Article
Chemistry, Multidisciplinary
Jin-A Lee, Keun-Chang Kwak
Summary: This paper proposes a method for heart sound classification using wavelet analysis techniques and an ensemble of deep learning models. The experimental results show that the proposed method performs well on two datasets compared to previous methods.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Biomedical
Xingyao Wang, Chengyu Liu, Yuwen Li, Xianghong Cheng, Jianqing Li, Gari D. Clifford
Summary: The TFAN algorithm outperformed other models in heart sound segmentation, with higher accuracy and better generalization capabilities, while using fewer parameters.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2021)
Article
Computer Science, Information Systems
Yang Chen, Bo Su, Wei Zeng, Chengzhi Yuan, Bing Ji
Summary: The objective of this study is to develop an automatic classification method for anomaly detection of heart sound signals. It uses a deep neural network (DNN) model to extract features from raw data, which are then fed to various shallow classifiers for anomaly detection. The proposed method achieves the highest accuracy of 99.61% and 99.44% for binary and multi-class classification, respectively, outperforming other state-of-the-art methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Biomedical
Sangita Das, Saurabh Pal, Madhuchhanda Mitra
Summary: A low-cost noninvasive heart murmur detection system based on phonocardiogram (PCG) signals was proposed in this study. By employing unsupervised segmentation and deep neural networks (DNN) with three hidden layers, the system achieved an F1-score of 98.31% and accuracy of 98.33% in identifying heart murmurs. This system can be highly beneficial in rural healthcare settings and small hospitals to assist general physicians in diagnosing heart diseases without specialized cardiology expertise.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Computer Science, Information Systems
Batyrkhan Omarov, Nurbek Saparkhojayev, Shyrynkyz Shekerbekova, Oxana Akhmetova, Meruert Sakypbekova, Guldina Kamalova, Zhanna Alimzhanova, Lyailya Tukenova, Zhadyra Akanova
Summary: Cardiovascular diseases are a leading cause of death globally. This study presents a prototype of a digital stethoscopic system that uses machine learning methods to diagnose cardiac abnormalities in real time. The system achieves an accuracy of over 90% in identifying abnormal heart sounds and offers the key advantage of speed and convenience.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Engineering, Electrical & Electronic
Monjur Morshed, Shaikh Anowarul Fattah
Summary: In this article, a deep learning network using split-self attention with residual paths is proposed for the automatic detection of heart valve defects (HVDs) from phonocardiogram (PCG) signals. The design of the network, which includes attention blocks and multipath feature extractors, improves the classification performance. Experimental results on two publicly available datasets demonstrate high accuracy and competitive performance compared to existing models.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Agostino Giorgio, Cataldo Guaragnella, Maria Rizzi
Summary: The study of heart sound signals is important for monitoring heart diseases and assessing heart hemodynamic condition. A computer-aided system is proposed to assist cardiologists in screening and prevention of cardiovascular pathology by segmenting and classifying phonocardiogram records. Features are extracted and analyzed for redundancy and discrimination capacity, and the system's performance is evaluated using the PhysioNet/CinC Challenge 2016 database, showing its ability to aid specialists in clinical practice.
CIRCUITS SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Chemistry, Multidisciplinary
Xingchen Xu, Xingguang Geng, Zhixing Gao, Hao Yang, Zhiwei Dai, Haiying Zhang
Summary: This paper proposes a new optimal heart sound segmentation algorithm based on K-means clustering and Haar wavelet transform, which can accurately localize S1 and S2. The algorithm includes three parts: extracting the envelope function of heart sound energy using the Viola integral method and Shannon's energy-based algorithm, extracting time-frequency domain features from the acquired envelope, and searching for the optimal peak adaptively based on a dynamic segmentation threshold. Finally, K-means clustering and Haar wavelet transform are used to localize S1 and S2 in the time domain. Validation results show that the algorithm achieves high recognition rates for S1 and S2, outperforming other methods.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Biomedical
Davoud Shariat Panah, Andrew Hines, Susan McKeever
Summary: The development of data-driven heart sound classification models is an active research area. Noise and degradations in heart sound signals can reduce the accuracy of these models. This study investigates the impact of different noises and degradations on the performance of heart sound classification models.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Chemistry, Analytical
Heejoon Park, Qun Wei, Soomin Lee, Miran Lee
Summary: Heart sounds and heart rate are important physiological signals for diagnosing cardiovascular diseases. This study presents a smart stethoscope that can measure these signals using multiple modalities simultaneously for personal cardiovascular health monitoring. The device is designed in the shape of a computer mouse for easy handling and uses a digital microphone and photoplethysmogram sensor to measure heart sound and pulse. Pre-processing of the measured data and communication with a smartphone are performed to improve the accuracy of existing methods.
Article
Computer Science, Information Systems
Ethan Grooby, Chiranjibi Sitaula, Davood Fattahi, Reza Sameni, Kenneth Tan, Lindsay Zhou, Arrabella King, Ashwin Ramanathan, Atul Malhotra, Guy Dumont, Faezeh Marzbanrad
Summary: This paper presents novel artificial intelligence-based methods for separating neonatal chest sounds. The proposed NMF and NMCF methods outperform existing methods in terms of signal-to-noise ratios, vital sign estimation error, and signal quality improvement.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Samit Kumar Ghosh, R. N. Ponnalagu, Rajesh Kumar Tripathy, Ganapati Panda, Ram Bilas Pachori
Summary: This article proposes a time-frequency-domain deep neural network approach for automated FHSA detection using PCG signals. The proposed method achieved higher accuracy compared to existing methods, according to the experiments conducted on two standard databases.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Cardiac & Cardiovascular Systems
David Susic, Gregor Poglajen, Anton Gradisek
Summary: Early detection of decompensation episodes in chronic heart failure patients is crucial in preventing hospitalizations, and machine learning algorithms show promise in improving this early detection.
FRONTIERS IN CARDIOVASCULAR MEDICINE
(2022)
Article
Chemistry, Analytical
Yan Chen, Aisheng Hou, Xiaodong Wu, Ting Cong, Zhikang Zhou, Youyou Jiao, Yungen Luo, Yuheng Wang, Weidong Mi, Jiangbei Cao
Summary: This study utilized a flexible material-based heart sound monitoring device on swine models to evaluate the degree of hemorrhagic shock. The results demonstrated that changes in the second heart sound correlated well with blood pressure and could be an early indicator of HS severity.
Article
Engineering, Electrical & Electronic
Samarjeet Das, Debasish Jyotishi, Samarendra Dandapat
Summary: This study proposes a novel method for detecting heart valve diseases using a phonocardiogram signal. The method combines feature fusion models with a hierarchical long-short-term memory network and achieves high accuracy in binary and multiclass classification.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Editorial Material
Computer Science, Cybernetics
Joao Barroso, Manuel Perez Cota, Hugo Paredes, Leontios Hadjileontiadis
UNIVERSAL ACCESS IN THE INFORMATION SOCIETY
(2017)
Article
Obstetrics & Gynecology
Kyriaki Spyridou, Ioanna Chouvarda, Leontios Hadjileontiadis, Nikolaos Maglaveras
JOURNAL OF PERINATAL MEDICINE
(2017)
Article
Engineering, Biomedical
Simanto Saha, Khawza Iftekhar Uddin Ahmed, Raqibul Mostafa, Leontios Hadjileontiadis, Ahsan Khandoker
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2018)
Review
Multidisciplinary Sciences
Leontios J. Hadjileontiadis
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES
(2018)
Article
Multidisciplinary Sciences
Dimitrios Iakovakis, Stelios Hadjidimitriou, Vasileios Charisis, Sevasti Bostantzopoulou, Zoe Katsarou, Leontios J. Hadjileontiadis
SCIENTIFIC REPORTS
(2018)
Article
Computer Science, Information Systems
Mohanad Alkhodari, Herbert F. Jelinek, Naoufel Werghi, Leontios J. Hadjileontiadis, Ahsan H. Khandoker
Summary: This study utilized ECG data to estimate LVEF levels, with the lowest RMSE observed during 3-4 am, 5-6 am and 6-7 pm, suggesting these as possible intervention and optimal treatment times. Furthermore, following the ACCF/AHA guidelines for LVEF classification leads to a more accurate assessment of mid-range LVEF, paving the way for automated classification processes for CAD patients.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2021)
Review
Health Care Sciences & Services
Ghada Alhussein, Leontios Hadjileontiadis
Summary: This study presents a systematic review and meta-analysis of mHealth apps targeting osteoporosis self-management. The results show that these apps can support and improve the management of osteoporosis and its symptoms, making them valuable tools for both patients and healthcare professionals.
JMIR MHEALTH AND UHEALTH
(2022)
Article
Health Care Sciences & Services
Peter Lee, Heepyung Kim, Yongshin Kim, Woohyeok Choi, M. Sami Zitouni, Ahsan Khandoker, Herbert F. Jelinek, Leontios Hadjileontiadis, Uichin Lee, Yong Jeong
Summary: This paper reviews smart masks that have emerged after the pandemic and explores their expansion, sensor technologies, and application platforms. Smart masks can address breathing discomfort from prolonged use and can be used for sensing COVID-19 and general health monitoring. Additionally, smart masks can enable group or community sensing, increasing the range and reliability of information. The service application fields for smart masks include daily-life health monitoring, sports training, protection for industry workers and soldiers, as well as respiratory hygiene in emergency rooms and ambulatory settings. Design considerations include sensor reliability, ergonomic design for user acceptance, and privacy-aware data handling.
JMIR MHEALTH AND UHEALTH
(2022)
Article
Health Care Sciences & Services
Despoina Petsani, Evdokimos Konstantinidis, Aikaterini-Marina Katsouli, Vasiliki Zilidou, Sofia B. Dias, Leontios Hadjileontiadis, Panagiotis Bamidis
Summary: This paper aims to predict well-being digital biomarkers using data collected from interactions with serious games (SG). The results showed that in-game metrics can effectively categorize participants and predict the value range of specific tests. These findings provide evidence for the value of in-game metrics as digital biomarkers.
JMIR SERIOUS GAMES
(2022)
Review
Health Care Sciences & Services
Peter Lee, Heepyung Kim, M. Sami Zitouni, Ahsan Khandoker, Herbert F. Jelinek, Leontios Hadjileontiadis, Uichin Lee, Yong Jeong
Summary: This paper provides a comprehensive analysis of smart helmet technology and its applications in promoting health and safety. It reviews the current trends and potential deployments of smart helmets, with a focus on continuous monitoring of users' health status and environmental conditions. The research includes a selection of relevant studies and an assessment of their quality.
JMIR MHEALTH AND UHEALTH
(2022)
Article
Health Care Sciences & Services
Stelios Hadjidimitriou, Efstathios Pagourelias, Georgios Apostolidis, Ioannis Dimaridis, Vasileios Charisis, Constantinos Bakogiannis, Leontios Hadjileontiadis, Vassilios Vassilikos
Summary: The objective of this study is to validate the clinical performance of an artificial intelligence-based tool for estimating left ventricular ejection fraction (LV-EF) and global longitudinal strain (LV-GLS) from echocardiography scans. The study consists of two phases, involving cardiologists and the AI tool to compare their accuracy and reliability in estimation. The results are expected to be available by summer 2023.
JMIR RESEARCH PROTOCOLS
(2023)
Review
Cardiac & Cardiovascular Systems
Mohanad Alkhodari, Zhaohan Xiong, Ahsan H. Khandoker, Leontios J. Hadjileontiadis, Paul Leeson, Winok Lapidaire
Summary: This review discusses the integration of artificial intelligence (AI) and big data analysis for personalized cardiovascular care, specifically in the management of hypertensive disorders of pregnancy (HDP). The use of AI can provide personalized recommendations based on a deeper analysis of medical history and imaging data, leading to improved knowledge on pregnancy-related disorders and personalized treatment planning.
EXPERT REVIEW OF CARDIOVASCULAR THERAPY
(2023)
Review
Cardiac & Cardiovascular Systems
Nikolina-Alexia Fasoula, Yi Xie, Nikoletta Katsouli, Mario Reidl, Michael A. Kallmayer, Hans-Henning Eckstein, Vasilis Ntziachristos, Leontios Hadjileontiadis, Dimitrios V. Avgerinos, Alexandros Briasoulis, Gerasimos Siasos, Kaveh Hosseini, Ilias Doulamis, Polydoros N. Kampaktsis, Angelos Karlas
Summary: Microvascular changes in diabetes can affect critical organ function, and the development of tools and techniques to detect these changes early is crucial. Various sensing and imaging techniques have been developed or used to assess microangiopathy in diabetic patients, including innovative technologies with translational potential.
JOURNAL OF CARDIOVASCULAR DEVELOPMENT AND DISEASE
(2023)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Abdulrahman Awad, Aamna AlShehhi, Sofia B. Dias, Sofia J. Hadjileontiadou, Leontios J. Hadjileontiadis
Summary: This study models user engagement with Learning Management Systems (LMSs) using a combined approach of blended and collaborative learning and predicts the Quality of Interaction (QoI) using Temporal Convolutional Neural Networks (T-CNN). The feedback from the T-CNN model provides insights to enhance the pedagogical experience.
TECHNOLOGY AND INNOVATION IN LEARNING, TEACHING AND EDUCATION, TECH-EDU 2022
(2022)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Sofia Dias, Leontios J. Hadjileontiadis, Herbert F. Jelinek
Summary: This article proposes a new rehabilitation framework called MultiGRehab, which combines serious games with multimodal biosignals for personalized post-stroke or post-heart attack recovery. By capturing and analyzing real-time biosignals during a patient's rehabilitation session, MultiGRehab estimates the patient's emotional state and adjusts the exercise type, duration, and intensity level in the serious game. This framework aims to increase patient motivation, adherence to the exercise protocol, and personalize rehabilitation targets and outcomes.
2022 IEEE INTERNATIONAL CONFERENCE ON DIGITAL HEALTH (IEEE ICDH 2022)
(2022)