1
|
Smolinska S, Popescu FD, Izquierdo E, Antolín-Amérigo D, Price OJ, Alvarez-Perea A, Eguíluz Gracia I, Papadopoulos NG, Pfaar O, Fassio F, Hoffmann-Sommergruber K, Dramburg S, Agache I, Jutel M, Brough HA, Fonseca JA, Angier E, Boccabella C, Bonini M, Dunn Galvin A, Gibson PG, Gawlik R, Hannachi F, Kalayci Ö, Klimek L, Knibb R, Matricardi P, Chivato T. Telemedicine with special focus on allergic diseases and asthma-Status 2022: An EAACI position paper. Allergy 2024; 79:777-792. [PMID: 38041429 DOI: 10.1111/all.15964] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2023] [Revised: 10/31/2023] [Accepted: 11/08/2023] [Indexed: 12/03/2023]
Abstract
Efficacious, effective and efficient communication between healthcare professionals (HCP) and patients is essential to achieve a successful therapeutic alliance. Telemedicine (TM) has been used for decades but during the COVID-19 pandemic its use has become widespread. This position paper aims to describe the terminology and most important forms of TM among HCP and patients and review the existing studies on the uses of TM for asthma and allergy. Besides, the advantages and risks of TM are discussed, concluding that TM application reduces costs and time for both, HCP and patients, but cannot completely replace face-to-face visits for physical examinations and certain tests that are critical in asthma and allergy. From an ethical point of view, it is important to identify those involved in the TM process, ensure confidentiality and use communication channels that fully guarantee the security of the information. Unmet needs and directions for the future regarding implementation, data protection, privacy regulations, methodology and efficacy are described.
Collapse
Affiliation(s)
- Sylwia Smolinska
- Department of Clinical Immunology, Wroclaw Medical University, Wroclaw, Poland
| | - Florin-Dan Popescu
- Department of Allergology, Nicolae Malaxa Clinical Hospital, Carol Davila University of Medicine and Pharmacy, Bucharest, Romania
| | - Elena Izquierdo
- Department of Basic Medical Sciences, Facultad de Medicina, Institute of Applied Molecular Medicine Instituto de Medicina Molecular Aplicada Nemesio Díez (IMMA), Universidad San Pablo-CEU, CEU Universities, Urbanización Montepríncipe, Madrid, Spain
| | - Darío Antolín-Amérigo
- Servicio de Alergia, Hospital Universitario Ramón y Cajal, Instituto Ramón y Cajal de Investigación Sanitaria (IRYCIS), Madrid, Spain
| | - Oliver J Price
- School of Biomedical Sciences, Faculty of Biological Sciences, University of Leeds, Leeds, UK
| | - Alberto Alvarez-Perea
- Allergy Service, Hospital General Universitario Gregorio Marañón, Madrid, Spain
- Gregorio Marañón Health Research Institute, Madrid, Spain
| | - Ibon Eguíluz Gracia
- Allergy Department, Hospital Regional Universitario de Malaga and Allergy Research Group, Instituto de Investigacion Biomedica de Malaga (IBIMA-Plataforma BIONAND). RICORS "Inflammatory Diseases", Malaga, Spain
| | - Nikolaos G Papadopoulos
- Allergy Department, 2nd Pediatric Clinic, National Kapodistrian University of Athens, Athens, Greece
| | - Oliver Pfaar
- Department of Otorhinolaryngology, Head and Neck Surgery, Section of Rhinology and Allergy, University Hospital Marburg, Philipps-Universität Marburg, Marburg, Germany
| | | | | | - Stephanie Dramburg
- Department of Pediatric Respiratory Care, Immunology and Intensive Care Medicine, Charité Universitätsmedizin, Berlin, Germany
| | - Ioana Agache
- Allergy and Clinical Immunology at Transylvania University, Brasov, Romania
| | - Marek Jutel
- Department of Clinical Immunology, Wroclaw Medical University, Wroclaw, Poland
- "ALL-MED" Medical Research Institute, Wroclaw, Poland
| | - Helen A Brough
- Children's Allergy Service, Evelina Children's Hospital, Guy's and St. Thomas' Hospital, London, UK
- Department of Women and Children's Health, School of Life Course Sciences, King's College London, London, UK
| | - João A Fonseca
- CINTESIS@RISE, MEDCIDS, Faculty of Medicine of the University of Porto, Porto, Portugal
| | - Elizabeth Angier
- Primary Care, Population Science and Medical Education, Faculty of Medicine, University of Southampton, Southampton, UK
| | - Cristina Boccabella
- Department of Cardiovascular and Thoracic Sciences, Fondazione Policlinico Universitario A Gemelli IRCCS, Università Cattolica del Sacro Cuore, Rome, Italy
| | - Matteo Bonini
- Department of Cardiovascular and Thoracic Sciences, Università Cattolica del Sacro Cuore, Rome, Italy
- Department of Clinical and Surgical Sciences, Fondazione Policlinico Universitario A. Gemelli-IRCCS, Rome, Italy
- National Heart and Lung Institute (NHLI), Imperial College London, London, UK
| | | | - Peter G Gibson
- John Hunter Hospital, Hunter Medical Research Institute, University of Newcastle, Newcastle, New South Wales, Australia
| | - Radoslaw Gawlik
- Department of Internal Medicine, Allergology and Clinical Immunology, Medical University of Silesia, Katowice, Poland
| | - Farah Hannachi
- Immuno-Allergology Unit, Hospital Centre of Luxembourg, Luxembourg City, Luxembourg
| | - Ömer Kalayci
- Hacettepe University School of Medicine, Ankara, Turkey
| | - Ludger Klimek
- Center for Rhinology and Allergology, Wiesbaden, Germany
| | - Rebecca Knibb
- School of Psychology, College of Health and Life Sciences, Aston University, Birmingham, UK
| | - Paolo Matricardi
- Department of Pediatric Respiratory Care, Immunology and Intensive Care Medicine, Charité Universitätsmedizin, Berlin, Germany
| | - Tomás Chivato
- Department of Clinical Medical Sciences, Facultad de Medicina, Universidad San Pablo-CEU, CEU Universities, Urbanización Montepríncipe, Madrid, Spain
| |
Collapse
|
2
|
Kapetanidis P, Kalioras F, Tsakonas C, Tzamalis P, Kontogiannis G, Karamanidou T, Stavropoulos TG, Nikoletseas S. Respiratory Diseases Diagnosis Using Audio Analysis and Artificial Intelligence: A Systematic Review. SENSORS (BASEL, SWITZERLAND) 2024; 24:1173. [PMID: 38400330 PMCID: PMC10893010 DOI: 10.3390/s24041173] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/15/2023] [Revised: 02/03/2024] [Accepted: 02/04/2024] [Indexed: 02/25/2024]
Abstract
Respiratory diseases represent a significant global burden, necessitating efficient diagnostic methods for timely intervention. Digital biomarkers based on audio, acoustics, and sound from the upper and lower respiratory system, as well as the voice, have emerged as valuable indicators of respiratory functionality. Recent advancements in machine learning (ML) algorithms offer promising avenues for the identification and diagnosis of respiratory diseases through the analysis and processing of such audio-based biomarkers. An ever-increasing number of studies employ ML techniques to extract meaningful information from audio biomarkers. Beyond disease identification, these studies explore diverse aspects such as the recognition of cough sounds amidst environmental noise, the analysis of respiratory sounds to detect respiratory symptoms like wheezes and crackles, as well as the analysis of the voice/speech for the evaluation of human voice abnormalities. To provide a more in-depth analysis, this review examines 75 relevant audio analysis studies across three distinct areas of concern based on respiratory diseases' symptoms: (a) cough detection, (b) lower respiratory symptoms identification, and (c) diagnostics from the voice and speech. Furthermore, publicly available datasets commonly utilized in this domain are presented. It is observed that research trends are influenced by the pandemic, with a surge in studies on COVID-19 diagnosis, mobile data acquisition, and remote diagnosis systems.
Collapse
Affiliation(s)
- Panagiotis Kapetanidis
- Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece (C.T.); (G.K.); (S.N.)
| | - Fotios Kalioras
- Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece (C.T.); (G.K.); (S.N.)
| | - Constantinos Tsakonas
- Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece (C.T.); (G.K.); (S.N.)
| | - Pantelis Tzamalis
- Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece (C.T.); (G.K.); (S.N.)
| | - George Kontogiannis
- Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece (C.T.); (G.K.); (S.N.)
| | - Theodora Karamanidou
- Pfizer Center for Digital Innovation, 55535 Thessaloniki, Greece; (T.K.); (T.G.S.)
| | | | - Sotiris Nikoletseas
- Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece (C.T.); (G.K.); (S.N.)
| |
Collapse
|
3
|
Mang LD, González Martínez FD, Martinez Muñoz D, García Galán S, Cortina R. Classification of Adventitious Sounds Combining Cochleogram and Vision Transformers. SENSORS (BASEL, SWITZERLAND) 2024; 24:682. [PMID: 38276373 PMCID: PMC10818433 DOI: 10.3390/s24020682] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/27/2023] [Revised: 01/13/2024] [Accepted: 01/19/2024] [Indexed: 01/27/2024]
Abstract
Early identification of respiratory irregularities is critical for improving lung health and reducing global mortality rates. The analysis of respiratory sounds plays a significant role in characterizing the respiratory system's condition and identifying abnormalities. The main contribution of this study is to investigate the performance when the input data, represented by cochleogram, is used to feed the Vision Transformer (ViT) architecture, since this input-classifier combination is the first time it has been applied to adventitious sound classification to our knowledge. Although ViT has shown promising results in audio classification tasks by applying self-attention to spectrogram patches, we extend this approach by applying the cochleogram, which captures specific spectro-temporal features of adventitious sounds. The proposed methodology is evaluated on the ICBHI dataset. We compare the classification performance of ViT with other state-of-the-art CNN approaches using spectrogram, Mel frequency cepstral coefficients, constant-Q transform, and cochleogram as input data. Our results confirm the superior classification performance combining cochleogram and ViT, highlighting the potential of ViT for reliable respiratory sound classification. This study contributes to the ongoing efforts in developing automatic intelligent techniques with the aim to significantly augment the speed and effectiveness of respiratory disease detection, thereby addressing a critical need in the medical field.
Collapse
Affiliation(s)
- Loredana Daria Mang
- Department of Telecommunication Engineering, University of Jaen, 23700 Linares, Spain; (F.D.G.M.); (D.M.M.); (S.G.G.)
| | | | - Damian Martinez Muñoz
- Department of Telecommunication Engineering, University of Jaen, 23700 Linares, Spain; (F.D.G.M.); (D.M.M.); (S.G.G.)
| | - Sebastián García Galán
- Department of Telecommunication Engineering, University of Jaen, 23700 Linares, Spain; (F.D.G.M.); (D.M.M.); (S.G.G.)
| | - Raquel Cortina
- Department of Computer Science, University of Oviedo, 33003 Oviedo, Spain;
| |
Collapse
|
4
|
Huang DM, Huang J, Qiao K, Zhong NS, Lu HZ, Wang WJ. Deep learning-based lung sound analysis for intelligent stethoscope. Mil Med Res 2023; 10:44. [PMID: 37749643 PMCID: PMC10521503 DOI: 10.1186/s40779-023-00479-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/29/2023] [Accepted: 09/05/2023] [Indexed: 09/27/2023] Open
Abstract
Auscultation is crucial for the diagnosis of respiratory system diseases. However, traditional stethoscopes have inherent limitations, such as inter-listener variability and subjectivity, and they cannot record respiratory sounds for offline/retrospective diagnosis or remote prescriptions in telemedicine. The emergence of digital stethoscopes has overcome these limitations by allowing physicians to store and share respiratory sounds for consultation and education. On this basis, machine learning, particularly deep learning, enables the fully-automatic analysis of lung sounds that may pave the way for intelligent stethoscopes. This review thus aims to provide a comprehensive overview of deep learning algorithms used for lung sound analysis to emphasize the significance of artificial intelligence (AI) in this field. We focus on each component of deep learning-based lung sound analysis systems, including the task categories, public datasets, denoising methods, and, most importantly, existing deep learning methods, i.e., the state-of-the-art approaches to convert lung sounds into two-dimensional (2D) spectrograms and use convolutional neural networks for the end-to-end recognition of respiratory diseases or abnormal lung sounds. Additionally, this review highlights current challenges in this field, including the variety of devices, noise sensitivity, and poor interpretability of deep models. To address the poor reproducibility and variety of deep learning in this field, this review also provides a scalable and flexible open-source framework that aims to standardize the algorithmic workflow and provide a solid basis for replication and future extension: https://github.com/contactless-healthcare/Deep-Learning-for-Lung-Sound-Analysis .
Collapse
Affiliation(s)
- Dong-Min Huang
- Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, 518055, Guangdong, China
| | - Jia Huang
- The Third People's Hospital of Shenzhen, Shenzhen, 518112, Guangdong, China
| | - Kun Qiao
- The Third People's Hospital of Shenzhen, Shenzhen, 518112, Guangdong, China
| | - Nan-Shan Zhong
- Guangzhou Institute of Respiratory Health, China State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, 510120, China.
| | - Hong-Zhou Lu
- The Third People's Hospital of Shenzhen, Shenzhen, 518112, Guangdong, China.
| | - Wen-Jin Wang
- Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, 518055, Guangdong, China.
| |
Collapse
|
5
|
Ariyanti W, Liu KC, Chen KY, Yu-Tsao. Abnormal Respiratory Sound Identification Using Audio-Spectrogram Vision Transformer. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2023; 2023:1-4. [PMID: 38083782 DOI: 10.1109/embc40787.2023.10341036] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/18/2023]
Abstract
Respiratory disease, the third leading cause of deaths globally, is considered a high-priority ailment requiring significant research on identification and treatment. Stethoscope-recorded lung sounds and artificial intelligence-powered devices have been used to identify lung disorders and aid specialists in making accurate diagnoses. In this study, audio-spectrogram vision transformer (AS-ViT), a new approach for identifying abnormal respiration sounds, was developed. The sounds of the lungs are converted into visual representations called spectrograms using a technique called short-time Fourier transform (STFT). These images are then analyzed using a model called vision transformer to identify different types of respiratory sounds. The classification was carried out using the ICBHI 2017 database, which includes various types of lung sounds with different frequencies, noise levels, and backgrounds. The proposed AS-ViT method was evaluated using three metrics and achieved 79.1% and 59.8% for 60:40 split ratio and 86.4% and 69.3% for 80:20 split ratio in terms of unweighted average recall and overall scores respectively for respiratory sound detection, surpassing previous state-of-the-art results.
Collapse
|
6
|
Sfayyih AH, Sulaiman N, Sabry AH. A review on lung disease recognition by acoustic signal analysis with deep learning networks. JOURNAL OF BIG DATA 2023; 10:101. [PMID: 37333945 PMCID: PMC10259357 DOI: 10.1186/s40537-023-00762-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/08/2022] [Accepted: 05/08/2023] [Indexed: 06/20/2023]
Abstract
Recently, assistive explanations for difficulties in the health check area have been made viable thanks in considerable portion to technologies like deep learning and machine learning. Using auditory analysis and medical imaging, they also increase the predictive accuracy for prompt and early disease detection. Medical professionals are thankful for such technological support since it helps them manage further patients because of the shortage of skilled human resources. In addition to serious illnesses like lung cancer and respiratory diseases, the plurality of breathing difficulties is gradually rising and endangering society. Because early prediction and immediate treatment are crucial for respiratory disorders, chest X-rays and respiratory sound audio are proving to be quite helpful together. Compared to related review studies on lung disease classification/detection using deep learning algorithms, only two review studies based on signal analysis for lung disease diagnosis have been conducted in 2011 and 2018. This work provides a review of lung disease recognition with acoustic signal analysis with deep learning networks. We anticipate that physicians and researchers working with sound-signal-based machine learning will find this material beneficial.
Collapse
Affiliation(s)
- Alyaa Hamel Sfayyih
- Department of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Putra Malaysia, 43400 Serdang, Malaysia
| | - Nasri Sulaiman
- Department of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Putra Malaysia, 43400 Serdang, Malaysia
| | - Ahmad H. Sabry
- Department of Computer Engineering, Al-Nahrain University, Al Jadriyah Bridge, 64074 Baghdad, Iraq
| |
Collapse
|
7
|
Heitmann J, Glangetas A, Doenz J, Dervaux J, Shama DM, Garcia DH, Benissa MR, Cantais A, Perez A, Müller D, Chavdarova T, Ruchonnet-Metrailler I, Siebert JN, Lacroix L, Jaggi M, Gervaix A, Hartley MA. DeepBreath-automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries. NPJ Digit Med 2023; 6:104. [PMID: 37268730 DOI: 10.1038/s41746-023-00838-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/30/2022] [Accepted: 05/05/2023] [Indexed: 06/04/2023] Open
Abstract
The interpretation of lung auscultation is highly subjective and relies on non-specific nomenclature. Computer-aided analysis has the potential to better standardize and automate evaluation. We used 35.9 hours of auscultation audio from 572 pediatric outpatients to develop DeepBreath : a deep learning model identifying the audible signatures of acute respiratory illness in children. It comprises a convolutional neural network followed by a logistic regression classifier, aggregating estimates on recordings from eight thoracic sites into a single prediction at the patient-level. Patients were either healthy controls (29%) or had one of three acute respiratory illnesses (71%) including pneumonia, wheezing disorders (bronchitis/asthma), and bronchiolitis). To ensure objective estimates on model generalisability, DeepBreath is trained on patients from two countries (Switzerland, Brazil), and results are reported on an internal 5-fold cross-validation as well as externally validated (extval) on three other countries (Senegal, Cameroon, Morocco). DeepBreath differentiated healthy and pathological breathing with an Area Under the Receiver-Operator Characteristic (AUROC) of 0.93 (standard deviation [SD] ± 0.01 on internal validation). Similarly promising results were obtained for pneumonia (AUROC 0.75 ± 0.10), wheezing disorders (AUROC 0.91 ± 0.03), and bronchiolitis (AUROC 0.94 ± 0.02). Extval AUROCs were 0.89, 0.74, 0.74 and 0.87 respectively. All either matched or were significant improvements on a clinical baseline model using age and respiratory rate. Temporal attention showed clear alignment between model prediction and independently annotated respiratory cycles, providing evidence that DeepBreath extracts physiologically meaningful representations. DeepBreath provides a framework for interpretable deep learning to identify the objective audio signatures of respiratory pathology.
Collapse
Affiliation(s)
- Julien Heitmann
- Intelligent Global Health Research Group, Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland
| | - Alban Glangetas
- Division of Pediatric Emergency Medicine, Department of Women, Child and Adolescent, Geneva University Hospitals (HUG), University of Geneva, Switzerland, Geneva, Switzerland
| | - Jonathan Doenz
- Intelligent Global Health Research Group, Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland
| | - Juliane Dervaux
- Intelligent Global Health Research Group, Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland
| | - Deeksha M Shama
- Intelligent Global Health Research Group, Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland
| | - Daniel Hinjos Garcia
- Intelligent Global Health Research Group, Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland
| | - Mohamed Rida Benissa
- Division of Pediatric Emergency Medicine, Department of Women, Child and Adolescent, Geneva University Hospitals (HUG), University of Geneva, Switzerland, Geneva, Switzerland
| | - Aymeric Cantais
- Pediatric Emergency Department, Hospital University of Saint Etienne, Saint Etienne, France
| | - Alexandre Perez
- Division of Pediatric Emergency Medicine, Department of Women, Child and Adolescent, Geneva University Hospitals (HUG), University of Geneva, Switzerland, Geneva, Switzerland
| | - Daniel Müller
- Intelligent Global Health Research Group, Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland
| | - Tatjana Chavdarova
- Intelligent Global Health Research Group, Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland
| | - Isabelle Ruchonnet-Metrailler
- Division of Pediatric Emergency Medicine, Department of Women, Child and Adolescent, Geneva University Hospitals (HUG), University of Geneva, Switzerland, Geneva, Switzerland
| | - Johan N Siebert
- Division of Pediatric Emergency Medicine, Department of Women, Child and Adolescent, Geneva University Hospitals (HUG), University of Geneva, Switzerland, Geneva, Switzerland
| | - Laurence Lacroix
- Division of Pediatric Emergency Medicine, Department of Women, Child and Adolescent, Geneva University Hospitals (HUG), University of Geneva, Switzerland, Geneva, Switzerland
| | - Martin Jaggi
- Intelligent Global Health Research Group, Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland
| | - Alain Gervaix
- Division of Pediatric Emergency Medicine, Department of Women, Child and Adolescent, Geneva University Hospitals (HUG), University of Geneva, Switzerland, Geneva, Switzerland
| | - Mary-Anne Hartley
- Intelligent Global Health Research Group, Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland.
- Center for Intelligent Systems (CIS), Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland.
- Division of Pediatric Emergency Medicine, Department of Pediatrics, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland.
| |
Collapse
|
8
|
Sfayyih AH, Sabry AH, Jameel SM, Sulaiman N, Raafat SM, Humaidi AJ, Kubaiaisi YMA. Acoustic-Based Deep Learning Architectures for Lung Disease Diagnosis: A Comprehensive Overview. Diagnostics (Basel) 2023; 13:diagnostics13101748. [PMID: 37238233 DOI: 10.3390/diagnostics13101748] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2023] [Revised: 05/04/2023] [Accepted: 05/11/2023] [Indexed: 05/28/2023] Open
Abstract
Lung auscultation has long been used as a valuable medical tool to assess respiratory health and has gotten a lot of attention in recent years, notably following the coronavirus epidemic. Lung auscultation is used to assess a patient's respiratory role. Modern technological progress has guided the growth of computer-based respiratory speech investigation, a valuable tool for detecting lung abnormalities and diseases. Several recent studies have reviewed this important area, but none are specific to lung sound-based analysis with deep-learning architectures from one side and the provided information was not sufficient for a good understanding of these techniques. This paper gives a complete review of prior deep-learning-based architecture lung sound analysis. Deep-learning-based respiratory sound analysis articles are found in different databases including the Plos, ACM Digital Libraries, Elsevier, PubMed, MDPI, Springer, and IEEE. More than 160 publications were extracted and submitted for assessment. This paper discusses different trends in pathology/lung sound, the common features for classifying lung sounds, several considered datasets, classification methods, signal processing techniques, and some statistical information based on previous study findings. Finally, the assessment concludes with a discussion of potential future improvements and recommendations.
Collapse
Affiliation(s)
- Alyaa Hamel Sfayyih
- Department of Electrical and Electronic Engineering, Faculty of Engineering, University Putra Malaysia, Serdang 43400, Malaysia
| | - Ahmad H Sabry
- Department of Computer Engineering, Al-Nahrain University Al Jadriyah Bridge, Baghdad 64074, Iraq
| | | | - Nasri Sulaiman
- Department of Electrical and Electronic Engineering, Faculty of Engineering, University Putra Malaysia, Serdang 43400, Malaysia
| | - Safanah Mudheher Raafat
- Department of Control and Systems Engineering, University of Technology, Baghdad 10011, Iraq
| | - Amjad J Humaidi
- Department of Control and Systems Engineering, University of Technology, Baghdad 10011, Iraq
| | - Yasir Mahmood Al Kubaiaisi
- Department of Sustainability Management, Dubai Academic Health Corporation, Dubai 4545, United Arab Emirates
| |
Collapse
|
9
|
Park JS, Kim K, Kim JH, Choi YJ, Kim K, Suh DI. A machine learning approach to the development and prospective evaluation of a pediatric lung sound classification model. Sci Rep 2023; 13:1289. [PMID: 36690658 PMCID: PMC9871007 DOI: 10.1038/s41598-023-27399-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2022] [Accepted: 01/02/2023] [Indexed: 01/25/2023] Open
Abstract
Auscultation, a cost-effective and non-invasive part of physical examination, is essential to diagnose pediatric respiratory disorders. Electronic stethoscopes allow transmission, storage, and analysis of lung sounds. We aimed to develop a machine learning model to classify pediatric respiratory sounds. Lung sounds were digitally recorded during routine physical examinations at a pediatric pulmonology outpatient clinic from July to November 2019 and labeled as normal, crackles, or wheezing. Ensemble support vector machine models were trained and evaluated for four classification tasks (normal vs. abnormal, crackles vs. wheezing, normal vs. crackles, and normal vs. wheezing) using K-fold cross-validation (K = 10). Model performance on a prospective validation set (June to July 2021) was compared with those of pediatricians and non-pediatricians. Total 680 clips were used for training and internal validation. The model accuracies during internal validation for normal vs. abnormal, crackles vs. wheezing, normal vs. crackles, and normal vs. wheezing were 83.68%, 83.67%, 80.94%, and 90.42%, respectively. The prospective validation (n = 90) accuracies were 82.22%, 67.74%, 67.80%, and 81.36%, respectively, which were comparable to pediatrician and non-pediatrician performance. An automated classification model of pediatric lung sounds is feasible and maybe utilized as a screening tool for respiratory disorders in this pandemic era.
Collapse
Affiliation(s)
- Ji Soo Park
- Department of Pediatrics, Seoul National University College of Medicine, Seoul, South Korea
| | - Kyungdo Kim
- Department of Biomedical Engineering, Duke University, Durham, NC, USA
| | - Ji Hye Kim
- Department of Pediatrics, Seoul National University College of Medicine, Seoul, South Korea
| | - Yun Jung Choi
- Department of Pediatrics, Seoul National University College of Medicine, Seoul, South Korea
| | - Kwangsoo Kim
- Transdisciplinary Department of Medicine & Advanced Technology, Seoul National University Hospital, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, South Korea.
| | - Dong In Suh
- Department of Pediatrics, Seoul National University College of Medicine, Seoul, South Korea.
- Department of Pediatrics, Seoul National University Hospital, Seoul National University College of Medicine, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, South Korea.
| |
Collapse
|
10
|
Sonali CS, Kiran J, Chinmayi BS, Suma KV, Easa M. Transformer-Based Network for Accurate Classification of Lung Auscultation Sounds. Crit Rev Biomed Eng 2023; 51:1-16. [PMID: 37824331 DOI: 10.1615/critrevbiomedeng.2023048981] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/14/2023]
Abstract
Respiratory diseases are a major cause of death worldwide, affecting a significant proportion of the population with lung function abnormalities that can lead to respiratory illnesses. Early detection and prevention are critical to effective management of these disorders. Deep learning algorithms offer a promising approach for analyzing complex medical data and aiding in early disease detection. While transformer-based models for sequence classification have proven effective for tasks like sentiment analysis, topic classification, etc., their potential for respiratory disease classification remains largely unexplored. This paper proposes a classifier utilizing the transformer-encoder block, which can capture complex patterns and dependencies in medical data. The proposed model is trained and evaluated on a large dataset from the International Conference on Biomedical Health Informatics 2017, achieving state-of-the-art results with a mean sensitivity of 70.53%, mean specificity of 84.10%, mean average score of 77.32%, and mean harmonic score of 76.10%. These results demonstrate the model's effectiveness in diagnosing respiratory diseases while taking up minimal computational resources.
Collapse
Affiliation(s)
- C S Sonali
- Department of Electronics and Communication Engineering, Ramaiah Institute of Technology, Bengaluru, India
| | - John Kiran
- Department of Electronics and Communication Engineering, Ramaiah Institute of Technology, Bengaluru, India
| | - B S Chinmayi
- Department of Electronics and Communication Engineering, Ramaiah Institute of Technology, Bengaluru, India
| | - K V Suma
- Department of Electronics and Communication Engineering, Ramaiah Institute of Technology, Bengaluru, India
| | - Muhammad Easa
- Department of Electronics and Communication Engineering, Ramaiah Institute of Technology, Bengaluru, India
| |
Collapse
|
11
|
Xia T, Han J, Mascolo C. Exploring machine learning for audio-based respiratory condition screening: A concise review of databases, methods, and open issues. Exp Biol Med (Maywood) 2022; 247:2053-2061. [PMID: 35974706 PMCID: PMC9791302 DOI: 10.1177/15353702221115428] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/30/2022] Open
Abstract
Auscultation plays an important role in the clinic, and the research community has been exploring machine learning (ML) to enable remote and automatic auscultation for respiratory condition screening via sounds. To give the big picture of what is going on in this field, in this narrative review, we describe publicly available audio databases that can be used for experiments, illustrate the developed ML methods proposed to date, and flag some under-considered issues which still need attention. Compared to existing surveys on the topic, we cover the latest literature, especially those audio-based COVID-19 detection studies which have gained extensive attention in the last two years. This work can help to facilitate the application of artificial intelligence in the respiratory auscultation field.
Collapse
|
12
|
Spectral features and optimal Hierarchical attention networks for pulmonary abnormality detection from the respiratory sound signals. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2022.103905] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
|
13
|
Pham L, Ngo D, Tran K, Hoang T, Schindler A, McLoughlin I. An Ensemble of Deep Learning Frameworks for Predicting Respiratory Anomalies. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2022; 2022:4595-4598. [PMID: 36086440 DOI: 10.1109/embc48229.2022.9871440] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
This paper evaluates a range of deep learning frameworks for detecting respiratory anomalies from input audio. Audio recordings of respiratory cycles collected from patients are transformed into time-frequency spectrograms to serve as front-end two-dimensional features. Cropped spectrogram segments are then used to train a range of back-end deep learning networks to classify respiratory cycles into predefined medically-relevant categories. A set of those trained high-performance deep learning frameworks are then fused to obtain the best score. Our experiments on the ICBHI benchmark dataset achieve the highest ICBHI score to date of 57.3%. This is derived from a late fusion of inception based and transfer learning based deep learning frameworks, easily outperforming other state-of-the-art systems. Clinical relevance--- Respiratory disease, wheeze, crackle, inception, convolutional neural network, transfer learning.
Collapse
|
14
|
Nguyen T, Pernkopf F. Lung Sound Classification Using Co-tuning and Stochastic Normalization. IEEE Trans Biomed Eng 2022; 69:2872-2882. [PMID: 35254969 DOI: 10.1109/tbme.2022.3156293] [Citation(s) in RCA: 16] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
Computational methods for lung sound analysis are beneficial for computer-aided diagnosis support, storage and monitoring in critical care. In this paper, we use pre-trained ResNet models as backbone architectures for classification of adventitious lung sounds and respiratory diseases. The learned representation of the pre-trained model is transferred by using vanilla fine-tuning, co-tuning, stochastic normalization and the combination of the co-tuning and stochastic normalization techniques. Furthermore, data augmentation in both time domain and time-frequency domain is used to account for the class imbalance of the ICBHI and our multi-channel lung sound dataset. Additionally, we introduce spectrum correction to account for the variations of the recording device properties on the ICBHI dataset. Empirically, our proposed systems mostly outperform all state-of-the-art lung sound classification systems for the adventitious lung sounds and respiratory diseases of both datasets.
Collapse
|