Chronic Heart Failure Detection from Heart Sounds Using a Stack of Machine-Learning Classifiers

Gjoreski, Martin; Simjanoska, Monika; Gradišek, Anton; Peterlin, Ana; Gams, Matjaž; Poglajen, Gregor

doi:10.1109/ie.2017.19

Cited by 38 publications

(31 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chronic heart failure (CHF) is a chronic, progressive condition underscored by the heart's inability to supply enough perfusion to target tissues and organs at the physiological filling pressures to meet their metabolic demands [1]. CHF has reached epidemic proportions in the population, as its incidence is increasing by 2% annually.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2020

Self Cite

View full text Add to dashboard Cite

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 features, and the DL learns from a spectro-temporal representation of the signal. The method was evaluated on recordings from 947 subjects from six publicly available datasets and one CHF dataset that was collected for this study. Using the same evaluation method as a recent PhysoNet challenge, the proposed method achieved a score of 89.3, which is 9.1 higher than the challenge's baseline method. The method's aggregated accuracy is 92.9% (error of 7.1%); while the experimental results are not directly comparable, this error rate is relatively close to the percentage of recordings labeled as ''unknown'' by experts (9.7%). Finally, we identified 15 expert features that are useful for building ML models to differentiate between CHF phases (i.e., in the decompensated phase during hospitalization and in the recompensated phase) with an accuracy of 93.2%. The proposed method shows promising results both for the distinction of recordings between healthy subjects and patients and for the detection of different CHF phases. This may lead to the easier identification of new CHF patients and the development of home-based CHF monitors for avoiding hospitalizations. INDEX TERMS Chronic heart failure, deep learning, heart sounds, machine learning, PCG.

show abstract

Section: Introductionmentioning

confidence: 99%

“…In recent years, many studies have proposed Machine-Learning (ML) approaches for the automatic detection of different heart conditions using PCG signals recorded with a digital stethoscope [1]. Nevertheless, methods that explicitly focus on CHF detection are quite scarce.…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…To support them, computerized medical system [16]- [19] with full of functionalities are there, which specially built to assist healthcare industry for the sake of patient's time, money, and most importantly to help the surgeons to save the patient's life. A kind of system proposed by [1] using ML approach for predicting the heart failure using heart sound reports. The study shown another proof that machine learning methods can applied on life saving system such as heart failure detection.…”

Section: Machine Learning Classifiers For Heart Disease Predictionmentioning

confidence: 99%

“…The main cause of heart stroke is due to blockage in arteries. It has many other names such as cardiovascular disease and arterial hypertension [1]. Approximately, there are almost 26 million people around the world affecting with heart disease [2].…”

Section: Introductionmentioning

confidence: 99%

“…Noticeably, these reasons are independent from each other; proper analysis on this kind of dataset can improve the process of diagnosing and can assist the heart surgeons as well. Previously, different researches used number of techniques to improve the HF diagnosis process such as Extreme Learning Machine [8], heart disease classification [9], and machine learning classifiers [1].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Implementation of Machine Learning Model to Predict Heart Failure Disease

Alotaibi¹

2019

IJACSA

188

View full text Add to dashboard Cite

In the current era, Heart Failure (HF) is one of the common diseases that can lead to dangerous situation. Every year almost 26 million of patients are affecting with this kind of disease. From the heart consultant and surgeon's point of view, it is complex to predict the heart failure on right time. Fortunately, classification and predicting models are there, which can aid the medical field and can illustrates how to use the medical data in an efficient way. This paper aims to improve the HF prediction accuracy using UCI heart disease dataset. For this, multiple machine learning approaches used to understand the data and predict the HF chances in a medical database. Furthermore, the results and comparative study showed that, the current work improved the previous accuracy score in predicting heart disease. The integration of the machine learning model presented in this study with medical information systems would be useful to predict the HF or any other disease using the live data collected from patients.

show abstract

Advancements in wearable heart sounds devices for the monitoring of cardiovascular diseases

Ahmad,

Khan,

Hilal

et al. 2024

SmartMat

View full text Add to dashboard Cite

Cardiovascular diseases remain a leading global cause of mortality, underscoring the urgent need for intelligent diagnostic tools to enhance early detection, prediction, diagnosis, prevention, treatment, and recovery. This demand has spurred the advancement of wearable and flexible technologies, revolutionizing continuous, noninvasive, and remote heart sound (HS) monitoring—a vital avenue for assessing heart activity. The conventional stethoscope, used to listen to HSs, has limitations in terms of its physical structure, as it is inflexible and bulky, which restricts its prospective applications. Recently, mechanoacoustic sensors have made remarkable advancements, evolving from primitive forms to soft, flexible, and wearable designs. This article provides an in‐depth review of the latest scientific and technological advancements by addressing various topics, including different types of sensors, sensing materials, design principles, denoising techniques, and clinical applications of flexible and wearable HS sensors. This transformative potential lies in the capacity for ongoing, remote, and personalized monitoring, promising enhanced patient outcomes, amplified remote monitoring capabilities, and timely diagnoses. Last, the article highlights current challenges and prospects for the future, suggesting techniques to advance HS sensing technologies for exciting real‐time applications.

show abstract

Chronic Heart Failure Detection from Heart Sounds Using a Stack of Machine-Learning Classifiers

Cited by 38 publications

References 26 publications

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

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

Implementation of Machine Learning Model to Predict Heart Failure Disease

Advancements in wearable heart sounds devices for the monitoring of cardiovascular diseases

Contact Info

Product

Resources

About