac death at 12 and 24 months. DISCUSSION: Since there is a wealth of patient-based all-comers data for iPCB available for this study, a propensity-score matched analysis is planned to compare cSCB and iPCB for the treatment of de novo and different types of ISR. In addition, pre-specified analyses in challenging lesion subsets such as chronic total occlusions will provide evidence whether the two balloon coating technologies differ in their clinical benefit for the patient. TRIAL REGISTRATION NUMBER: ClinicalTrials.gov Identifier: NCT04470934.

Genetic Markers of Insulin Resistance and Atherosclerosis in Type 2 Diabetes Mellitus Patients with Coronary Artery Disease.

Type 2 diabetes mellitus (T2DM) is characterized by impaired insulin secretion on a background of insulin resistance (IR). IR and T2DM are associated with atherosclerotic coronary artery disease (CAD). The mechanisms of IR and atherosclerosis are known to share similar genetic and environmental roots. Endothelial dysfunction (ED) detected at the earliest stages of IR might be the origin of atherosclerosis progression. ED influences the secretion of pro-inflammatory cytokines and their encoding genes. The genes and their single nucleotide polymorphisms (SNPs) act as potential genetic markers of IR and atherosclerosis. This review focuses on the link between IR, T2DM, atherosclerosis, CAD, and the potential genetic markers CHI3L1, CD36, LEPR, RETN, IL-18, RBP-4, and RARRES2 genes.

Current Insights on Dyslipidaemia Management for Prevention of Atherosclerotic Cardiovascular Disease: A Malaysian Perspective.

Dyslipidaemia is highly prevalent in the Malaysian population and is one of the main risk factors for atherosclerotic cardiovascular disease (ASCVD). Low-density lipoprotein cholesterol (LDL-C) is recognised as the primary target of lipid-lowering therapy to reduce the disease burden of ASCVD. Framingham General CV Risk Score has been validated in the Malaysian population for CV risk assessment. The Clinical Practice Guidelines (CPG) on the management of dyslipidaemia were last updated in 2017. Since its publication, several newer randomised clinical trials have been conducted with their results published in research articles and compared in meta-analysis. This underscores a need to update the previous guidelines to ensure good quality care and treatment for the patients. This review summarises the benefits of achieving LDL-C levels lower than the currently recommended target of < 1.8mmol/L without any safety concerns. In most high and very high-risk individuals, statins are the first line of therapy for dyslipidaemia management. However, certain high-risk individuals are not able to achieve the LDL-C goal as recommended in the guideline even with high-intensity statin therapy. In such individuals, lower LDL-C levels can be achieved by combining the statins with non-statin agents such as ezetimibe and PCSK9 inhibitors. Emerging non-statin lipid-lowering therapies and challenges in dyslipidaemia management are discussed in this article. The review also summarises the recent updates on local and international guidelines for dyslipidaemia management.

From Primary to Tertiary Care: Expert Position Statements to Guide Heart Failure with Preserved Ejection Fraction Diagnosis.

Globally, heart failure with preserved ejection fraction (HFpEF) is quickly becoming the dominant form of heart failure (HF) in ageing populations. However, there are still multiple gaps and challenges in making a firm diagnosis of HFpEF in many low-to-middle income Asian countries. In response to this unmet need, the Malaysian HFpEF Working Group (MY-HPWG) gathered and reviewed evidence surrounding the use of different diagnostic modalities indicated for patients with HFpEF to identify diagnostic tools that could be conveniently accessed across different healthcare settings. As a result, five recommendation statements were proposed and an accompanying algorithm was developed, with the aim of improving the diagnostic rate of HFpEF. The MY-HPWG recommends using more easily accessible and non-invasive tools, such as natriuretic peptide (NP) biomarkers and basic echocardiogram (ECHO), to ensure timely HFpEF diagnosis in the primary and secondary care settings, and prompt referral to a tertiary care centre for more comprehensive assessments in uncertain cases.

Harmonising Individual Patient Level Cardiac Registry Data Across the Asia Pacific Region-A Feasibility Study of In-Hospital Outcomes of STEMI Patients From the Asia Pacific Evaluation of Cardiovascular Therapies (ASPECT) Network.

OBJECTIVE: The Asia-Pacific Evaluation of Cardiovascular Therapies (ASPECT) collaboration was established to inform on percutaneous coronary intervention (PCI) in the Asia-Pacific Region. Our aims were to (i) determine the operational requirements to assemble an international individual patient dataset and validate the processes of governance, data quality and data security, and subsequently (ii) describe the characteristics and outcomes for ST-elevation myocardial infarction (STEMI) patients undergoing PCI in the ASPECT registry. METHODS: Seven (7) ASPECT members were approached to provide a harmonised anonymised dataset from their local registry. Patient characteristics were summarised and associations between the characteristics and in-hospital outcomes for STEMI patients were analysed. RESULTS: Six (6) participating sites (86%) provided governance approvals for the collation of individual anonymised patient data from 2015 to 2017. Five (5) sites (83%) provided >90% of agreed data elements and 68% of the collated elements had <10% missingness. From the registry (n=12,620), 84% were male. The mean age was 59.2±12.3 years. The Malaysian cohort had a high prevalence of previous myocardial infarction (34%), almost twice that of any other sites (p<0.001). Adverse in-hospital outcomes were the lowest in Hong Kong whilst in-hospital mortality varied from 2.7% in Vietnam to 7.9% in Singapore. CONCLUSIONS: Governance approvals for the collation of individual patient anonymised data was achieved with a high level of data alignment. Secure data transfer process and repository were established. Patient characteristics and presentation varied significantly across the Asia-Pacific region with this likely to be a major predictor of variations in the clinical outcomes observed across the region.

In-hospital mortality risk stratification of Asian ACS patients with artificial intelligence algorithm.

BACKGROUND: Conventional risk score for predicting in-hospital mortality following Acute Coronary Syndrome (ACS) is not catered for Asian patients and requires different types of scoring algorithms for STEMI and NSTEMI patients. 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.

Combined Analysis of Two Parallel Randomized Trials of Sirolimus-Coated and Paclitaxel-Coated Balloons in Coronary In-Stent Restenosis Lesions.

BACKGROUND: Paclitaxel-coated balloons (PCBs) are a preferred treatment option for coronary in-stent restenosis. To date, data from randomized trials of alternative drug coatings are lacking. The aim of the randomized Malaysian and German-Swiss randomized trials was to investigate a novel sirolimus-coated balloon (SCB) compared with a PCB in in-stent restenosis. METHODS: One hundred one patients with drug-eluting stent in-stent restenosis were enrolled in 2 identical randomized trials comparing the novel SCB (SeQuent SCB, 4 µg/mm²) with the clinically proven PCB (SeQuent Please, 3 µg/mm²). Primary end point was angiographic late lumen loss at 6 months. Secondary end points included procedural success, major adverse cardiac events, and individual clinical end points such as stent thrombosis, cardiac death, target lesion myocardial infarction, clinically driven target lesion revascularization, and binary restenosis. RESULTS: Quantitative coronary angiography revealed no differences in baseline parameters. After 6 months, in-segment late lumen loss was 0.25±0.57 mm in the PCB group versus 0.26±0.60 mm in the SCB group. Mean difference between SCB and PCB was 0.01 (95% CI, -0.23 to 0.24). Noninferiority at a predefined margin of 0.35 was shown. Clinical events up to 12 months did not differ between the groups. CONCLUSIONS: This first-in man comparison of a novel SCB with a crystalline coating showed similar angiographic and clinical outcomes in the treatment of coronary drug-eluting stent in-stent restenosis compared with PCB. REGISTRATION: URL: https://www. CLINICALTRIALS: gov; Unique identifier: NCT02996318, NCT03242096.

2022 Malaysian Working Group Consensus Statement on Renal Denervation for management of arterial hypertension.

Hypertension is highly prevalent and a major contributor to cardiovascular mortality and morbidity. In spite of the availability of efficacious, safe and affordable anti-hypertensive drugs, hypertension remains poorly controlled in the majority of hypertensive patients. Various reasons including non-adherence to the anti-hypertensive drugs, account for the poor control. Resistant hypertension is also one of the reasons for poor control of blood pressure (BP). The sympathetic nervous system (SNS) has long been recognized as one of the determinants in the pathophysiology of a raised BP. Overactivity of the SNS is a contributor to sustained arterial hypertension. Renal denervation (RDN) is increasingly recognized as a safe and effective adjunctive therapy to control BP with or without pharmacotherapy. Hence for patients who remain uncontrolled despite all efforts, renal denervation (RDN) is a novel treatment that can potentially improve BP control, hence reducing the major adverse cardiovascular events (MACE). More recent randomized, sham control trials of RDN have shown that RDN produces a sustained lowering of BP. To date, this lowering of BP through RDN is maintained for at least 3 years. Furthermore, this procedure has been found to be safe. Hence this consensus summarises the science behind RDN and the available clinical data to support the use of this therapy. It is hoped that this consensus will offer guidance on the importance of identifying patients who will benefit most from this therapy. A multidisciplinary team approach in the management of the patient undergoing RDN is recommended.

Short- and long-term mortality prediction after an acute ST-elevation myocardial infarction (STEMI) in Asians: A machine learning approach.

BACKGROUND: Conventional risk score for predicting short and long-term mortality following an ST-segment elevation myocardial infarction (STEMI) is often not population specific. 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.

Single Nucleotide Polymorphism rs17173608 in the Chemerin Encoding Gene: Is It a Predictor of Insulin Resistance and Severity of Coronary Artery Disease in Non-Obese Type 2 Diabetes?

(1) Background: Chemerin, or the RARRES2 (Retinoic Acid Receptor Responder 2) gene, is found to be associated with an increased incidence of insulin resistance, endothelial dysfunction, type 2 diabetes (T2D), and coronary artery disease (CAD). This study investigates associations of RARRES2rs17173608 with insulin resistance and the severity of CAD in non-obese T2D patients in relation to the clinical and genetic factors. (2) Methods: A total of 300 patients with T2D and CAD were recruited in this study. The associations of insulin resistance and the severity of CAD with RARRES2rs17173608 and clinical factors were assessed. The genotyping procedures were performed using the TaqMan method. The significant associations (p ≤ 0.05) from preliminary tests were employed to carry out the secondary analysis. (3) Results: RARRES2rs17173608 (TT, TG, and GG polymorphisms in the preliminary analysis; TG and GG polymorphisms in a secondary analysis) was associated with insulin resistance and the severity of CAD in both the preliminary and secondary analysis (all p-values were < 0.05). Additionally, in the secondary analysis, FPG and ACEI were also associated with insulin resistance and the severity of CAD (all p-values were < 0.05). (4) Conclusion: From the preliminary findings, rs17173608 is a significant predictor of insulin resistance and the severity of CAD.

A novel approach for heart disease prediction using strength scores with significant predictors.

BACKGROUND: Cardiovascular disease is the leading cause of death in many countries. Physicians often diagnose cardiovascular disease based on current clinical tests and previous experience of diagnosing patients with similar symptoms. Patients who suffer from heart disease require quick diagnosis, early treatment and constant observations. To address their needs, many data mining approaches have been used in the past in diagnosing and predicting heart diseases. Previous research was also focused on identifying the significant contributing features to heart disease prediction, however, less importance was given to identifying the strength of these features. METHOD: This paper is motivated by the gap in the literature, thus proposes an algorithm that measures the strength of the significant features that contribute to heart disease prediction. The study is aimed at predicting heart disease based on the scores of significant features using Weighted Associative Rule Mining. RESULTS: A set of important feature scores and rules were identified in diagnosing heart disease and cardiologists were consulted to confirm the validity of these rules. The experiments performed on the UCI open dataset, widely used for heart disease research yielded the highest confidence score of 98% in predicting heart disease. CONCLUSION: This study managed to provide a significant contribution in computing the strength scores with significant predictors in heart disease prediction. From the evaluation results, we obtained important rules and achieved highest confidence score by utilizing the computed strength scores of significant predictors on Weighted Associative Rule Mining in predicting heart disease.

Efficacy and Safety of Long-Term Evolocumab Use Among Asian Subjects　- A Subgroup Analysis of the Further Cardiovascular Outcomes Research With PCSK9 Inhibition in Subjects With Elevated Risk (FOURIER) Trial.

BACKGROUND: There are concerns that Asian patients respond differently to some medications. This study evaluated the efficacy and safety of evolocumab among Asian vs. other subjects in the FOURIER trial, which randomized stable atherosclerosis patients to receive either evolocumab or placebo.Methods and Results:Effects of adding evolocumab vs. placebo to background statin therapy on low-density lipoprotein cholesterol (LDL-C) reductions, cardiovascular outcomes, and adverse events were compared among 27,564 participants with atherosclerotic disease, according to self-reported Asian (n=2,723) vs. other (n=24,841) races followed for a median of 2.2 years in the FOURIER trial. The primary endpoint was a composite of cardiovascular death, myocardial infarction, stroke, hospitalization for unstable angina, or coronary revascularization. At randomization, Asians had slightly lower LDL-C (median 89 [IQR 78-104] mg/dL vs. 92 [80-109] mg/dL; P<0.001) and were much less likely to be on a high-intensity statin (33.3% vs. 73.3%; P<0.001). Evolocumab lowered LDL-C more in Asians than in others (66% vs. 58%; P<0.001). The effect of evolocumab on the primary endpoint was similar in Asians (HR, 0.79; 95% CI, 0.61-1.03) and others (HR, 0.86; 95% CI, 0.79-0.93; P interaction=0.55). There was no excess of serious adverse events with evolocumab among Asians over others. CONCLUSIONS: Use of evolocumab robustly lowers LDL-C and is equally efficacious in lowering the risk of cardiovascular events and safe in Asians as it is in others.

Sex and gender differences in presentation, treatment and outcomes in acute coronary syndrome, a 10 year study from a multi-ethnic Asian population: The Malaysian National Cardiovascular Disease Database-Acute Coronary Syndrome (NCVD-ACS) registry.

BACKGROUND: Sex and gender differences in acute coronary syndrome (ACS) have been well studied in the western population. However, limited studies have examined the trends of these differences in a multi-ethnic Asian population. OBJECTIVES: To study the trends in sex and gender differences in ACS using the Malaysian NCVD-ACS Registry. METHODS: Data from 24 hospitals involving 35,232 ACS patients (79.44% men and 20.56% women) from 1st. Jan 2012 to 31st. Dec 2016 were analysed. Data were collected on demographic characteristics, coronary risk factors, anthropometrics, treatments and outcomes. Analyses were done for ACS as a whole and separately for ST-segment elevation myocardial infarction (STEMI), Non-STEMI and unstable angina. These were then compared to published data from March 2006 to February 2010 which included 13,591 ACS patients (75.8% men and 24.2% women). RESULTS: Women were older and more likely to have diabetes mellitus, hypertension, dyslipidemia, previous heart failure and renal failure than men. Women remained less likely to receive aspirin, beta-blocker, angiotensin-converting enzyme inhibitor (ACE-I) and statin. Women were less likely to undergo angiography and percutaneous coronary intervention (PCI) despite an overall increase. In the STEMI cohort, despite a marked increase in presentation with Killip class IV, women were less likely to received primary PCI or fibrinolysis and had longer median door-to-needle and door-to-balloon time compared to men, although these had improved. Women had higher unadjusted in-hospital, 30-Day and 1-year mortality rates compared to men for the STEMI and NSTEMI cohorts. After multivariate adjustments, 1-year mortality remained significantly higher for women with STEMI (adjusted OR: 1.31 (1.09-1.57), p<0.003) but were no longer significant for NSTEMI cohort. CONCLUSION: Women continued to have longer system delays, receive less aggressive pharmacotherapies and invasive treatments with poorer outcome. There is an urgent need for increased effort from all stakeholders if we are to narrow this gap.

Comparative overview of ST-elevation myocardial infarction epidemiology, demographics, management, and outcomes in five Asia-Pacific countries: a meta-analysis.

The aim of this study is to gain insight into the differences in demographics of ST-elevation myocardial infarction (STEMI) patients in Asia-Pacific, as well as inter-country variation in treatment and mortality outcomes. Systematic review of published studies and reports from known registries in Australia, Japan, Korea, Singapore, and Malaysia that began data collection after the year 2000. Supplementary self-report survey questionnaire on public health data answered by representative cardiologists working in these countries. Twenty studies comprising of 158 420 patients were included in the meta-analysis. The mean age was 61.6 years. Chronic kidney disease prevalence was higher in Japan, while dyslipidaemia was low in Korea. Use of aspirin, P2Y12 inhibitors, and statins were high throughout, but ACEi/ARB and ß-blocker prescriptions were lower in Japan and Malaysia. Reperfusion strategies varied greatly, with high rates of primary percutaneous coronary intervention (pPCI) in Korea (91.6%), whilst Malaysia relies far more on fibrinolysis (72.6%) than pPCI (9.6%). Similarly, mortality differed, with 1-year mortality from STEMI was considerably greater in Malaysia (17.9%) and Singapore (11.2%) than in Korea (8.1%), Australia (7.8%), and Japan (6.2%). The countries were broadly similar in development and public health indices. Singapore has the highest gross national income and total healthcare expenditure per capita, whilst Malaysia has the lowest. Primary PCI is available in all countries 24/7/365. Despite broadly comparable public health systems, differences exist in patient profile, in-hospital treatment, and mortality outcomes in these five countries. Our study reveals areas for improvements. The authors advocate further registry-based multi-country comparative studies focused on the Asia-Pacific region.

Feature selection and risk prediction for patients with coronary artery disease using data mining.

Coronary artery disease (CAD) is an important cause of mortality across the globe. Early risk prediction of CAD would be able to reduce the death rate by allowing early and targeted treatments. In healthcare, some studies applied data mining techniques and machine learning algorithms on the risk prediction of CAD using patient data collected by hospitals and medical centers. However, most of these studies used all the attributes in the datasets which might reduce the performance of prediction models due to data redundancy. The objective of this research is to identify significant features to build models for predicting the risk level of patients with CAD. In this research, significant features were selected using three methods (i.e., Chi-squared test, recursive feature elimination, and Embedded Decision Tree). Synthetic Minority Over-sampling Technique (SMOTE) oversampling technique was implemented to address the imbalanced dataset issue. The prediction models were built based on the identified significant features and eight machine learning algorithms, utilizing Acute Coronary Syndrome (ACS) datasets provided by National Cardiovascular Disease Database (NCVD) Malaysia. The prediction models were evaluated and compared using six performance evaluation metrics, and the top-performing models have achieved AUC more than 90%. Graphical abstract.