Machine Learning and End-to-End Deep Learning for the Detection of Chronic Heart Failure From Heart Sounds

  title={Machine Learning and End-to-End Deep Learning for the Detection of Chronic Heart Failure From Heart Sounds},
  author={Martin Gjoreski and Anton Gradi{\vs}ek and Borut Budna and Matja{\vz} Gams and Gregor Poglajen},
  journal={IEEE Access},
Chronic heart failure (CHF) affects over 26 million of people worldwide, and its incidence is increasing by 2% annually. Despite the significant burden that CHF poses and despite the ubiquity of sensors in our lives, methods for automatically detecting CHF are surprisingly scarce, even in the research community. We present a method for CHF detection based on heart sounds. The method combines classic Machine-Learning (ML) and end-to-end Deep Learning (DL). The classic ML learns from expert… 
Heart Failure diagnosis based on deep learning techniques
The deep learning methods provide quite high results with the Autoencoder plus DNN approach to demonstrate accuracy 91.71%, sensitivity 90.74%, specificity 92.31% and f-score 89.36%.
Hilbert-Envelope Features for Cardiac Disease Classification from Noisy Phonocardiograms
A time-domain Hilbert envelope feature (HEF) extraction scheme that can effectively distinguish among different cardiac anomalies from heart sounds even in highly noisy recordings is proposed that can significantly impact computer-aided auscultation systems when deployed in noisy conditions.
Applications of Deep Learning in Cardiovascular Disease (CVD) diagnosis and prognosis: A Review
A brief literature survey has been done with machine learning and deep learning approaches to deal with CVDs and the accuracy of the machine learning model accuracy downgrades with image data.
Heart Anomaly Detection using Deep Learning Approach Supported Signal Analysis
An intelligent neural network approach for the classification of PCG data using a one-dimensional solution Neural network based on phonocardiogram data for discrepancies in the heart sound is proposed.
A Machine Learning Approach for Chronic Heart Failure Diagnosis
The aim of this study was to address chronic heart failure diagnosis with the application of machine learning (ML) approaches, and the results were quite satisfactory with a high accuracy, sensitivity, and specificity when features from all categories were utilized.
Machine Learning-Based Automated Diagnostic Systems Developed for Heart Failure Prediction Using Different Types of Data Modalities: A Systematic Review and Future Directions
This study targets systematic review of automated diagnosis for heart disease prediction based on different types of modalities, i.e., clinical feature-based data modality, images, and ECG, and critically evaluates the previous methods and presents the limitations in these methods.
Predicting Heart Disease at Early Stages using Machine Learning: A Survey
  • R. Katarya, P. Srinivas
  • Computer Science, Medicine
    2020 International Conference on Electronics and Sustainable Communication Systems (ICESC)
  • 2020
Predicting and detection of heart disease has always been a critical and challenging task for healthcare practitioners. Hospitals and other clinics are offering expensive therapies and operations to
Comparative Study to Identify the Heart Disease Using Machine Learning Algorithms
A development that which factor is vulnerable to heart disease given basic prefix like sex, glucose, Blood pressure, Heart rate, etc is proposed.
Score and Correlation Coefficient-Based Feature Selection for Predicting Heart Failure Diagnosis by Using Machine Learning Algorithms
A machine-learning-based approach that distinguishes the most important correlated features amongst patients' electronic clinical records is proposed and then feature engineering method has been applied to create new features correlated strongly in order to train machine learning models and obtain promising results.
Designing ECG Monitoring Healthcare System with Federated Transfer Learning and Explainable AI


Chronic Heart Failure Detection from Heart Sounds Using a Stack of Machine-Learning Classifiers
The study confirmed that advanced machine learning applied on real-life sounds recorded with an unobtrusive digital stethoscope can be used for chronic heart failure detection.
A convolutional neural network approach to detect congestive heart failure
A tensor approach to heart sound classification
  • I. D. Bobillo
  • Computer Science
    2016 Computing in Cardiology Conference (CinC)
  • 2016
This work presents an accurate, compact and fast algorithm that can effectively classify noisy PCG signals of different duration, achieving a balanced accuracy of 91.9% in 10-fold cross-validation, and 84.54% on the Challenge hidden test data.
Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds
The authors' classifier ensemble approach obtained the highest score of the competition with a sensitivity, specificity, and overall score of 0.9424, 0.7781, and 0.8602, respectively.
Classification of normal/abnormal heart sound recordings: The PhysioNet/Computing in Cardiology Challenge 2016
The PhysioNet/Computing in Cardiology (CinC) Challenge 2016 addresses the issue of a large and open database of heart sound recordings by assembling the largest public heart sound database, aggregated from eight sources obtained by seven independent research groups around the world.
DropConnected neural networks trained on time-frequency and inter-beat features for classifying heart sounds.
OBJECTIVE Automatic heart sound analysis has the potential to improve the diagnosis of valvular heart diseases in the primary care phase, as well as in countries where there is neither the expertise
Heart sound anomaly and quality detection using ensemble of neural networks without segmentation
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.
Bag-of-Deep-Features: Noise-Robust Deep Feature Representations for Audio Analysis
This paper quantises deep feature representations of various in-the-wild audio data sets by comparing the efficacy of various feature spaces extracted from different fully connected deep neural networks to classify six real-world audio corpora and shows the suitability of quantising the deep representations for noisy in- the- wild audio data.
Classical and deep learning methods for recognizing human activities and modes of transportation with smartphone sensors
Heart sounds analysis using probability assessment.
A method for automated discrimination of heart sounds recordings according to the Physionet Challenge 2016 to decide if the recording refers to normal or abnormal heart sounds or if it is not possible to decide, a prototype of a new machine-learning method.