Automated Diagnosis of Coronary Artery Disease: A Review and Workflow

Bioactive lipids improve serum HDL and PON1 activities in coronary artery disease patients: Ex-vivo study

BACKGROUND

Atherosclerotic cardiovascular disease (CVD) remains a leading cause of vascular disease worldwide. Atherosclerosis is characterized by the accumulation of lipids and oxidized lipids on the blood vessel walls. Coronary artery disease (CAD) is the most common display of atherosclerotic CVD.

OBJECTIVES

We investigated the effects of the bioactive lipids as lyso-diacylglyceryltrimethylhomoserine (lyso-DGTS (20,5,0)) and its derivative oleoyl-N-trimethyl homoserine amide (oleoyl amide-MHS) on the properties and functionality of HDL and paraoxonase 1 (PON1) activities in the serum of individuals who exhibited arterial plaque as observed by coronary CT angiography (CCTA).

METHODS

The study included two independent groups comprising 40 patients who had undergone arterial CCTA scans at Ziv Medical Center for various medical indications. The CAD group included 20 patients with coronary artery plaques with luminal stenosis of more than 50 % in a major coronary vessel. The control group consisted of 20 healthy patients (patients without artery plaques).

RESULTS

Serum samples from CAD patients exhibited lower serum PON1 and cholesterol efflux activities and higher pro-inflammatory than the control group. HDL isolated from CAD patients contains elevated levels of oxidizing lipids (specifically lyso- phosphatidyl ethanolamines and lyso-phosphocholines(compared to the control. However, incubation of the CAD patients' serum with lyso-DGTS and oleoyl amide-MHS restored the antiatherogenic activities of HDL. The lipids increased serum PON1 activities, enhanced apoB-depleted serum cholesterol-efflux activity, and elevated the serum's anti-inflammatory properties.

CONCLUSIONS

The results of the present study suggest the potential of the bioactive lipids lyso-DGTS and oleoyl amide-MHS to attenuate atherosclerosis via the improvement of dysfunctional HDL properties and PON1 activities. Further, in-vivo experiments are needed to assess the athero-protective effect of the lipids.

Classification of coronary artery disease using radial artery pulse wave analysis via machine learning

BACKGROUND

Coronary artery disease (CAD) is a major global cardiovascular health threat and the leading cause of death in many countries. The disease has a significant impact in China, where it has become the leading cause of death. There is an urgent need to develop non-invasive, rapid, cost-effective, and reliable techniques for the early detection of CAD using machine learning (ML).

METHODS

Six hundred eight participants were divided into three groups: healthy, hypertensive, and CAD. The raw data of pulse wave from those participants was collected. The data were de-noised, normalized, and analyzed using several applications. Seven ML classifiers were used to model the processed data, including Decision Tree (DT), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Extra Trees (ET), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting (LightGBM), and Unbiased Boosting with Categorical Features (CatBoost).

RESULTS

The Extra Trees classifier demonstrated the best classification performance. After tunning, the results performance evaluation on test set are: 0.8579 accuracy, 0.9361 AUC, 0.8561 recall, 0.8581 precision, 0.8571 F1 score, 0.7859 kappa coefficient, and 0.7867 MCC. The top 10 feature importances of ET model are w/t1, t3/tmax, tmax, t3/t1, As, hf/3, tf/3/tmax, tf/5, w and tf/3/t1.

CONCLUSION

Radial artery pulse wave can be used to identify healthy, hypertensive and CAD participants by using Extra Trees Classifier. This method provides a potential pathway to recognize CAD patients by using a simple, non-invasive, and cost-effective technique.

A review of computational methodologies to predict the fractional flow reserve in coronary arteries with stenosis

Computational methodologies for predicting the fractional flow reserve (FFR) in coronary arteries with stenosis have gained significant attention due to their potential impact on healthcare outcomes. Coronary artery disease is a leading cause of mortality worldwide, prompting the need for accurate diagnostic and treatment approaches. The use of medical image-based anatomical vascular geometries in computational fluid dynamics (CFD) simulations to evaluate the hemodynamics has emerged as a promising tool in the medical field. This comprehensive review aims to explore the state-of-the-art computational methodologies focusing on the possible considerations. Key aspects include the rheology of blood, boundary conditions, fluid-structure interaction (FSI) between blood and the arterial wall, and multiscale modelling (MM) of stenosis. Through an in-depth analysis of the literature, the goal is to obtain an overview of the major achievements regarding non-invasive methods to compute FFR and to identify existing gaps and challenges that inform further advances in the field. This research has the major objective of improving the current diagnostic capabilities and enhancing patient care in the context of cardiovascular diseases.

Exosomal miRNA-21-5p and miRNA-21-3p as key biomarkers of myocardial infarction

Objective

Coronary artery disease (CAD) is a debilitating condition that can lead to myocardial infarction (MI). Exosomal miRNAs (exo-miRNA) can be diagnostic biomarkers for detecting MI. Here, we conduct a study to evaluate the efficacy of exo-miRNA-21-5p/3p for early detection of MI.

Methods

A total of 135 CAD patients and 150 healthy subjects participated in this study. Additionally, we randomly divided 26 male Wistar rats (12 weeks old) into two groups: control and induced MI. Angiographic images were used to identify patients and healthy individuals of all genders. In the following, serum exosomes were obtained, and exo-miRNA-21-5p/3p was measured by reverse-transcriptase polymerase chain reaction.

Results

We observed an upregulation of exo-miRNA-21-5p/3p in CAD patient and MI-induced animal groups compared to controls. Analysis of the ROC curves defined 82% and 88% of the participants' exo-miRNA-21-5p and exo-miRNA-21-3p diagnostic power, respectively, which in the animal model was 92 and 82.

Conclusion

This study revealed that the mean expression levels of exo-miRNA-21-5p/3p were significantly increased in CAD patients and animal models of induced MI. Also, these results are associated with the atherogenic lipid profile of CAD patients, which may play an important role in the progression of the disease. Therefore, they can be considered as novel biomarkers.

Dynamic assessment of coronary artery during different cardiac cycle in patients with coronary artery disease using coronary CT angiography

INTRODUCTION

To evaluate the effect of the cardiac cycle for the coronary artery opening and coronary stenosis at the plaque to determine the phase of measuring maximum diameters required for coronary artery disease (CAD).

METHODS

This retrospective study assessed data for 208 consecutive patients who underwent coronary computed tomography angiography (CTA). The cross-sectional area and diameters of the opening of the left main coronary artery (LM), left anterior descending branch (LAD), left circumflex branch (LCX) and right coronary artery (RCA), the stenosis rate of involved vessels were measured in 10 cardiac cycles. And all their dynamic changes were estimated by the linear mixed model. The relationship between stenosis rate and opening orifice were analyzed by monofactorial variance.

RESULTS

The opening parameters and stenosis rate of the four main coronary arteries varied within the cardiac cycle (p < .05). The maximum opening area occurred at the 45%-55% phase; The range of stenosis rate varied approximately 11%-14% and the maximum stenosis rate was at the 65% phase. The degree of vascular stenosis for LM, LAD and LCX were not associated with their corresponding opening diameters, but were positively intercorrelation with each other.

CONCLUSION

For patients with CAD, the maximum coronary artery stenosis rate were at 65% phase and the maximum value of coronary artery opening were at 45%-55% phase, which were chosen for the appropriate measurement and evaluation by CTA.

Machine learning-enhanced echocardiography for screening coronary artery disease

BACKGROUND

Since myocardial work (MW) and left atrial strain are valuable for screening coronary artery disease (CAD), this study aimed to develop a novel CAD screening approach based on machine learning-enhanced echocardiography.

METHODS

This prospective study used data from patients undergoing coronary angiography, in which the novel echocardiography features were extracted by a machine learning algorithm. A total of 818 patients were enrolled and randomly divided into training (80%) and testing (20%) groups. An additional 115 patients were also enrolled in the validation group.

RESULTS

The superior diagnosis model of CAD was optimized using 59 echocardiographic features in a gradient-boosting classifier. This model showed that the value of the receiver operating characteristic area under the curve (AUC) was 0.852 in the test group and 0.834 in the validation group, with high sensitivity (0.952) and low specificity (0.691), suggesting that this model is very sensitive for detecting CAD, but its low specificity may increase the high false-positive rate. We also determined that the false-positive cases were more susceptible to suffering cardiac events than the true-negative cases.

CONCLUSIONS

Machine learning-enhanced echocardiography can improve CAD detection based on the MW and left atrial strain features. Our developed model is valuable for estimating the pre-test probability of CAD and screening CAD patients in clinical practice.

TRIAL REGISTRATION

Registered as NCT03905200 at ClinicalTrials.gov. Registered on 5 April 2019.

Next Generation Infectious Diseases Monitoring Gages via Incremental Federated Learning: Current Trends and Future Possibilities

Infectious diseases are always alarming for the survival of human life and are a key concern in the public health domain. Therefore, early diagnosis of these infectious diseases is a high demand for modern-era healthcare systems. Novel general infectious diseases such as coronavirus are infectious diseases that cause millions of human deaths across the globe in 2020. Therefore, early, robust recognition of general infectious diseases is the desirable requirement of modern intelligent healthcare systems. This systematic study is designed under Kitchenham guidelines and sets different RQs (research questions) for robust recognition of general infectious diseases. From 2018 to 2021, four electronic databases, IEEE, ACM, Springer, and ScienceDirect, are used for the extraction of research work. These extracted studies delivered different schemes for the accurate recognition of general infectious diseases through different machine learning techniques with the inclusion of deep learning and federated learning models. A framework is also introduced to share the process of detection of infectious diseases by using machine learning models. After the filtration process, 21 studies are extracted and mapped to defined RQs. In the future, early diagnosis of infectious diseases will be possible through wearable health monitoring cages. Moreover, these gages will help to reduce the time and death rate by detection of severe diseases at starting stage.

Efficient Model for Coronary Artery Disease Diagnosis: A Comparative Study of Several Machine Learning Algorithms

Background

In today's industrialized world, coronary artery disease (CAD) is one of the leading causes of death, and early detection and timely intervention can prevent many of its complications and eliminate or reduce the resulting mortality. Machine learning (ML) methods as one of the cutting-edge technologies can be used as a suitable solution in diagnosing this disease.

Methods

In this study, different ML algorithms' performances were compared for their effectiveness in developing a model for early CAD diagnosis based on clinical examination features. This applied descriptive study was conducted on 303 records and overall 26 features, of which 26 were selected as the target features with the advice of several clinical experts. In order to provide a diagnostic model for CAD, we ran most of the most critical classification algorithms, including Multilayer Perceptron (MLP), Support Vector Machine (SVM), Logistic Regression (LR), J48, Random Forest (RF), K-Nearest Neighborhood (KNN), and Naive Bayes (NB). Seven different classification algorithms with 26 predictive features were tested to cover all feature space and reduce model error, and the most efficient algorithms were identified by comparison of the results.

Results

Based on the compared performance metrics, SVM (AUC = 0.88, F-measure = 0.88, ROC = 0.85), and RF (AUC = 0.87, F-measure = 0.87, ROC = 0.91) were the most effective ML algorithms. Among the algorithms, the KNN algorithm had the lowest efficiency (AUC = 0.81, F-measure = 0.81, ROC = 0.77). In the diagnosis of coronary artery disease, machine learning algorithms have played an important role. Proposed ML models can provide practical, cost-effective, and valuable support to doctors in making decisions according to a good prediction. Discussion. It can become the basis for developing clinical decision support systems. SVM and RF algorithms had the highest efficiency and could diagnose CAD based on patient examination data. It is suggested that further studies be performed using these algorithms to diagnose coronary artery disease to obtain more accurate results.

Automatic prediction of coronary artery disease using differential evolution-based support vector machine

Coronary artery disease (CAD) is a common heart disease that causes the blockage of coronary arteries. To reduce fatality, an accurate diagnosis of this disease is very important. Angiography is one of the most trustworthy and conventional methods for CAD diagnosis however, it is risky, expensive, and time-consuming. Therefore in this study, we proposed a differential evolution-based support vector machine (SVM) for early and accurate detection of CAD. To improve the accuracy, different data preprocessing techniques such as one-hot encoding and normalization are also used with differential evolution for feature selection before performing classification. The proposed approach is benchmarked with the Z-Alizadeh Sani and Cleveland datasets against four state-of-the-art machine learning algorithms, and a highly cited genetic algorithm-based SVM (N2GC-nuSVM). The experimental results show that our proposed differential evolution-based SVM outperforms all the compared algorithms. The proposed method provides accuracies of 95±1% and 86.22% for predicting CAD on the benchmark datasets.

Futuristic CRISPR-based biosensing in the cloud and internet of things era: an overview

Biosensors-based devices are transforming medical diagnosis of diseases and monitoring of patient signals. The development of smart and automated molecular diagnostic tools equipped with biomedical big data analysis, cloud computing and medical artificial intelligence can be an ideal approach for the detection and monitoring of diseases, precise therapy, and storage of data over the cloud for supportive decisions. This review focused on the use of machine learning approaches for the development of futuristic CRISPR-biosensors based on microchips and the use of Internet of Things for wireless transmission of signals over the cloud for support decision making. The present review also discussed the discovery of CRISPR, its usage as a gene editing tool, and the CRISPR-based biosensors with high sensitivity of Attomolar (10^-18 M), Femtomolar (10^-15 M) and Picomolar (10^-12 M) in comparison to conventional biosensors with sensitivity of nanomolar 10^-9 M and micromolar 10^-3 M. Additionally, the review also outlines limitations and open research issues in the current state of CRISPR-based biosensing applications.

Opium may affect coronary artery disease by inducing inflammation but not through the expression of CD9, CD36, and CD68

The molecular mechanisms of opium with regard to coronary artery disease (CAD) have not yet been determined. The aim of the present study was to evaluate the effect of opium on the expression of scavenger receptors including CD36, CD68, and CD9 tetraspanin in monocytes and the plasma levels of tumor necrosis factor alpha (TNF-α), interferon gamma (IFN-γ), malondialdehyde (MDA), and nitric oxide metabolites (NO_x) in patients with CAD with and without opium addiction. This case-control study was conducted in three groups: (1) opium-addicted patients with CAD (CAD+OA, n=30); (2) patients with CAD with no opium addiction (CAD, n=30); and (3) individuals without CAD and opium addiction as the control group (Ctrl, n=17). Protein and messenger RNA (mRNA) levels of CD9, CD36, and CD68 were evaluated by flow cytometry and reverse transcription-quantitative PCR methods, respectively. Consumption of atorvastatin, aspirin, and glyceryl trinitrate was found to be higher in the CAD groups compared with the control group. The plasma level of TNF-α was significantly higher in the CAD+OA group than in the CAD and Ctrl groups (p=0.001 and p=0.005, respectively). MDA levels significantly increased in the CAD and CAD+OA groups in comparison with the Ctrl group (p=0.010 and p=0.002, respectively). No significant differences were found in CD9, CD36, CD68, IFN-γ, and NO_x between the three groups. The findings demonstrated that opium did not have a significant effect on the expression of CD36, CD68, and CD9 at the gene and protein levels, but it might be involved in the development of CAD by inducing inflammation through other mechanisms.

The impact of omentin-1 gene polymorphisms (rs2274907 and rs2274908) on serum lipid concentrations and coronary artery disease in a sample of Iraqi individuals (A pilot study)

BACKGROUND

Coronary artery disease (CAD) is the primary cause of death worldwide. It is mainly caused by atherosclerosis that initiates from a genetic-environmental interaction. Studies highlighted the association of numerous gene polymorphisms with CAD. Omentin-1 is secreted from visceral adipose tissues, intestine, and others; it has anti-inflammatory and insulin sensitivity improving roles.

AIM

To explore the association of the omentin-1 gene polymorphisms (rs2274907 and rs2274908) with serum lipid concentrations and CAD in a sample of the Iraqi population.

METHODS

A case-control study was followed, in which CAD patients were analyzed versus a group of healthy persons. Serum lipid concentrations were measured by enzymatic methods. Genotyping of the omentin-1 gene for rs2274907 SNP was achieved by ARMS-PCR, while for rs2274908 SNP by allele-specific PCR (AS-PCR) techniques.

RESULTS

Atherogenic serum lipid concentrations increased significantly in CAD patients relative to the control group. Genotyping of the omentin-1 gene for rs2274907 SNP revealed a significant (OR = 4.11, P = 0.035) elevation of the AT genotype carriers in CAD versus the control groups. The genotype analysis of the rs2274908 SNP failed to exhibit a significant variation. The two analyzed SNPs were indicated to be in linkage disequilibrium (r = 0.772, P < 0.0001). The global haplotype association of the 2 SNPs was demonstrated to be significant (P = 0.006). Serum lipid concentrations were found to be independent of the genotype distribution of the rs2274907 SNP.

CONCLUSION

Carriers of the AT genotype of rs2274907 SNP in the omentin-1gene may have a four-fold risk of developing CAD compared to those of the wild genotype. Alterations of serum lipid concentrations may do not depend on the genotypes of this SNP.

Prediction of all-cause mortality in coronary artery disease patients with atrial fibrillation based on machine learning models

BACKGROUND

Machine learning (ML) can include more diverse and more complex variables to construct models. This study aimed to develop models based on ML methods to predict the all-cause mortality in coronary artery disease (CAD) patients with atrial fibrillation (AF).

METHODS

A total of 2037 CAD patients with AF were included in this study. Three ML methods were used, including the regularization logistic regression, random forest, and support vector machines. The fivefold cross-validation was used to evaluate model performance. The performance was quantified by calculating the area under the curve (AUC) with 95% confidence intervals (CI), sensitivity, specificity, and accuracy.

RESULTS

After univariate analysis, 24 variables with statistical differences were included into the models. The AUC of regularization logistic regression model, random forest model, and support vector machines model was 0.732 (95% CI 0.649-0.816), 0.728 (95% CI 0.642-0.813), and 0.712 (95% CI 0.630-0.794), respectively. The regularization logistic regression model presented the highest AUC value (0.732 vs 0.728 vs 0.712), specificity (0.699 vs 0.663 vs 0.668), and accuracy (0.936 vs 0.935 vs 0.935) among the three models. However, no statistical differences were observed in the receiver operating characteristic (ROC) curve of the three models (all P > 0.05).

CONCLUSION

Combining the performance of all aspects of the models, the regularization logistic regression model was recommended to be used in clinical practice.

Machine learning and statistical approaches for classification of risk of coronary artery disease using plasma cytokines

Background

As per the 2017 WHO fact sheet, Coronary Artery Disease (CAD) is the primary cause of death in the world, and accounts for 31% of total fatalities. The unprecedented 17.6 million deaths caused by CAD in 2016 underscores the urgent need to facilitate proactive and accelerated pre-emptive diagnosis. The innovative and emerging Machine Learning (ML) techniques can be leveraged to facilitate early detection of CAD which is a crucial factor in saving lives. The standard techniques like angiography, that provide reliable evidence are invasive and typically expensive and risky. In contrast, ML model generated diagnosis is non-invasive, fast, accurate and affordable. Therefore, ML algorithms can be used as a supplement or precursor to the conventional methods. This research demonstrates the implementation and comparative analysis of K Nearest Neighbor (k-NN) and Random Forest ML algorithms to achieve a targeted “At Risk” CAD classification using an emerging set of 35 cytokine biomarkers that are strongly indicative predictive variables that can be potential targets for therapy. To ensure better generalizability, mechanisms such as data balancing, repeated k-fold cross validation for hyperparameter tuning, were integrated within the models. To determine the separability efficacy of “At Risk” CAD versus Control achieved by the models, Area under Receiver Operating Characteristic (AUROC) metric is used which discriminates the classes by exhibiting tradeoff between the false positive and true positive rates.

Results

A total of 2 classifiers were developed, both built using 35 cytokine predictive features. The best AUROC score of .99 with a 95% Confidence Interval (CI) (.982,.999) was achieved by the Random Forest classifier using 35 cytokine biomarkers. The second-best AUROC score of .954 with a 95% Confidence Interval (.929,.979) was achieved by the k-NN model using 35 cytokines. A p-value of less than 7.481e-10 obtained by an independent t-test validated that Random Forest classifier was significantly better than the k-NN classifier with regards to the AUROC score.

Presently, as large-scale efforts are gaining momentum to enable early, fast, reliable, affordable, and accessible detection of individuals at risk for CAD, the application of powerful ML algorithms can be leveraged as a supplement to conventional methods such as angiography. Early detection can be further improved by incorporating 65 novel and sensitive cytokine biomarkers. Investigation of the emerging role of cytokines in CAD can materially enhance the detection of risk and the discovery of mechanisms of disease that can lead to new therapeutic modalities.

RDW Value may Increase the Diagnostic Accuracy of MPS

Objectives:

As the feasibility of obtaining health care has improved in the last decade, there is an increase in the number of performing unnecessary coronary angiogram. Red Cell Distribution Width (RDW), which shows erythrocyte dispersion volume, is associated with coronary artery disease. The present study aims to evaluate the relationship between RDW value and the severity of coronary artery disease in patients who undergo myocardial perfusion scintigraphy (MPS) as an evaluation for coronary ischemia and after which patients had a coronary angiography.

Methods:

This retrospective study included 452 patients diagnosed as stabile angina that had MPS to evaluate coronary ischemia and after which coronary angiography was performed. Complete blood count was obtained on the same day. Patients were first divided into two groups: patients with and without ischemia on MPS. Then, the group who had ischemia on the MPS where divided into another two groups: patients who had RDW values ≥13.5 and the others who had RDW value <13.5. Patients who had fixed perfusion defect, chronic kidney disease, thyroid dysfunction, hematological disease, those who use iron supplements, and those who had active infectious disease were excluded from this study.

Results:

The basic characteristics were the same between study groups. We found that severe coronary vessel disease, single vessel, two vessels and three vessels diseases were higher in patients who had ischemia on the MPS and RDW values ≥13.5 (p-value were 0.032, 0.004, 0.042 respectively). RDW values ≥13.5 was found to be an independent predictor for the presence of severe coronary artery disease (p<0.001 OR: 3.55).

Conclusion:

Patients who have MPS for ischemic evaluation and RDW values of ≥ 13.5 were more severe coronary heart diseases. As a result, the findings suggest that using of RDW value is a cheap and feasible parameter that may prevent performing unnecessary coronary angiography for patients after MPS.

An Analysis of the Effects of Noisy Electrocardiogram Signal on Heartbeat Detection Performance

Heartbeat detection for ambulatory cardiac monitoring is more challenging as the level of noise and artefacts induced by daily-life activities are considerably higher than monitoring in a hospital setting. It is valuable to understand the relationship between the characteristics of electrocardiogram (ECG) noises and the beat detection performance in the cardiac monitoring system. For this purpose, three well-known algorithms for the beat detection process were re-implemented. The beat detection algorithms were validated using two types of ambulatory datasets, which were the ECG signal from the MIT-BIH Arrhythmia Database and the simulated noise-contaminated ECG signal with different intensities of baseline wander (BW), muscle artefact (MA) and electrode motion (EM) artefact from the MIT-BIH Noise Stress Test Database. The findings showed that signals contaminated with noise and artefacts decreased the potential of beat detection in ambulatory signal with the poorest performance noted for ECG signal affected by the EM artefacts. In conclusion, none of the algorithms was able to detect all QRS complexes without any false detection at the highest level of noise. The EM noise influenced the beat detection performance the most in comparison to the MA and BW noises that resulted in the highest number of misdetections and false detections.

Minimal Patient Clinical Variables to Accurately Predict Stress Echocardiography Outcome: Validation Study Using Machine Learning Techniques

Background

Stress echocardiography is a well-established diagnostic tool for suspected coronary artery disease (CAD). Cardiovascular risk factors are used in the assessment of the probability of CAD. The link between the outcome of stress echocardiography and patients’ variables including risk factors, current medication, and anthropometric variables has not been widely investigated.

Objective

This study aimed to use machine learning to predict significant CAD defined by positive stress echocardiography results in patients with chest pain based on anthropometrics, cardiovascular risk factors, and medication as variables. This could allow clinical prioritization of patients with likely prediction of CAD, thus saving clinician time and improving outcomes.

Methods

A machine learning framework was proposed to automate the prediction of stress echocardiography results. The framework consisted of four stages: feature extraction, preprocessing, feature selection, and classification stage. A mutual information–based feature selection method was used to investigate the amount of information that each feature carried to define the positive outcome of stress echocardiography. Two classification algorithms, support vector machine (SVM) and random forest classifiers, have been deployed. Data from 529 patients were used to train and validate the framework. Patient mean age was 61 (SD 12) years. The data consists of anthropological data and cardiovascular risk factors such as gender, age, weight, family history, diabetes, smoking history, hypertension, hypercholesterolemia, prior diagnosis of CAD, and prescribed medications at the time of the test. There were 82 positive (abnormal) and 447 negative (normal) stress echocardiography results. The framework was evaluated using the whole dataset including cases with prior diagnosis of CAD. Five-fold cross-validation was used to validate the performance of the framework. We also investigated the model in the subset of patients with no prior CAD.

Results

The feature selection methods showed that prior diagnosis of CAD, sex, and prescribed medications such as angiotensin-converting enzyme inhibitor/angiotensin receptor blocker were the features that shared the most information about the outcome of stress echocardiography. SVM classifiers showed the best trade-off between sensitivity and specificity and was achieved with three features. Using only these three features, we achieved an accuracy of 67.63% with sensitivity and specificity 72.87% and 66.67% respectively. However, for patients with no prior diagnosis of CAD, only two features (sex and angiotensin-converting enzyme inhibitor/angiotensin receptor blocker use) were needed to achieve accuracy of 70.32% with sensitivity and specificity at 70.24%.

Conclusions

This study shows that machine learning can predict the outcome of stress echocardiography based on only a few features: patient prior cardiac history, gender, and prescribed medication. Further research recruiting higher number of patients who underwent stress echocardiography could further improve the performance of the proposed algorithm with the potential of facilitating patient selection for early treatment/intervention avoiding unnecessary downstream testing.

Synthetic PPG generation from haemodynamic model with baroreflex autoregulation: a Digital twin of cardiovascular system

Synthetic data generation has recently emerged as a substitution technique for handling the problem of bulk data needed in training machine learning algorithms. Healthcare, primarily cardiovascular domain is a major area where synthetic physiological data like Photoplethysmogram (PPG), Electrocardiogram (ECG), Phonocardiogram (PCG), etc. are being used to improve accuracy of machine learning algorithm. Conventional synthetic data generation approach using mathematical formulations lack interpretability. Hence, aim of this paper is to generate synthetic PPG signal from a Digital twin platform replicating cardiovascular system. Such system can serve the dual purpose of replicating the physical system, so as to simulate specific `what if' scenarios as well as to generate large scale synthetic data with patho-physiological interpretability. Cardio-vascular Digital twin is modeled with a two chambered heart, haemodynamic equations and a baroreflex based pressure control mechanism to generate blood pressure and flow variations. Synthetic PPG signal is generated from the model for healthy and Atherosclerosis condition. Initial validation of the platform has been made on the basis of efficiency of the platform in clustering Coronary Artery Disease (CAD) and non CAD PPG data by extracting features from the synthetically generated PPG and comparing that with PPG obtained from Physionet data.

Coronary Artery Disease Diagnosis; Ranking the Significant Features Using a Random Trees Model

Heart disease is one of the most common diseases in middle-aged citizens. Among the vast number of heart diseases, coronary artery disease (CAD) is considered as a common cardiovascular disease with a high death rate. The most popular tool for diagnosing CAD is the use of medical imaging, e.g., angiography. However, angiography is known for being costly and also associated with a number of side effects. Hence, the purpose of this study is to increase the accuracy of coronary heart disease diagnosis through selecting significant predictive features in order of their ranking. In this study, we propose an integrated method using machine learning. The machine learning methods of random trees (RTs), decision tree of C5.0, support vector machine (SVM), and decision tree of Chi-squared automatic interaction detection (CHAID) are used in this study. The proposed method shows promising results and the study confirms that the RTs model outperforms other models.

Deep Deterministic Learning for Pattern Recognition of Different Cardiac Diseases through the Internet of Medical Things

Electrocardiography (ECG) sensors play a vital role in the Internet of Medical Things, and these sensors help in monitoring the electrical activity of the heart. ECG signal analysis can improve human life in many ways, from diagnosing diseases among cardiac patients to managing the lifestyles of diabetic patients. Abnormalities in heart activities lead to different cardiac diseases and arrhythmia. However, some cardiac diseases, such as myocardial infarction (MI) and atrial fibrillation (Af), require special attention due to their direct impact on human life. The classification of flattened T wave cases of MI in ECG signals and how much of these cases are similar to ST-T changes in MI remain an open issue for researchers. This article presents a novel contribution to classify MI and Af. To this end, we propose a new approach called deep deterministic learning (DDL), which works by combining predefined heart activities with fused datasets. In this research, we used two datasets. The first dataset, Massachusetts Institute of Technology-Beth Israel Hospital, is publicly available, and we exclusively obtained the second dataset from the University of Malaya Medical Center, Kuala Lumpur Malaysia. We first initiated predefined activities on each individual dataset to recognize patterns between the ST-T change and flattened T wave cases and then used the data fusion approach to merge both datasets in a manner that delivers the most accurate pattern recognition results. The proposed DDL approach is a systematic stage-wise methodology that relies on accurate detection of R peaks in ECG signals, time domain features of ECG signals, and fine tune-up of artificial neural networks. The empirical evaluation shows high accuracy (i.e., ≤99.97%) in pattern matching ST-T changes and flattened T waves using the proposed DDL approach. The proposed pattern recognition approach is a significant contribution to the diagnosis of special cases of MI.

Futuristic biosensors for cardiac health care: an artificial intelligence approach

Biosensor-based devices are pioneering in the modern biomedical applications and will be the future of cardiac health care. The coupling of artificial intelligence (AI) for cardiac monitoring-based biosensors for the point of care (POC) diagnostics is prominently reviewed here. This review deciphers the most significant machine-learning algorithms for the futuristic biosensors along with the internet of things, computational techniques and microchip-based essential cardiac biomarkers for real-time health monitoring and improving patient compliance. The present review also discusses the recently developed cardiac biosensors along with technical strategies involved in their mechanism of working and their applications in healthcare. Additionally, it provides a key for the ontogeny of an effective and supportive hierarchical protocol for clinical decision-making about personalized medicine through combinatory information analysis, and integrated multidisciplinary AI approaches.

Deep Learning Methods for Predicting Disease Status Using Genomic Data

Predicting disease status for a complex human disease using genomic data is an important, yet challenging, step in personalized medicine. Among many challenges, the so-called curse of dimensionality problem results in unsatisfied performances of many state-of-art machine learning algorithms. A major recent advance in machine learning is the rapid development of deep learning algorithms that can efficiently extract meaningful features from high-dimensional and complex datasets through a stacked and hierarchical learning process. Deep learning has shown breakthrough performance in several areas including image recognition, natural language processing, and speech recognition. However, the performance of deep learning in predicting disease status using genomic datasets is still not well studied. In this article, we performed a review on the four relevant articles that we found through our thorough literature search. All four articles first used auto-encoders to project high-dimensional genomic data to a low dimensional space and then applied the state-of-the-art machine learning algorithms to predict disease status based on the low-dimensional representations. These deep learning approaches outperformed existing prediction methods, such as prediction based on transcript-wise screening and prediction based on principal component analysis. The limitations of the current deep learning approach and possible improvements were also discussed.