Hasil untuk "Diseases of the respiratory system"

Guantong Qi, Jiasheng Wang, Mei Ling Chong et al.

Millions of children worldwide are affected by severe rare Mendelian disorders, yet exome and genome sequencing still fail to provide a definitive molecular diagnosis for a large fraction of patients, prolonging the diagnostic odyssey. Bridging this gap increasingly requires transitioning from DNA-only interpretation to multi-modal diagnostic reasoning that combines genomic data, transcriptomic sequencing (RNA-seq), and phenotype information; however, computational frameworks that coherently integrate these signals remain limited. Here we present RareCollab, an agentic diagnostic framework that pairs a stable quantitative Diagnostic Engine with Large Language Model (LLM)-based specialist modules that produce high-resolution, interpretable assessments from transcriptomic signals, phenotypes, variant databases, and the literature to prioritize potential diagnostic variants. In a rigorously curated benchmark of Undiagnosed Diseases Network (UDN) patients with paired genomic and transcriptomic data, RareCollab achieved 77% top-5 diagnostic accuracy and improved top-1 to top-5 accuracy by ~20% over widely used variant-prioritization approaches. RareCollab illustrates how modular artificial intelligence (AI) can operationalize multi-modal evidence for accurate, scalable rare disease diagnosis, offering a promising path toward reducing the diagnostic odyssey for affected families.

Divine Darlington Logo, Prakash B. Kodali, Judith Anaman-Torgbor et al.

Introduction Tobacco use among adolescents is a concern in the Upper East Region of Ghana. We estimated the prevalence and identified factors contributing to single and multiple use of tobacco products among junior high school students in Ghana. Methods We conducted a cross-sectional analysis of a baseline survey of a schoolbased tobacco control intervention among adolescents in the Upper East Region of Ghana in 2022. A multi-stage cluster sampling approach was employed to identify the study sample, and data were collected using self-administered questionnaires. Current use of single tobacco products (at least one: cigarette, e-cigarette, shisha, or smokeless tobacco products) and multiple products (≥2 products) in the past 30 days was assessed. Multinomial logistic regression was used to assess the association of sociodemographic characteristics, perceptions towards tobacco’s health risks, and exposure to tobacco products with single and multiple product use. Adjusted relative risk ratios (ARRR) and their corresponding 95% confidence intervals (CI) were computed. Results We surveyed 1328 adolescents, comprising an equal proportion of males (49.8%) and females (50.4%). One in five (21.7%) reported using tobacco products, with 11.5% using single products and 13.0% using multiple products. Shisha (13.6%), cigarettes (10.6%), e-cigarettes (8.2%), and smokeless tobacco (6.0%) were used. A number of factors were identified to be associated with tobacco use among adolescents. Conclusions One in five junior high school students used at least one form of tobacco product. Adolescent tobacco use is impacted by demographic factors and risk perceptions. Further studies are needed to better understand these associations.

Peidong Wei, Shiyu Miao, Lin Li

Deep neural networks have been applied to audio spectrograms for respiratory sound classification, but it remains challenging to achieve satisfactory performance due to the scarcity of available data. Moreover, domain mismatch may be introduced into the trained models as a result of the respiratory sound samples being collected from various electronic stethoscopes, patient demographics, and recording environments. To tackle this issue, we proposed a modified MaskedAutoencoder(MAE) model, named Disentangling Dual-Encoder MAE (DDE-MAE) for respiratory sound classification. Two independent encoders were designed to capture disease-related and disease-irrelevant information separately, achieving feature disentanglement to reduce the domain mismatch. Our method achieves a competitive performance on the ICBHI dataset.

Akinari Atsumi, Tetsuo Tani, Kota Ishioka et al.

ABSTRACT A 62‐year‐old woman with a history of papillary thyroid carcinoma presented to our hospital with fever and cough and was diagnosed with stage IV non‐small cell lung carcinoma (NSCLC). One year after chemoimmunotherapy, a re‐biopsy of the left pleural tumour lesion was performed. Histological analysis revealed papillary thyroid carcinoma. Another biopsy was performed on the primary tumour, and the histological analysis of the primary tumour lesion confirmed NSCLC. BRAF V600E mutations were detected in both left pleural metastatic lesions of papillary thyroid carcinoma and the primary tumour of NSCLC. Dabrafenib and trametinib reduced both tumour lesions. Here, we report a rare case of concomitant BRAF V600E‐mutated NSCLC and pleural metastasis from papillary thyroid carcinoma.

A. J. Bequet, C. Jallais, J. Quick et al.

Stress impacts driving-related cognitive functions like attention and decision-making, and may arise in automated vehicles due to non-driving tasks. Unobtrusive relaxation techniques are needed to regulate stress without distracting from driving. Tactile wearables have shown efficacy in stress regulation through respiratory guidance, but individual variations may affect their efficacy. This study assessed slow-breathing tactile guidance under different stress levels on 85 participants. Physiological, behavioral and subjective data were collected. The influence of individual variations (e.g., driving habits and behavior, personality) using logistic regression analysis was explored. Participants could follow the guidance and adjust breathing while driving, but subjective efficacy depended on individual variations linked to different efficiency in using the technique, in relation with its attentional cost. An influence of factors linked to the evaluation of context criticality was also found. The results suggest that considering individual and contextual variations is crucial in designing and using such techniques in demanding driving contexts. In this line some design recommendations and insights for further studies are provided.

Shijia Ge, Weixiang Zhang, Shuzhao Xie et al.

Respiratory sound classification plays a pivotal role in diagnosing respiratory diseases. While deep learning models have shown success with various respiratory sound datasets, our experiments indicate that models trained on one dataset often fail to generalize effectively to others, mainly due to data collection and annotation \emph{inconsistencies}. To address this limitation, we introduce \emph{Lungmix}, a novel data augmentation technique inspired by Mixup. Lungmix generates augmented data by blending waveforms using loudness and random masks while interpolating labels based on their semantic meaning, helping the model learn more generalized representations. Comprehensive evaluations across three datasets, namely ICBHI, SPR, and HF, demonstrate that Lungmix significantly enhances model generalization to unseen data. In particular, Lungmix boosts the 4-class classification score by up to 3.55\%, achieving performance comparable to models trained directly on the target dataset.

Yuwei Zhang, Tong Xia, Aaqib Saeed et al.

The high incidence and mortality rates associated with respiratory diseases underscores the importance of early screening. Machine learning models can automate clinical consultations and auscultation, offering vital support in this area. However, the data involved, spanning demographics, medical history, symptoms, and respiratory audio, are heterogeneous and complex. Existing approaches are insufficient and lack generalizability, as they typically rely on limited training data, basic fusion techniques, and task-specific models. In this paper, we propose RespLLM, a novel multimodal large language model (LLM) framework that unifies text and audio representations for respiratory health prediction. RespLLM leverages the extensive prior knowledge of pretrained LLMs and enables effective audio-text fusion through cross-modal attentions. Instruction tuning is employed to integrate diverse data from multiple sources, ensuring generalizability and versatility of the model. Experiments on five real-world datasets demonstrate that RespLLM outperforms leading baselines by an average of 4.6% on trained tasks, 7.9% on unseen datasets, and facilitates zero-shot predictions for new tasks. Our work lays the foundation for multimodal models that can perceive, listen to, and understand heterogeneous data, paving the way for scalable respiratory health diagnosis.

Yuwei Zhang, Tong Xia, Jing Han et al.

Respiratory audio, such as coughing and breathing sounds, has predictive power for a wide range of healthcare applications, yet is currently under-explored. The main problem for those applications arises from the difficulty in collecting large labeled task-specific data for model development. Generalizable respiratory acoustic foundation models pretrained with unlabeled data would offer appealing advantages and possibly unlock this impasse. However, given the safety-critical nature of healthcare applications, it is pivotal to also ensure openness and replicability for any proposed foundation model solution. To this end, we introduce OPERA, an OPEn Respiratory Acoustic foundation model pretraining and benchmarking system, as the first approach answering this need. We curate large-scale respiratory audio datasets (~136K samples, over 400 hours), pretrain three pioneering foundation models, and build a benchmark consisting of 19 downstream respiratory health tasks for evaluation. Our pretrained models demonstrate superior performance (against existing acoustic models pretrained with general audio on 16 out of 19 tasks) and generalizability (to unseen datasets and new respiratory audio modalities). This highlights the great promise of respiratory acoustic foundation models and encourages more studies using OPERA as an open resource to accelerate research on respiratory audio for health. The system is accessible from https://github.com/evelyn0414/OPERA.

Bushra Ahmed, Michele Arigliani, Atul Gupta

Acute chest syndrome (ACS) is a leading cause of respiratory distress and hospitalisation in children with sickle cell disease (SCD). The aetiology is multifactorial and includes fat embolism, venous thromboembolism, alveolar hypoventilation and respiratory infections, with the latter being particularly common in children. These triggers contribute to a vicious cycle of erythrocyte sickling, adhesion to the endothelium, haemolysis, vaso-occlusion and ventilation–perfusion mismatch in the lungs, resulting in the clinical manifestations of ACS. The clinical presentation includes fever, chest pain, dyspnoea, cough, wheeze and hypoxia, accompanied by a new pulmonary infiltrate on chest radiography. Respiratory symptoms may overlap with those of acute asthma, which may be difficult to distinguish. Patients with ACS may deteriorate rapidly; thus prevention, early recognition and aggressive, multidisciplinary team management is essential. In this narrative review, we highlight the current evidence regarding the epidemiology, pathophysiology, treatment and preventative strategies for ACS, focusing on the aspects of major interest for the paediatric pulmonologist and multidisciplinary team who manage children with SCD.

Zifang Li, Yu Sheng, Dongdong Huang

Carbapenem-resistant Acinetobacter baumannii (CR-AB) is rarely found in community respiratory infections, and there are currently no reports of hemorrhagic bronchitis caused by its infection. This work presents a case of bronchial bleeding in a diabetic patient who acquired a community-acquired infection of CR-AB. Treatment with levofloxacin was unsuccessful, as the patient's hemoptysis symptoms recur. The patient was treated with minocycline based on the drug sensitivity test, resulting in the disappearance of hemoptysis symptoms. The patient was subjected to follow-up by phone for three months and did not experience any further hemoptysis symptoms. This case highlights that CR-AB infection causes hemorrhagic bronchitis, and the antimicrobial treatment should be based on drug sensitivity results.

Gerdinique (G. C.) Maessen, Thijs ( T. W.) Hoffman, Lidwien ( L.) Graat‐Verboom et al.

Abstract Pulmonary artery pseudoaneurysm (PAP) is a rare cause of hemoptysis. Potential causes include trauma, infection, or medical interventions. There is a risk of rupture, which is associated with a high mortality rate. We describe a 72‐year‐old patient, with a past medical history of a lung carcinoma for which she was treated with chemoradiotherapy 6 years prior, who presented with hemoptysis. She was hemodynamically stable and there were no other complaints. CT angiography of the thorax showed a PAP originating from a branch of the right pulmonary artery in the previously irradiated area. The patient was successfully treated by an embolization with plugs. Treatment of lung carcinoma with chemoradiotherapy can result in the development of a PAP. Clinicians should be aware of this complication, even years after the therapy. In literature, only a few cases of PAP in patients treated with (chemo)radiotherapy for lung cancer are described, with a maximum interval up to 7 years.

Chao Du, Chaohai Wang, Fang Zhang et al.

Abstract Background The new coronavirus Omicron variant strain spread rapidly worldwide and is currently the primary mutant strain prevalent in the world. Objective To explore the clinical features of severe central nervous system lesions in children infected with novel coronavirus Omicron mutant strain, so as to provide a reference for clinical diagnosis and treatment. Materials and methods The clinical data of 13 children diagnosed with novel coronavirus Omicron variant strain complicated with severe central nervous system infection from December 13, 2022, to January 31, 2023, in the Children’s Intensive Care Medicine Department of Shanxi Children’s Hospital were retrospectively analyzed. Results Among the 13 children, there were 9 males (69%) and 4 females (31%); the ages ranged from 1-year-old 16 days to 13 years old, with a median age of 9 years old, and most of them were school-age children (84.6%). The 13 children were usually healthy, but this time they were all positive for the new coronavirus nucleic acid test. The 13 children had obvious signs of the abnormal nervous system when they were admitted to the hospital, among which 12 cases (92.3%) showed convulsions, 11 children had obvious disturbance of consciousness (84.6%) when they were admitted to the hospital, and 5 children had circulatory disorders (38.4%). Among the 13 children, 2 were cured (15.3%), 5 children had serious sequelae (38.4%) when they were discharged from the hospital, and 6 children died of severe illness (46.3%). Conclusion This study illuminates the clinical characteristics of severe central nervous system complications in children with coronavirus variant infection, highlighting rapid onset, swift progression, relatively poor prognosis, and notable symptoms such as high fever, convulsions, altered consciousness, elevated interleukin-6 levels, increased cerebrospinal fluid lactate levels, and early imaging changes.

Mohd. Zuber, Charu Khosla, Nargis Begum Javed

Housing amounts to the physical structures that provide shelter, social services with a hygienic neighborhood, to fulfill the essential needs of the people. Housing factors have been shown to have an effect on an individual’s state of physical, mental, social and economic well-being. Indoor environmental factors such as crowding, environmental tobacco smoke, biofuels, dampness, house dust mites, temperature, age of building, pets, and indoor plants affect the wellbeing and productivity of the occupants. A literature review was performed on studies of housing conditions and health outcomes conducted in India and abroad from 1999 to 2020. The studies assessed housing quality by self-reported questionnaires administered through the postal system, face-to-face or via the internet. Visual signs and non-volumetric methods were used to assess indoor air quality and housing conditions, while the health of residents was assessed by self-reported questionnaire, or SF-36 questionnaire. Studies conducted in the United States of America, Europe, the United Kingdom, Middle East, Africa and Australasia have revealed that factors affecting health conditions were ventilation, dampness, presence of molds, overcrowding, house dust mite allergens, age and renovation of buildings and these factors showed an association with respiratory illnesses, colds, coughs, asthma, conjunctivitis, atopic dermatitis and ear infections. However, studies in India revealed that lack of proper ventilation, use of traditional fuels, crowding and poor hygienic conditions are the main factors associated with acute respiratory infections, asthma, tuberculosis, cardiovascular diseases and lung cancer. Thus, the review highlights that there is a need to improve housing conditions in India to enable the people to lead a healthy and productive life.

Fortune O. Alabi, Hadaya A. Alkhateeb, Mukudzeishe T. Zibanayi et al.

Abstract Background Despite the evidence-based guidelines promoted by the Global Initiative for Chronic Obstructive Lung Disease (GOLD), the overuse of prescription drugs to manage COPD, particularly inhaled corticosteroids (ICS), remains a persistent challenge. In this real-world study, we evaluated how patients with COPD were divided into ABCD groups based on the 2017 GOLD guidelines, determined the rate of adherence to the GOLD treatment recommendations, described the rate of ICS usage, and determined the rate of triple therapy (TT) prescription. Methods The charts of 2291 patients diagnosed with COPD were retrospectively analyzed, of which 1438 matched the eligibility criteria. Results The average patient age was 69.6 ± 10.9 years; 52% of patients were female. The average COPD assessment test (CAT) score was 18.3 ± 9.1. The ABCD breakdown was as follows: group A 19.5%, group B 64.1%, group C 1.8%, and group D 14.6%. All groups, except group D, showed discordance in COPD treatment relative to the proposed GOLD guidelines. Only 18.9% of group A and 26% of group B were treated in concordance with the guidelines. TT was primarily used in group D (63.3%) and overused in groups A (30.6%) and B (47.8%). ICS was overused in all groups, particularly in groups A (56.2%) and B (67.3%). Conclusion Studies from the last decade have consistently revealed a lack of conformity between what physicians prescribe and what GOLD guidelines recommend. The excessive usage of ICS, which continues despite all the associated adverse effects and the attributable costs, is concerning. The awareness of GOLD guidelines among primary care physicians (PCPs) and respiratory specialists needs to be improved.

Idil Aytekin, Onat Dalmaz, Kaan Gonc et al.

Monitoring of prevalent airborne diseases such as COVID-19 characteristically involves respiratory assessments. While auscultation is a mainstream method for preliminary screening of disease symptoms, its utility is hampered by the need for dedicated hospital visits. Remote monitoring based on recordings of respiratory sounds on portable devices is a promising alternative, which can assist in early assessment of COVID-19 that primarily affects the lower respiratory tract. In this study, we introduce a novel deep learning approach to distinguish patients with COVID-19 from healthy controls given audio recordings of cough or breathing sounds. The proposed approach leverages a novel hierarchical spectrogram transformer (HST) on spectrogram representations of respiratory sounds. HST embodies self-attention mechanisms over local windows in spectrograms, and window size is progressively grown over model stages to capture local to global context. HST is compared against state-of-the-art conventional and deep-learning baselines. Demonstrations on crowd-sourced multi-national datasets indicate that HST outperforms competing methods, achieving over 83% area under the receiver operating characteristic curve (AUC) in detecting COVID-19 cases.

Zizhao Chen, Hongliang Wang, Chia-Hui Yeh et al.

Recognizing patterns in lung sounds is crucial to detecting and monitoring respiratory diseases. Current techniques for analyzing respiratory sounds demand domain experts and are subject to interpretation. Hence an accurate and automatic respiratory sound classification system is desired. In this work, we took a data-driven approach to classify abnormal lung sounds. We compared the performance using three different feature extraction techniques, which are short-time Fourier transformation (STFT), Mel spectrograms, and Wav2vec, as well as three different classifiers, including pre-trained ResNet18, LightCNN, and Audio Spectrogram Transformer. Our key contributions include the bench-marking of different audio feature extractors and neural network based classifiers, and the implementation of a complete pipeline using STFT and a fine-tuned ResNet18 network. The proposed method achieved Harmonic Scores of 0.89, 0.80, 0.71, 0.36 for tasks 1-1, 1-2, 2-1 and 2-2, respectively on the testing sets in the IEEE BioCAS 2022 Grand Challenge on Respiratory Sound Classification.

Matthias Hüser, Martin Faltys, Xinrui Lyu et al.

The development of respiratory failure is common among patients in intensive care units (ICU). Large data quantities from ICU patient monitoring systems make timely and comprehensive analysis by clinicians difficult but are ideal for automatic processing by machine learning algorithms. Early prediction of respiratory system failure could alert clinicians to patients at risk of respiratory failure and allow for early patient reassessment and treatment adjustment. We propose an early warning system that predicts moderate/severe respiratory failure up to 8 hours in advance. Our system was trained on HiRID-II, a data-set containing more than 60,000 admissions to a tertiary care ICU. An alarm is typically triggered several hours before the beginning of respiratory failure. Our system outperforms a clinical baseline mimicking traditional clinical decision-making based on pulse-oximetric oxygen saturation and the fraction of inspired oxygen. To provide model introspection and diagnostics, we developed an easy-to-use web browser-based system to explore model input data and predictions visually.

Chinazunwa Uwaoma

While physical activity has been described as a primary prevention against chronic diseases, strenuous physical exertion under adverse ambient conditions has also been reported as a major contributor to exacerbation of chronic respiratory conditions. Maintaining a balance by monitoring the type and the level of physical activities of affected individuals, could help in reducing the cost and burden of managing respiratory ailments. This paper explores the potentiality of motion sensors in Smartphones to estimate physical activity thresholds that could trigger symptoms of exercise induced respiratory conditions (EiRCs). The focus is on the extraction of measurements from the embedded motion sensors to determine the activity level and the type of activity that is tolerable to individuals respiratory health. The calculations are based on the correlation between Signal Magnitude Area (SMA) and Energy Expenditure (EE). We also consider the effect of changes in the ambient conditions like temperature and humidity, as contributing factors to respiratory distress during physical exercise. Real time data collected from healthy individuals were used to demonstrate the potentiality of a mobile phone as tool to regulate the level of physical activities of individuals with EiRCs. We describe a practical situation where the experimental outcomes can be applied to promote good respiratory health.

Lam Pham

This thesis focuses on dealing with the task of acoustic scene classification (ASC), and then applied the techniques developed for ASC to a real-life application of detecting respiratory disease. To deal with ASC challenges, this thesis addresses three main factors that directly affect the performance of an ASC system. Firstly, this thesis explores input features by making use of multiple spectrograms (log-mel, Gamma, and CQT) for low-level feature extraction to tackle the issue of insufficiently discriminative or descriptive input features. Next, a novel Encoder network architecture is introduced. The Encoder firstly transforms each low-level spectrogram into high-level intermediate features, or embeddings, and thus combines these high-level features to form a very distinct composite feature. The composite or combined feature is then explored in terms of classification performance, with different Decoders such as Random Forest (RF), Multilayer Perception (MLP), and Mixture of Experts (MoE). By using this Encoder-Decoder framework, it helps to reduce the computation cost of the reference process in ASC systems which make use of multiple spectrogram inputs. Since the proposed techniques applied for general ASC tasks were shown to be highly effective, this inspired an application to a specific real-life application. This was namely the 2017 Internal Conference on Biomedical Health Informatics (ICBHI) respiratory sound dataset. Building upon the proposed ASC framework, the ICBHI tasks were tackled with a deep learning framework, and the resulting system shown to be capable at detecting respiratory anomaly cycles and diseases.

Zurabi Ugulava, Zaza Osmanov

In this work we investigate viral load propagation due to liquid droplets expelled during respiratory actions. We describe a mechanism of the transmission of such evaporating system and analyze dependence on several ambient parameters for different respiratory processes, such as sneezing, coughing and speaking. Our study has found that a significant amount of viral load and droplets from the respiratory fluid might transfer beyond the customary 2m distance, understanding of which might give us a better insight about regulations and risks posed by an infected individual.