Classification of Multi-Class Cardiovascular Disorders using Ensemble Classifier and Impulsive Domain Analysis
15 Jul 2021-
TL;DR: In this paper, an algorithm for classifying various types of cardiovascular diseases using PCG auscultations is proposed. But, the proposed methodology obtained a cumulative accuracy of 98.8 %, specificity of 97.56 %, and sensitivity of 99.99 %.
Abstract: Cardiovascular diseases (CVD) have been one of the top two causes of death globally, accounting for 633,842 fatalities. An intelligent system capable of detecting these disorders is needed urgently. Phonocardiogram (PCG) signals are useful in the earlier detection of CVDs as they help determine the actual nature and condition of the heart. Cardiac auscultation is the most used procedure for examining, classifying, and analyzing the cardiac sounds in a PCG. We formulated an algorithm for classifying various types of cardiovascular diseases using PCG auscultations. Dataset repository (Normal & Extrahls) is made up of personally acquired PCGs from different clinical facilities. Empirical Mode Decomposition (EMD) helps denoise and pre-process these raw signals. To extract the area of interest, soft threshold-based signal segmentation is applied. Then, four Impulsive domain features are extracted from each class’s pre-processed signal and fed to six separate machine learning-based ensemble classifiers to evaluate optimum accuracy. The proposed methodology obtained a cumulative accuracy of 98.8 %, specificity of 97.56%, and sensitivity of 99.99 %. This system will assist Pakistani doctors to detect and classify heart disease without any invasive technology usage.
Citations
More filters
TL;DR: The amalgamation of image-based strategies with conventional risk factors provides the highest stability when using the three CVD paradigms in non-cloud and cloud-based frameworks.
Abstract: Abstract Background and Motivation: Cardiovascular disease (CVD) causes the highest mortality globally. With escalating healthcare costs, early non-invasive CVD risk assessment is vital. Conventional methods have shown poor performance compared to more recent and fast-evolving Artificial Intelligence (AI) methods. The proposed study reviews the three most recent paradigms for CVD risk assessment, namely multiclass, multi-label, and ensemble-based methods in (i) office-based and (ii) stress-test laboratories. Methods: A total of 265 CVD-based studies were selected using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) model. Due to its popularity and recent development, the study analyzed the above three paradigms using machine learning (ML) frameworks. We review comprehensively these three methods using attributes, such as architecture, applications, pro-and-cons, scientific validation, clinical evaluation, and AI risk-of-bias (RoB) in the CVD framework. These ML techniques were then extended under mobile and cloud-based infrastructure. Findings: Most popular biomarkers used were office-based, laboratory-based, image-based phenotypes, and medication usage. Surrogate carotid scanning for coronary artery risk prediction had shown promising results. Ground truth (GT) selection for AI-based training along with scientific and clinical validation is very important for CVD stratification to avoid RoB. It was observed that the most popular classification paradigm is multiclass followed by the ensemble, and multi-label. The use of deep learning techniques in CVD risk stratification is in a very early stage of development. Mobile and cloud-based AI technologies are more likely to be the future. Conclusions: AI-based methods for CVD risk assessment are most promising and successful. Choice of GT is most vital in AI-based models to prevent the RoB. The amalgamation of image-based strategies with conventional risk factors provides the highest stability when using the three CVD paradigms in non-cloud and cloud-based frameworks.
14 citations
30 Aug 2021
TL;DR: In this paper, a Cubic-Support Vector Machine classifier is trained on four different EMG (Electromyography) based hand gestures named as wrist flexion, wrist extension, resting hand, clenched fist.
Abstract: Machines are built to give accessibility, precision, cost-effectiveness, and adaptability characteristics. This work will facilitate the recognition of hand gestures based on supervised learning. Signal processing-based techniques such as pre-processing (normalization) and segmentation (empirical mode decomposition) are employed. The Cubic-Support Vector Machine classifier is trained on four different EMG (Electromyography) based hand gestures named as wrist flexion, wrist extension, resting hand, clenched fist. Spectral domain features are extracted, which provide less variance than other extraction methods. This supervised machine learning model achieved a cumulative classification accuracy of 98.9%. This hand gesture-based system can help handicapped people in nonverbal communication and physically challenged individuals in non-invasive machine communication.
6 citations
TL;DR: In this article , the authors evaluate AI technology in the context of healthcare costs, namely in the areas of diagnosis and treatment, and then compare it to the traditional or non-AI-based approaches.
5 citations
TL;DR: A detailed summary of research done on fall detection systems, with comparisons across different types of studies, is provided in this paper , where datasets, limitations, and future imperatives in fall detection are discussed in detail.
Abstract: Falls are a major public health concern among the elderly and the number of gadgets designed to detect them has increased significantly in recent years. This document provides a detailed summary of research done on fall detection systems, with comparisons across different types of studies. Its purpose is to be a resource for doctors and engineers who are planning or conducting field research. Following the examination, datasets, limitations, and future imperatives in fall detection were discussed in detail. The quantity of research using context-aware approaches continues to rise, but there is a new trend toward integrating fall detection into smartphones, as well as the use of artificial intelligence in the detection algorithm. Concerns with real-world performance, usability, and reliability are also highlighted.
24 Nov 2022
TL;DR: In this paper , a range of classical methodologies that includes diverse factors such as ECG, blood pressure, blood glucose and cholesterol are reviewed in order to diagnose each type of cardiovascular disease and build a framework to help physicians.
Abstract: Cardiovascular disease (CVD), the predominant reason of deaths across the globe, has been a significant challenge to healthful living all over the world, placing a vast social-economic load on patients, families and nations annually. WHO (World Health Organization) report states that increase in cardiovascular risk factors such as high blood pressure, diabetes, overweight and smoking will lead to a maximize the mortality rate by 24.5 million in 2030. In many cases, the time before a doctor's visit and necessary hospitalization is significantly relied upon saving the life of patients. Therefore, the frequent updates are provided to the doctors about the medicinal status of patient in order to reduce the mortality rate. To find the risk of this disease, it is important to diagnose each type of cardiovascular disease (CVD) and build a framework to help physicians so that the accurate and effectual decisions are made during diagnosis. The doctors attempt to differentiate a coronary disorder by analyzing the values of various features. This work considers a range of classical methodologies that includes diverse factors such as ECG, blood pressure, blood glucose and cholesterol. The techniques of detecting the cardiovascular disease are reviewed in this paper.
References
More filters
TL;DR: A sequence of morphological operations is used to smooth the irregular boundary along the mediastinum in order to obtain results consistent with these obtained by manual analysis, in which only the most central pulmonary arteries are excluded from the lung region.
Abstract: Segmentation of pulmonary X-ray computed tomography (CT) images is a precursor to most pulmonary image analysis applications. This paper presents a fully automatic method for identifying the lungs in three-dimensional (3-D) pulmonary X-ray CT images. The method has three main steps. First, the lung region is extracted from the CT images by gray-level thresholding. Then, the left and right lungs are separated by identifying the anterior and posterior junctions by dynamic programming. Finally, a sequence of morphological operations is used to smooth the irregular boundary along the mediastinum in order to obtain results consistent with these obtained by manual analysis, in which only the most central pulmonary arteries are excluded from the lung region. The method has been tested by processing 3-D CT data sets from eight normal subjects, each imaged three times at biweekly intervals with lungs at 90% vital capacity. The authors present results by comparing their automatic method to manually traced borders from two image analysts. Averaged over all volumes, the root mean square difference between the computer and human analysis is 0.8 pixels (0.54 mm). The mean intrasubject change in tissue content over the three scans was 2.75%/spl plusmn/2.29% (mean/spl plusmn/standard deviation).
1,013 citations
Emory University1, University of Oxford2, Massachusetts Institute of Technology3, Polytechnic University of Valencia4, Georgia Institute of Technology5, University of Valencia6, University of Michigan7, Aalborg University8, Aristotle University of Thessaloniki9, K.N.Toosi University of Technology10, University of Upper Alsace11, University of Strasbourg12, Dalian University of Technology13, Shiraz University14, Isfahan University of Medical Sciences15
TL;DR: A public heart sound database, assembled for an international competition, the PhysioNet/Computing in Cardiology (CinC) Challenge 2016, which comprises nine different heart sound databases sourced from multiple research groups around the world is described.
Abstract: In the past few decades, analysis of heart sound signals (i.e. the phonocardiogram or PCG), especially for automated heart sound segmentation and classification, has been widely studied and has been reported to have the potential value to detect pathology accurately in clinical applications. However, comparative analyses of algorithms in the literature have been hindered by the lack of high-quality, rigorously validated, and standardized open databases of heart sound recordings. This paper describes a public heart sound database, assembled for an international competition, the PhysioNet/Computing in Cardiology (CinC) Challenge 2016. The archive comprises nine different heart sound databases sourced from multiple research groups around the world. It includes 2435 heart sound recordings in total collected from 1297 healthy subjects and patients with a variety of conditions, including heart valve disease and coronary artery disease. The recordings were collected from a variety of clinical or nonclinical (such as in-home visits) environments and equipment. The length of recording varied from several seconds to several minutes. This article reports detailed information about the subjects/patients including demographics (number, age, gender), recordings (number, location, state and time length), associated synchronously recorded signals, sampling frequency and sensor type used. We also provide a brief summary of the commonly used heart sound segmentation and classification methods, including open source code provided concurrently for the Challenge. A description of the PhysioNet/CinC Challenge 2016, including the main aims, the training and test sets, the hand corrected annotations for different heart sound states, the scoring mechanism, and associated open source code are provided. In addition, several potential benefits from the public heart sound database are discussed.
477 citations
TL;DR: Results indicate that the performance of SVM classifier is better than other machine learning-based classifiers on noise removed feature extracted signal for beat classification.
Abstract: Medical expert systems are part of the portable and smart healthcare monitoring devices used in day-to-day life. Arrhythmic beat classification is mainly used in electrocardiogram (ECG) abnormality detection for identifying heart related problems. In this paper, ECG signal preprocessing and support vector machine-based arrhythmic beat classification are performed to categorize into normal and abnormal subjects. In ECG signal preprocessing, a delayed error normalized LMS adaptive filter is used to achieve high speed and low latency design with less computational elements. Since the signal processing technique is developed for remote healthcare systems, white noise removal is mainly focused. Discrete wavelet transform is applied on the preprocessed signal for HRV feature extraction and machine learning techniques are used for performing arrhythmic beat classification. In this paper, SVM classifier and other popular classifiers have been used on noise removed feature extracted signal for beat classification. Results indicate that the performance of SVM classifier is better than other machine learning-based classifiers.
177 citations
TL;DR: The methodology discussed in this paper can be used to diagnose heart disorders in patients up to 97% accuracy and is improved, automatic classification algorithm for cardiac disorder by heart sound signal.
Abstract: Cardiac disorders are critical and must be diagnosed in the early stage using routine auscultation examination with high precision. Cardiac auscultation is a technique to analyze and listen to heart sound using electronic stethoscope, an electronic stethoscope is a device which provides the digital recording of the heart sound called phonocardiogram (PCG). This PCG signal carries useful information about the functionality and status of the heart and hence several signal processing and machine learning technique can be applied to study and diagnose heart disorders. Based on PCG signal, the heart sound signal can be classified to two main categories i.e., normal and abnormal categories. We have created database of 5 categories of heart sound signal (PCG signals) from various sources which contains one normal and 4 are abnormal categories. This study proposes an improved, automatic classification algorithm for cardiac disorder by heart sound signal. We extract features from phonocardiogram signal and then process those features using machine learning techniques for classification. In features extraction, we have used Mel Frequency Cepstral Coefficient (MFCCs) and Discrete Wavelets Transform (DWT) features from the heart sound signal, and for learning and classification we have used support vector machine (SVM), deep neural network (DNN) and centroid displacement based k nearest neighbor. To improve the results and classification accuracy, we have combined MFCCs and DWT features for training and classification using SVM and DWT. From our experiments it has been clear that results can be greatly improved when Mel Frequency Cepstral Coefficient and Discrete Wavelets Transform features are fused together and used for classification via support vector machine, deep neural network and k-neareast neighbor(KNN). The methodology discussed in this paper can be used to diagnose heart disorders in patients up to 97% accuracy. The code and dataset can be accessed at “https://github.com/yaseen21khan/Classification-of-Heart-Sound-Signal-Using-Multiple-Features-/blob/master/README.md”.
177 citations
01 Mar 2016
TL;DR: The objective of this study is to develop an automatic classification method for anomaly and quality detection of PCG recordings without segmentation in order to evaluate the heart hemodynamic status and to detect a cardiovascular disease.
Abstract: Phonocardiogram (PCG) signal is used as a diagnostic test in ambulatory monitoring in order to evaluate the heart hemodynamic status and to detect a cardiovascular disease. The objective of this study is to develop an automatic classification method for anomaly (normal vs. abnormal) and quality (good vs. bad) detection of PCG recordings without segmentation. For this purpose, a subset of 18 features is selected among 40 features based on a wrapper feature selection scheme. These features are extracted from time, frequency, and time-frequency domains without any segmentation. The selected features are fed into an ensemble of 20 feedforward neural networks for classification task. The proposed algorithm achieved the overall score of 91.50% (94.23% sensitivity and 88.76% specificity) and 85.90% (86.91% sensitivity and 84.90% specificity) on the train and unseen test datasets, respectively. The proposed method got the second best score in the PhysioNet/CinC Challenge 2016.
145 citations