Submit to Diagnostics Review for Diagnostics Propose a Special Issue

Journal Browser

Implementing AI in Diagnosis of Cardiovascular Diseases

Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Diagnostics (ISSN 2075-4418). This special issue belongs to the section "Machine Learning and Artificial Intelligence in Diagnostics".

Deadline for manuscript submissions: closed (19 March 2023) | Viewed by 14421

Share This Special Issue

Special Issue Editors

Dr. Syed Ahmad Chan Bukhari

E-Mail Website
Guest Editor

Division of Computer Science, Mathematics and Science, Collins College of Professional Studies, St. John's University, Queens, NY, USA
Interests: healthcare informatics; healthcare data standards and vocabularies; database management systems for healthcare; software development
Special Issues, Collections and Topics in MDPI journals

Dr. Hafiz Tayyab Rauf

E-Mail Website
Co-Guest Editor

Centre for Smart Systems, AI and Cybersecurity, Staffordshire University, Stoke-on-Trent ST4 2DE, UK
Interests: image processing; computer vision; machine learning; evolutionary computing; social network data analysis
Special Issues, Collections and Topics in MDPI journals

Dr. Liaqat Ali

E-Mail Website
Co-Guest Editor

Department of Electrical Engineering, University of Science and Technology Bannu, Bannu, Pakistan
Interests: health informatics; machine learning; data mining; computer vision

Dr. Jiechao Gao

E-Mail Website
Co-Guest Editor

Department of Computer Science, College of Engineering, University of Virginia, Charlottesville, VA, USA
Interests: machine learning; data mining; computer vision; IoT; federated learning

Special Issue Information

Dear colleagues,

Over the last few years, the diversity of Machine Learning-assisted methods has increased. Thanks to technological breakthroughs in Medical Decision Support Systems, a tremendous increase in qualitative accuracy and refinement have been feasible. In particular, Cardiovascular Disease (CVD) detection, including Heart Failure (HF) prediction, needs remarkable improvement to be deployable by the clinicians. The recent integration of machine learning and deep learning has supported novel approaches with feature extraction and fusion-based identifications, specifically with image-based data sets. However, there is still some loop whole with the patient health records combined with their diagnostics image-based scans. Furthermore, recently researchers have implemented numerous AI-based diagnostic systems for CVD detection. However, there are still some challenges that should be tackled. These challenges include a lack of large-size datasets and over-estimated models using minimal scale data.

Another side of this Special Issue is the integration of Evolutionary Computing (EC) with deep learning-based approaches for CVD. Evolutionary algorithms can be employed on both the optimization and machine-learning sides in the data-based development for CVD. Other examples in this setting include employing evolutionary algorithms to optimize the topology of neural networks for CVD.

This Special Issue aims to attract papers and ideas that would address the issues of AI-assisted approaches for CVD. This Special Issue will cover a wide range of topics, including but not limited to.

Prof. Syed Ahmad Chan Bukhari
Dr. Hafiz Tayyab Rauf
Dr. Liaqat Ali
Dr. Jiechao Gao
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Diagnostics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

Advances in feature fusion for CVD
Advances in feature extraction for CVD
Fuzzy inference rule for CVD
Data mining for CVD
Text mining for CVD
Metaheuristics in cardiovascular image processing
Swarm Intelligence in cardiovascular image processing
Genetic algorithm for personalized cardiac imaging
Knowledge extraction for CVD
Knowledge learning for CVD
Big data for CVD
Visualization in CVD
Machine learning and artificial intelligence
Cardiac analysis of anatomical structures

Published Papers (6 papers)

Download All Papers

Research

Jump to: Review

20 pages, 2332 KiB

Open AccessArticle

An Automatic Premature Ventricular Contraction Recognition System Based on Imbalanced Dataset and Pre-Trained Residual Network Using Transfer Learning on ECG Signal

by Hadaate Ullah, Md Belal Bin Heyat, Faijan Akhtar, Abdullah Y. Muaad, Chiagoziem C. Ukwuoma, Muhammad Bilal, Mahdi H. Miraz, Mohammad Arif Sobhan Bhuiyan, Kaishun Wu, Robertas Damaševičius, Taisong Pan, Min Gao, Yuan Lin and Dakun Lai

Diagnostics 2023, 13(1), 87; https://doi.org/10.3390/diagnostics13010087 - 28 Dec 2022

Cited by 12 | Viewed by 3097

Abstract

The development of automatic monitoring and diagnosis systems for cardiac patients over the internet has been facilitated by recent advancements in wearable sensor devices from electrocardiographs (ECGs), which need the use of patient-specific approaches. Premature ventricular contraction (PVC) is a common chronic cardiovascular disease that can cause conditions that are potentially fatal. Therefore, for the diagnosis of likely heart failure, precise PVC detection from ECGs is crucial. In the clinical settings, cardiologists typically employ long-term ECGs as a tool to identify PVCs, where a cardiologist must put in a lot of time and effort to appropriately assess the long-term ECGs which is time consuming and cumbersome. By addressing these issues, we have investigated a deep learning method with a pre-trained deep residual network, ResNet-18, to identify PVCs automatically using transfer learning mechanism. Herein, features are extracted by the inner layers of the network automatically compared to hand-crafted feature extraction methods. Transfer learning mechanism handles the difficulties of required large volume of training data for a deep model. The pre-trained model is evaluated on the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) Arrhythmia and Institute of Cardiological Technics (INCART) datasets. First, we used the Pan–Tompkins algorithm to segment 44,103 normal and 6423 PVC beats, as well as 106,239 normal and 9987 PVC beats from the MIT-BIH Arrhythmia and IN-CART datasets, respectively. The pre-trained model employed the segmented beats as input after being converted into 2D (two-dimensional) images. The method is optimized with the using of weighted random samples, on-the-fly augmentation, Adam optimizer, and call back feature. The results from the proposed method demonstrate the satisfactory findings without the using of any complex pre-processing and feature extraction technique as well as design complexity of model. Using LOSOCV (leave one subject out cross-validation), the received accuracies on MIT-BIH and INCART are 99.93% and 99.77%, respectively, suppressing the state-of-the-art methods for PVC recognition on unseen data. This demonstrates the efficacy and generalizability of the proposed method on the imbalanced datasets. Due to the absence of device-specific (patient-specific) information at the evaluating stage on the target datasets in this study, the method might be used as a general approach to handle the situations in which ECG signals are obtained from different patients utilizing a variety of smart sensor devices. Full article

(This article belongs to the Special Issue Implementing AI in Diagnosis of Cardiovascular Diseases)

► Show Figures

Figure 1

15 pages, 5976 KiB

Open AccessArticle

New Real-Time Impulse Noise Removal Method Applied to Chest X-ray Images

by Nasr Rashid, Kamel Berriri, Mohammed Albekairi, Khaled Kaaniche, Ahmed Ben Atitallah, Muhammad Attique Khan and Osama I. El-Hamrawy

Diagnostics 2022, 12(11), 2738; https://doi.org/10.3390/diagnostics12112738 - 9 Nov 2022

Cited by 5 | Viewed by 1629

Abstract

In this paper, we propose a new Modified Laplacian Vector Median Filter (MLVMF) for real-time denoising complex images corrupted by “salt and pepper” impulsive noise. The method consists of two rounds with three steps each: the first round starts with the identification of pixels that may be contaminated by noise using a Modified Laplacian Filter. Then, corrupted pixels pass a neighborhood-based validation test. Finally, the Vector Median Filter is used to replace noisy pixels. The MLVMF uses a 5 × 5 window to observe the intensity variations around each pixel of the image with a rotation step of π/8 while the classic Laplacian filters often use rotation steps of π/2 or π/4. We see better identification of noise-corrupted pixels thanks to this rotation step refinement. Despite this advantage, a high percentage of the impulsive noise may cause two or more corrupted pixels (with the same intensity) to collide, preventing the identification of noise-corrupted pixels. A second round is then necessary using a second set of filters, still based on the Laplacian operator, but allowing focusing only on the collision phenomenon. To validate our method, MLVMF is firstly tested on standard images, with a noise percentage varying from 3% to 30%. Obtained performances in terms of processing time, as well as image restoration quality through the PSNR (Peak Signal to Noise Ratio) and the NCD (Normalized Color Difference) metrics, are compared to the performances of VMF (Vector Median Filter), VMRHF (Vector Median-Rational Hybrid Filter), and MSMF (Modified Switching Median Filter). A second test is performed on several noisy chest x-ray images used in cardiovascular disease diagnosis as well as COVID-19 diagnosis. The proposed method shows a very good quality of restoration on this type of image, particularly when the percentage of noise is high. The MLVMF provides a high PSNR value of 5.5% and a low NCD value of 18.2%. Finally, an optimized Field-Programmable Gate Array (FPGA) design is proposed to implement the proposed method for real-time processing. The proposed hardware implementation allows an execution time equal to 9 ms per 256 × 256 color image. Full article

(This article belongs to the Special Issue Implementing AI in Diagnosis of Cardiovascular Diseases)

► Show Figures

Graphical abstract

15 pages, 4630 KiB

Open AccessArticle

Cardiovascular and Diabetes Diseases Classification Using Ensemble Stacking Classifiers with SVM as a Meta Classifier

by Asfandyar Khan, Abdullah Khan, Muhammad Muntazir Khan, Kamran Farid, Muhammad Mansoor Alam and Mazliham Bin Mohd Su’ud

Diagnostics 2022, 12(11), 2595; https://doi.org/10.3390/diagnostics12112595 - 26 Oct 2022

Cited by 5 | Viewed by 1908

Abstract

Cardiovascular disease includes coronary artery diseases (CAD), which include angina and myocardial infarction (commonly known as a heart attack), and coronary heart diseases (CHD), which are marked by the buildup of a waxy material called plaque inside the coronary arteries. Heart attacks are still the main cause of death worldwide, and if not treated right they have the potential to cause major health problems, such as diabetes. If ignored, diabetes can result in a variety of health problems, including heart disease, stroke, blindness, and kidney failure. Machine learning methods can be used to identify and diagnose diabetes and other illnesses. Diabetes and cardiovascular disease both can be diagnosed using several classifier types. Naive Bayes, K-Nearest neighbor (KNN), linear regression, decision trees (DT), and support vector machines (SVM) were among the classifiers employed, although all of these models had poor accuracy. Therefore, due to a lack of significant effort and poor accuracy, new research is required to diagnose diabetes and cardiovascular disease. This study developed an ensemble approach called “Stacking Classifier” in order to improve the performance of integrated flexible individual classifiers and decrease the likelihood of misclassifying a single instance. Naive Bayes, KNN, Linear Discriminant Analysis (LDA), and Decision Tree (DT) are just a few of the classifiers used in this study. As a meta-classifier, Random Forest and SVM are used. The suggested stacking classifier obtains a superior accuracy of 0.9735 percent when compared to current models for diagnosing diabetes, such as Naive Bayes, KNN, DT, and LDA, which are 0.7646 percent, 0.7460 percent, 0.7857 percent, and 0.7735 percent, respectively. Furthermore, for cardiovascular disease, when compared to current models such as KNN, NB, DT, LDA, and SVM, which are 0.8377 percent, 0.8256 percent, 0.8426 percent, 0.8523 percent, and 0.8472 percent, respectively, the suggested stacking classifier performed better and obtained a higher accuracy of 0.8871 percent. Full article

(This article belongs to the Special Issue Implementing AI in Diagnosis of Cardiovascular Diseases)

► Show Figures

Figure 1

17 pages, 989 KiB

Open AccessArticle

Incorporating CNN Features for Optimizing Performance of Ensemble Classifier for Cardiovascular Disease Prediction

by Furqan Rustam, Abid Ishaq, Kashif Munir, Mubarak Almutairi, Naila Aslam and Imran Ashraf

Diagnostics 2022, 12(6), 1474; https://doi.org/10.3390/diagnostics12061474 - 15 Jun 2022

Cited by 24 | Viewed by 2986

Abstract

Cardiovascular diseases (CVDs) have been regarded as the leading cause of death with 32% of the total deaths around the world. Owing to the large number of symptoms related to age, gender, demographics, and ethnicity, diagnosing CVDs is a challenging and complex task. Furthermore, the lack of experienced staff and medical experts, and the non-availability of appropriate testing equipment put the lives of millions of people at risk, especially in under-developed and developing countries. Electronic health records (EHRs) have been utilized for diagnosing several diseases recently and show the potential for CVDs diagnosis as well. However, the accuracy and efficacy of EHRs-based CVD diagnosis are limited by the lack of an appropriate feature set. Often, the feature set is very small and unable to provide enough features for machine learning models to obtain a good fit. This study solves this problem by proposing the novel use of feature extraction from a convolutional neural network (CNN). An ensemble model is designed where a CNN model is used to enlarge the feature set to train linear models including stochastic gradient descent classifier, logistic regression, and support vector machine that comprise the soft-voting based ensemble model. Extensive experiments are performed to analyze the performance of different ratios of feature sets to the training dataset. Performance analysis is carried out using four different datasets and results are compared with recent approaches used for CVDs. Results show the superior performance of the proposed model with 0.93 accuracy, and 0.92 scores each for precision, recall, and F1 score. Results indicate both the superiority of the proposed approach, as well as the generalization of the ensemble model using multiple datasets. Full article

(This article belongs to the Special Issue Implementing AI in Diagnosis of Cardiovascular Diseases)

► Show Figures

Figure 1

11 pages, 982 KiB

Open AccessArticle

A Coronary Artery Disease Monitoring Model Built from Clinical Data and Alpha-1-Antichymotrypsin

by Chen-Chi Chang, I-Jung Tsai, Wen-Chi Shen, Hung-Yi Chen, Po-Wen Hsu and Ching-Yu Lin

Diagnostics 2022, 12(6), 1415; https://doi.org/10.3390/diagnostics12061415 - 8 Jun 2022

Cited by 1 | Viewed by 1700

Abstract

Coronary artery disease (CAD) is one of the most common subtypes of cardiovascular disease. The progression of CAD initiates from the plaque of atherosclerosis and coronary artery stenosis, and eventually turns into acute myocardial infarction (AMI) or stable CAD. Alpha-1-antichymotrypsin (AACT) has been highly associated with cardiac events. In this study, we proposed incorporating clinical data on AACT levels to establish a model for estimating the severity of CAD. Thirty-six healthy controls (HCs) and 162 CAD patients with stenosis rates of <30%, 30–70%, and >70% were included in this study. Plasma concentration of AACT was determined by enzyme-linked immunosorbent assay (ELISA). The receiver operating characteristic (ROC) curve analysis and associations were conducted. Further, five machine learning models, including decision tree, random forest, support vector machine, XGBoost, and lightGBM were implemented. The lightGBM model obtained a sensitivity of 81.4%, a specificity of 67.3%, and an area under the curve (AUC) of 0.822 for identifying CAD patients with a stenosis rate of <30% versus >30%. In this study, we provided a demonstration of a monitoring model with clinical data and AACT. Full article

(This article belongs to the Special Issue Implementing AI in Diagnosis of Cardiovascular Diseases)

► Show Figures

Figure 1

Review

Jump to: Research

16 pages, 4925 KiB

Open AccessReview

Meta-Analysis of Cardiovascular Risk Factors in Offspring of Preeclampsia Pregnancies

by Weikai Wang, Ru Lin, Lan Yang, Yanxia Wang, Baohong Mao, Xiaoying Xu and Jing Yu

Diagnostics 2023, 13(4), 812; https://doi.org/10.3390/diagnostics13040812 - 20 Feb 2023

Cited by 3 | Viewed by 1454

Abstract

This study aimed to assess cardiovascular risk factors in the offspring of preeclampsia (PE) pregnancies. PubMed, Web of Science, Ovid, and other foreign language databases, as well as SinoMed, China National Knowledge Infrastructure, Wanfang, and China Science and Technology Journal Databases, were searched. The case-control studies on cardiovascular risk factors in the offspring of PE pregnancies from 1 January 2010 to 31 December 2019 were collected. A random-effects model or a fixed-effects model was used, and RevMan 5.3 software was used for meta-analysis to determine the OR value and 95%CI of each cardiovascular risk factor. A total of 16 documents were included in this research, all of which were case-control studies, with a total of 4046 cases in the experimental group and 31,505 in the control group. The meta-analysis that was conducted demonstrated that SBP [MD = 1.51, 95%CI (1.15, 1.88)] and DBP [MD = 1.90, 95%CI (1.69, 2.10)] values in the PE pregnancy offspring group presented an elevation relative to the non-PE pregnancy offspring group. The total cholesterol value in the PE pregnancy offspring group presented an elevation relative to the non-PE pregnancy offspring group [MD = 0.11, 95%CI (0.08, 0.13)]. The low-density lipoprotein cholesterol value in the PE pregnancy offspring group was comparable to that in the non-PE pregnancy offspring group [MD = 0.01, 95%CI (−0.02, 0.05)]. The high-density lipoprotein cholesterol value in the PE pregnancy offspring group presented an elevation relative to the non-PE pregnancy offspring group [MD = 0.02, 95%CI (0.01, 0.03)]. The non-HDL cholesterol value in the PE pregnancy offspring group presented an elevation relative to the non-PE pregnancy offspring group [MD = 0.16, 95%CI (0.13, 0.19)]. The triglycerides [MD = −0.02, 95%CI (−0.03, −0.01)] and glucose [MD = −0.08, 95%CI (−0.09, −0.07)] values in the PE pregnancy offspring group presented a depletion relative to the non-PE pregnancy group. The insulin value in the PE pregnancy offspring group presented a depletion relative to the non-PE pregnancy offspring group [MD = −0.21, 95%CI (−0.32, −0.09)]. The BMI value in the PE pregnancy offspring group presented an elevation relative to the non-PE pregnancy offspring group [MD = 0.42, 95%CI (0.27, 0.57)]. In conclusion, dyslipidemia, elevated blood pressure, and increased BMI occur postpartum with PE, all of which are risk factors for cardiovascular diseases. Full article

(This article belongs to the Special Issue Implementing AI in Diagnosis of Cardiovascular Diseases)

► Show Figures