-
Military Medical Research Sep 2023Auscultation is crucial for the diagnosis of respiratory system diseases. However, traditional stethoscopes have inherent limitations, such as inter-listener variability... (Review)
Review
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 .
Topics: Humans; Stethoscopes; Artificial Intelligence; Respiratory Sounds; Deep Learning; Reproducibility of Results; Retrospective Studies
PubMed: 37749643
DOI: 10.1186/s40779-023-00479-3 -
Journal of Veterinary Diagnostic... Sep 2023Two adult mixed-breed ewes were presented with a 2-wk history of upper respiratory disease. Both animals were depressed, with bilateral serosanguineous nasal discharge...
Two adult mixed-breed ewes were presented with a 2-wk history of upper respiratory disease. Both animals were depressed, with bilateral serosanguineous nasal discharge and harsh bronchovesicular sounds accompanied by crackles and wheezes on auscultation. One animal was recumbent and was euthanized at presentation. The other animal with similar signs, as well as exophthalmos, was euthanized because of a mass in the nasal passages. On autopsy, severe pyogranulomatous and necrotizing ethmoidal rhinitis with focal pyogranulomatous pneumonia was diagnosed in both animals. An intralesional fungal organism was identified in the nares and lungs of both animals. The organism could not be isolated via fungal culture but was identified as sp. by a PCR assay. spp. are rarely associated with disease in veterinary medicine. This ubiquitous fungus might cause disease following trauma to the nasal passages or secondary to immunocompromise.
Topics: Female; Animals; Sheep; Trichosporonosis; Lung; Pneumonia; Trichosporon; Sheep Diseases
PubMed: 37387318
DOI: 10.1177/10406387231185568 -
The Canadian Veterinary Journal = La... Mar 2024To describe the findings, treatment, and outcome of small intestinal volvulus (SIV) in 47 cows.
OBJECTIVE
To describe the findings, treatment, and outcome of small intestinal volvulus (SIV) in 47 cows.
ANIMALS AND PROCEDURE
Retrospective analysis of medical records. Comparison of the findings for 18 surviving and 29 non-surviving cows.
RESULTS
The most common abnormal vital signs were tachycardia (68.0%), tachypnea (59.6%), and decreased rectal temperature (51.1%). Signs of colic occurred in 66.0% of cows in the study. Rumen motility was reduced or absent in 93.6% of cows, and intestinal motility in 76.6%. Clinical signs on ballottement and/or percussion and simultaneous auscultation were positive on the right side in 78.7% of cows. Transrectal examination showed dilated small intestines in 48.9% of cows. The rectum contained little or no feces in 93.6% of cows. The principal laboratory abnormalities were hypocalcemia (74.1%), hypokalemia (73.8%), azotemia (62.8%), hypermagnesemia (61.6%), and hemoconcentration (60.0%). The principal ultrasonographic findings were dilated small intestines (87.1%) and reduced or absent small intestinal motility (85.2%). Forty-one of the 47 cows underwent right flank laparotomy and the SIV was reduced in 21 cows. When comparing the clinical and laboratory findings of 18 surviving and 29 non-surviving cows, the groups differed significantly with respect to severely abnormal general condition (16.7 37.9%), rumen stasis (22.2 79.3%), intestinal atony (16.7 48.3%), serum urea concentration (6.5 9.8 mmol/L), and serum magnesium concentration (0.98 1.30 mmol/L). In summary, 38.3% of the cows were discharged and 61.7% were euthanized before, during, or after surgery.
CONCLUSION AND CLINICAL RELEVANCE
An acute course of disease, little or no feces in the rectum, and dilated small intestines were characteristic of SIV in this study population.
Topics: Humans; Female; Cattle; Animals; Pregnancy; Intestinal Volvulus; Retrospective Studies; Intestine, Small; Rectum; Feces; Magnesium; Cattle Diseases
PubMed: 38434172
DOI: No ID Found -
Journal of Applied Physiology... Oct 2023Regular Finnish sauna use is associated with a reduced risk of cardiovascular mortality. However, physiological mechanisms underlying this association remain unknown.... (Randomized Controlled Trial)
Randomized Controlled Trial
Regular Finnish sauna use is associated with a reduced risk of cardiovascular mortality. However, physiological mechanisms underlying this association remain unknown. This study determined if an 8-wk Finnish sauna intervention improves peripheral endothelial function, microvascular function, central arterial stiffness, and blood pressure in adults with coronary artery disease (CAD). Forty-one adults (62 ± 6 yr, 33 men/8 women) with stable CAD were randomized to 8 wk of Finnish sauna use ( = 21, 4 sessions/wk, 20-30 min/session, 79°C, 13% relative humidity) or a control intervention ( = 20, lifestyle maintenance). Brachial artery flow-mediated dilation (FMD), carotid-femoral pulse wave velocity (cf-PWV), total (area under the curve) and peak postocclusion forearm reactive hyperemia, and blood pressure (automated auscultation) were measured before and after the intervention. After the sauna intervention, resting core temperature was lower (-0.27°C [-0.54, -0.01], = 0.046) and sweat rate during sauna exposure was greater (0.3 L/h [0.1, 0.5], = 0.003). The change in brachial artery FMD did not differ between interventions (control: 0.07% [-0.99, +1.14] vs. sauna: 0.15% [-0.89, +1.19], interaction = 0.909). The change in total ( = 0.031) and peak ( = 0.024) reactive hyperemia differed between interventions due to a nonsignificant decrease in response to the sauna intervention and an increase in response to control. The change in cf-PWV ( = 0.816), systolic ( = 0.951), and diastolic ( = 0.292) blood pressure did not differ between interventions. These results demonstrate that four sessions of Finnish sauna bathing per week for 8 wk does not improve markers of vascular health in adults with stable CAD. This study determined if unsupervised Finnish sauna bathing for 8 wk improves markers of vascular health in adults with coronary artery disease. Finnish sauna bathing reduced resting core temperature and improved sweating capacity, indicative of heat acclimation. Despite evidence of heat acclimation, Finnish sauna bathing did not improve markers of endothelial function, microvascular function, arterial stiffness, or blood pressure.
Topics: Male; Adult; Female; Humans; Steam Bath; Coronary Artery Disease; Hyperemia; Pulse Wave Analysis; Blood Pressure
PubMed: 37650138
DOI: 10.1152/japplphysiol.00322.2023 -
Micromachines Nov 2023The aim of this work is to present a preliminary study for the design of a digital auscultation system, i.e., a novel wearable device for patient chest auscultation and...
The aim of this work is to present a preliminary study for the design of a digital auscultation system, i.e., a novel wearable device for patient chest auscultation and a digital stethoscope. The development and testing of the electronic stethoscope prototype is reported with an emphasis on the description and selection of sound transduction systems and analog electronic processing. The focus on various microphone technologies, such as micro-electro-mechanical systems (MEMSs), electret condensers, and piezoelectronic diaphragms, intends to emphasize the most suitable transducer for auscultation. In addition, we report on the design and development of a digital acquisition system for the human body for sound recording by using a modular device approach in order to fit the chosen analog and digital mics. Tests were performed on a designed phantom setup, and a qualitative comparison between the sounds recorded with the newly developed acquisition device and those recorded with two commercial digital stethoscopes is reported.
PubMed: 38004949
DOI: 10.3390/mi14112092 -
Medicina (Kaunas, Lithuania) Dec 2023Point-of-care ultrasound (PoCUS) has become an indispensable standard in emergency medicine. Emergency medicine ultrasound (EMUS) is the application of bedside PoCUS by... (Review)
Review
Point-of-care ultrasound (PoCUS) has become an indispensable standard in emergency medicine. Emergency medicine ultrasound (EMUS) is the application of bedside PoCUS by the attending emergency physician to assist in the diagnosis and management of many time-sensitive health emergencies. In many ways, using PoCUS is not only the mere application of technology, but also a fusion of already existing examiner skills and technology in the context of a patient encounter. EMUS practice can be defined using distinct anatomy-based applications. The type of applications and their complexity usually depend on local needs and resources, and practice patterns can vary significantly among regions, countries, or even continents. A different approach suggests defining EMUS in categories such as resuscitative, diagnostic, procedural guidance, symptom- or sign-based, and therapeutic. Because EMUS is practiced in a constantly evolving emergency medical setting where no two patient encounters are identical, the concept of EMUS should also be practiced in a fluid, constantly adapting manner driven by the physician treating the patient. Many recent advances in ultrasound technology have received little or no attention from the EMUS community, and several important technical advances and research findings have not been translated into routine clinical practice. The authors believe that four main areas have great potential for the future growth and development of EMUS and are worth integrating: 1. In recent years, many articles have been published on novel ultrasound applications. Only a small percentage has found its way into routine use. We will discuss two important examples: trauma ultrasound that goes beyond e-FAST and EMUS lung ultrasound for suspected pulmonary embolism. 2. The more ultrasound equipment becomes financially affordable; the more ultrasound should be incorporated into the physical examination. This merging and possibly even replacement of aspects of the classical physical exam by technology will likely outperform the isolated use of stethoscope, percussion, and auscultation. 3. The knowledge of pathophysiological processes in acute illness and ultrasound findings should be merged in clinical practice. The translation of this knowledge into practical concepts will allow us to better manage many presentations, such as hypotension or the dyspnea of unclear etiology. 4. Technical innovations such as elastography; CEUS; highly sensitive color Doppler such as M-flow, vector flow, or other novel technology; artificial intelligence; cloud-based POCUS functions; and augmented reality devices such as smart glasses should become standard in emergencies over time.
Topics: Humans; Point-of-Care Systems; Artificial Intelligence; Emergencies; Ultrasonography; Emergency Medicine
PubMed: 38138282
DOI: 10.3390/medicina59122179 -
Computers in Biology and Medicine Sep 2023Cardiopulmonary and cardiovascular diseases are fatal factors that threaten human health and cause many deaths worldwide each year, so it is essential to screen... (Review)
Review
Cardiopulmonary and cardiovascular diseases are fatal factors that threaten human health and cause many deaths worldwide each year, so it is essential to screen cardiopulmonary disease more accurately and efficiently. Auscultation is a non-invasive method for physicians' perception of the disease. The Heart Sounds (HS) and Lung Sounds (LS) recorded by an electronic stethoscope consist of acoustic information that is helpful in the diagnosis of pulmonary conditions. Still, inter-interference between HS and LS presented in both the time and frequency domains blocks diagnostic efficiency. This paper proposes a blind source separation (BSS)strategy that first classifies Heart-Lung-Sound (HLS) according to its LS features and then separates it into HS and LS. Sparse Non-negative Matrix Factorization (SNMF) is employed to extract the LS features in HLS, then proposed a network constructed by Dilated Convolutional Neural Network (DCNN) to classify HLS into five types by the magnitude features of LS. Finally, Multi-Channel UNet (MCUNet) separation model is utilized for each category of HLS. This paper is the first to propose the HLS classification method SNMF-DCNN and apply UNet to the cardiopulmonary sound separation domain. Compared with other state-of-the-art methods, the proposed framework in this paper has higher separation quality and robustness.
Topics: Humans; Heart Sounds; Respiratory Sounds; Neural Networks, Computer; Algorithms; Lung
PubMed: 37499297
DOI: 10.1016/j.compbiomed.2023.107282 -
Biomedical Signal Processing and Control Aug 2023Stethoscopes are used ubiquitously in clinical settings to 'listen' to lung sounds. The use of these systems in a variety of healthcare environments (hospitals, urgent...
Stethoscopes are used ubiquitously in clinical settings to 'listen' to lung sounds. The use of these systems in a variety of healthcare environments (hospitals, urgent care rooms, private offices, community sites, mobile clinics, etc.) presents a range of challenges in terms of ambient noise and distortions that mask lung signals from being heard clearly or processed accurately using auscultation devices. With advances in technology, computerized techniques have been developed to automate analysis or access a digital rendering of lung sounds. However, most approaches are developed and tested in controlled environments and do not reflect real-world conditions where auscultation signals are typically acquired. Without a priori access to a recording of the ambient noise (for signal-to-noise estimation) or a reference signal that reflects the true undistorted lung sound, it is difficult to evaluate the quality of the lung signal and its potential clinical interpretability. The current study proposes an objective reference-free Auscultation Quality Metric (AQM) which incorporates low-level signal attributes with high-level representational embeddings mapped to a nonlinear quality space to provide an independent evaluation of the auscultation quality. This metric is carefully designed to solely judge the signal based on its integrity relative to external distortions and masking effects and not confuse an adventitious breathing pattern as low-quality auscultation. The current study explores the robustness of the proposed AQM method across multiple clinical categorizations and different distortion types. It also evaluates the temporal sensitivity of this approach and its translational impact for deployment in digital auscultation devices.
PubMed: 38274002
DOI: 10.1016/j.bspc.2023.104852