Search

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Image Quality Assessment (IQA) is essential for the accuracy of systems for automatic recognition of tree species for wood samples. In this study, a No-Reference IQA (NR-IQA), wood NR-IQA (WNR-IQA) metric was proposed to assess the quality of wood images. Support Vector Regression (SVR) was trained using Generalized Gaussian Distribution (GGD) and Asymmetric Generalized Gaussian Distribution (AGGD) features, which were measured for wood images. Meanwhile, the Mean Opinion Score (MOS) was obtained from the subjective evaluation. This was followed by a comparison between the proposed IQA metric, WNR-IQA, and three established NR-IQA metrics, namely Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), deepIQA, Deep Bilinear Convolutional Neural Networks (DB-CNN), and five Full Reference-IQA (FR-IQA) metrics known as MSSIM, SSIM, FSIM, IWSSIM, and GMSD. The proposed WNR-IQA metric, BRISQUE, deepIQA, DB-CNN, and FR-IQAs were then compared with MOS values to evaluate the performance of the automatic IQA metrics. As a result, the WNR-IQA metric exhibited a higher performance compared to BRISQUE, deepIQA, DB-CNN, and FR-IQA metrics. Highest quality images may not be routinely available due to logistic factors, such as dust, poor illumination, and hot environment present in the timber industry. Moreover, motion blur could occur due to the relative motion between the camera and the wood slice. Therefore, the advantage of WNR-IQA could be seen from its independency from a "perfect" reference image for the image quality evaluation. [ABSTRACT FROM AUTHOR]

Background: The objective of this study was to assess regional and ethnic differences in an unselected patient population treated with polymer-free sirolimus-eluting stents (PF-SES) in Asia and Europe. Methods: Two all-comers observational studies based on the same protocol (ClinicalTrials.gov Identifiers: NCT02629575 and NCT02905214) were combined for data analysis to assure sufficient statistical power. The primary endpoint was the accumulated target lesion revascularization (TLR) rate at 9–12 months. Results: Of the total population of 7243 patients, 44.0% (3186) were recruited in the Mediterranean region and 32.0% (2317) in central Europe. The most prominent Asian region was South Korea (17.6%, 1274) followed by Malaysia (5.7%, 413). Major cardiovascular risk factors varied significantly across regions. The overall rates for accumulated TLR and MACE were low with 2.2% (140/6374) and 4.4% (279/6374), respectively. In ACS patients, there were no differences in terms of MACE, TLR, MI and accumulated mortality between the investigated regions. Moreover, dual antiplatelet therapy (DAPT) regimens were substantially longer in Asian countries even in patients with stable coronary artery disease as compared to those in Europe. Conclusions: PF-SES angioplasty is associated with low clinical event rates in all regions. Further reductions in clinical event rates seem to be associated with longer DAPT regimens. [ABSTRACT FROM AUTHOR]

Introduction: The increasing disease burden of coronary artery disease (CAD) calls for sustainable cardiac service. Teaching hospitals and general hospitals in Malaysia are main providers of percutaneous coronary intervention (PCI), a common treatment for CAD. Few studies have analyzed the contemporary data on local cardiac facilities. Service expansion and budget allocation require cost evidence from various providers. We aim to compare the patient characteristics, procedural outcomes, and cost profile between a teaching hospital (TH) and a general hospital (GH). Methods: This cross-sectional study was conducted from the healthcare providers’ perspective from January 1st to June 30th 2014. TH is a university teaching hospital in the capital city, while GH is a state-level general hospital. Both are government-funded cardiac referral centers. Clinical data was extracted from a national cardiac registry. Cost data was collected using mixed method of top-down and bottom-up approaches. Total hospitalization cost per PCI patient was summed up from the costs of ward admission and cardiac catheterization laboratory utilization. Clinical characteristics were compared with chi-square and independent t-test, while hospitalization length and cost were analyzed using Mann-Whitney test. Results: The mean hospitalization cost was RM 12,117 (USD 3,366) at GH and RM 16,289 (USD 4,525) at TH. The higher cost at TH can be attributed to worse patients’ comorbidities and cardiac status. In contrast, GH recorded a lower mean length of stay as more patients had same-day discharge, resulting in 29% reduction in mean cost of admission compared to TH. For both hospitals, PCI consumables accounted for the biggest proportion of total cost. Conclusions: The high PCI consumables cost highlighted the importance of cost-effective purchasing mechanism. Findings on the heterogeneity of the patients, treatment practice and hospitalization cost between TH and GH are vital for formulation of cost-saving strategies to ensure sustainable and equitable cardiac service in Malaysia. [ABSTRACT FROM AUTHOR]

Background: Inflammation, endothelial activation and oxidative stress have been established as key events in the initiation and progression of atherosclerosis. High-density lipoprotein cholesterol (HDL-c) is protective against atherosclerosis and coronary heart disease, but its association with inflammation, endothelial activation and oxidative stress is not well established. Objectives: (1) To compare the concentrations of biomarkers of inflammation, endothelial activation and oxidative stress in subjects with low HDL-c compared to normal HDL-c; (2) To examine the association and correlation between HDL-c and these biomarkers and (3) To determine whether HDL-c is an independent predictor of these biomarkers. Methods: 422 subjects (mean age±SD = 43.2±11.9years) of whom 207 had low HDL-c concentrations (HDL-c <1.0mmol/L and <1.3mmol/L for males and females respectively) and 215 normal controls (HDL-c ≥1.0 and ≥1.3mmol/L for males and females respectively) were recruited in this study. The groups were matched for age, gender, ethnicity, smoking status, diabetes mellitus and hypertension. Fasting blood samples were collected for analysis of biomarkers of inflammation [high-sensitivity C-reactive protein (hsCRP) and Interleukin-6 (IL-6)], endothelial activation [soluble Vascular Cell Adhesion Molecule-1 (sVCAM-1), soluble Intercellular Adhesion Molecule-1 (sICAM-1) and E-selectin)] and oxidative stress [F2-Isoprostanes, oxidized Low Density Lipoprotein (ox-LDL) and Malondialdehyde (MDA)]. Results: Subjects with low HDL-c had greater concentrations of inflammation, endothelial activation and oxidative stress biomarkers compared to controls. There were negative correlations between HDL-c concentration and biomarkers of inflammation (IL-6, p = 0.02), endothelial activation (sVCAM-1 and E-selectin, p = 0.029 and 0.002, respectively), and oxidative stress (MDA and F2-isoprostane, p = 0.036 and <0.0001, respectively). Multiple linear regression analysis showed HDL-c as an independent predictor of IL-6 (p = 0.02) and sVCAM-1 (p<0.03) after correcting for various confounding factors. Conclusion: Low serum HDL-c concentration is strongly correlated with enhanced status of inflammation, endothelial activation and oxidative stress. It is also an independent predictor for enhanced inflammation and endothelial activation, which are pivotal in the pathogenesis of atherosclerosis and atherosclerosis-related complications. [ABSTRACT FROM AUTHOR]

Objectives: To assess whether gender differences exist in the clinical presentation, angiographic severity, management and outcomes in patients with coronary artery disease (CAD). Methods: The study comprised of 1,961 women and 8,593 men who underwent percutaneous coronary intervention (PCI) and were included in the Malaysian NCVD-PCI Registry from 2007–2009. Significant stenosis was defined as ≥70% stenosis in at least one of the epicardial vessels. Results: Women were significantly older and had significantly higher rates of diabetes mellitus, hypertension, chronic renal failure, new onset angina and prior history of heart failure whereas smokers and past history of myocardial infarction were higher in men. In the ST-elevation myocardial infarction (STEMI) cohort, more women were in Killip class III-IV, had longer door-to-balloon time (169.5 min. vs 127.3 min, p<0.052) and significantly longer transfer time (300.4 min vs 166.3 min, p<0.039). Overall, women had significantly more left main stem (LMS) disease (1.3% vs 0.6%, p<0.003) and smaller diameter vessels (<3.0 mm: 45.5% vs 34.8%, p<0.001). In-hospital mortality rates for all PCI, STEMI, Non-STEMI (NSTEMI) and unstable angina for women and men were 1.99% vs 0.98%, Odds ratio (OR): 2.06 (95% confidence interval (CI): 1.40 to 3.01), 6.19% vs 2.88%, OR: 2.23 (95% CI: 1.31 to 3.79), 2.90% vs 0.79%, OR: 3.75 (95% CI: 1.58 to 8.90) and 1.79% vs 0.29%, OR: 6.18 (95% CI: 0.56 to 68.83), respectively. Six-month adjusted OR for mortality for all PCI, STEMI and NSTEMI in women were 2.18 (95% CI: 0.97 to 4.90), 2.68 (95% CI: 0.37 to 19.61) and 2.66 (95% CI: 0.73 to 9.69), respectively. Conclusions: Women who underwent PCI were older with more co-morbidities. In-hospital and six-month mortality for all PCI, STEMI and NSTEMI were higher due largely to significantly more LMS disease, smaller diameter vessels, longer door-to-balloon and transfer time in women. [ABSTRACT FROM AUTHOR]