Hasil untuk "Diseases of the respiratory system"

Theodore Aptekarev, Vladimir Sokolovsky, Gregory Furman

Respiratory sound analysis is a crucial tool for screening asthma and other pulmonary pathologies, yet traditional auscultation remains subjective and experience-dependent. Our prior research established a CNN baseline using DenseNet201, which demonstrated high sensitivity in classifying respiratory sounds. In this work, we (i) adapt the Audio Spectrogram Transformer (AST) for respiratory sound analysis and (ii) evaluate a multimodal Vision-Language Model (VLM) that integrates spectrograms with structured patient metadata. AST is initialized from publicly available weights and fine-tuned on a medical dataset containing hundreds of recordings per diagnosis. The VLM experiment uses a compact Moondream-type model that processes spectrogram images alongside a structured text prompt (sex, age, recording site) to output a JSON-formatted diagnosis. Results indicate that AST achieves approximately 97% accuracy with an F1-score around 97% and ROC AUC of 0.98 for asthma detection, significantly outperforming both the internal CNN baseline and typical external benchmarks. The VLM reaches 86-87% accuracy, performing comparably to the CNN baseline while demonstrating the capability to integrate clinical context into the inference process. These results confirm the effectiveness of self-attention for acoustic screening and highlight the potential of multimodal architectures for holistic diagnostic tools.

Pengfei Zhang, Tianxin Xie, Minghao Yang et al.

Deep learning-based respiratory auscultation is currently hindered by two fundamental challenges: (i) inherent information loss, as converting signals into spectrograms discards transient acoustic events and clinical context; (ii) limited data availability, exacerbated by severe class imbalance. To bridge these gaps, we present Resp-Agent, an autonomous multimodal system orchestrated by a novel Active Adversarial Curriculum Agent (Thinker-A$^2$CA). Unlike static pipelines, Thinker-A$^2$CA serves as a central controller that actively identifies diagnostic weaknesses and schedules targeted synthesis in a closed loop. To address the representation gap, we introduce a modality-weaving Diagnoser that weaves clinical text with audio tokens via strategic global attention and sparse audio anchors, capturing both long-range clinical context and millisecond-level transients. To address the data gap, we design a flow matching Generator that adapts a text-only Large Language Model (LLM) via modality injection, decoupling pathological content from acoustic style to synthesize hard-to-diagnose samples. As a foundation for this work, we introduce Resp-229k, a benchmark corpus of 229k recordings paired with LLM-distilled clinical narratives. Extensive experiments demonstrate that Resp-Agent consistently outperforms prior approaches across diverse evaluation settings, improving diagnostic robustness under data scarcity and long-tailed class imbalance. Our code and data are available at https://github.com/zpforlove/Resp-Agent.

Ola Alhalabi, Khaled Abouhazima, Fatima Al Maadid et al.

Conclusions: FMF should be considered for children with CD who exhibit pulmonary symptoms that do not respond to CD treatment.

Carly E. Byrd, Jennifer E. Schramm, Jun Yang et al.

ABSTRACT Cellular communication network 2 (CCN2) is a secreted matricellular protein associated with pulmonary arterial hypertension (PAH) but has not been studied relative to PAH severity, outcomes, or right ventricle (RV) structure and function in a large human cohort and preclinical animal model. This study assessed the associations between CCN2 and PAH severity, survival, hemodynamic measurements, and cardiovascular dysfunction. Serum CCN2 levels were compared in 2548 adults with PAH and 216 controls. CCN2 levels in PAH patients were compared to functional and hemodynamic measurements, and survival outcomes. RV‐pulmonary artery coupling and RV morphology were also assessed in a small subset of patients via pressure–volume loops and cardiac magnetic resonance imaging. In a preclinical PAH model, plasma CCN2 levels were compared between ventricles with PAH progression. CCN2 mRNA levels in both ventricles in the preclinical model were measured to compare with morphologic histologic variables. CCN2 serum levels were significantly higher in PAH compared to controls (p < 0.0001). Higher CCN2 levels were associated with reduced RV contractility (p = 0.003). Higher CCN2 levels were associated with worse 6MWD (p = 0.035), and higher risk of mortality or transplant (p = 0.025). In the preclinical model, prepulmonary CCN2 plasma levels increased with the progression of disease. CCN2 mRNA levels in the RV were associated with decreased RV capillary density (p = 0.015) and increased RV fibrosis (p = 0.045). Though more investigation is needed, it appears that CCN2 plays a role in the development of PAH and potentially in RV maladaptation in PAH.

Xuejun Sun, Yiran Song, Xiaochen Zhou et al.

Respiratory viral infections pose a global health burden, yet the cellular immune responses driving protection or pathology remain unclear. Natural infection cohorts often lack pre-exposure baseline data and structured temporal sampling. In contrast, inoculation and vaccination trials generate insightful longitudinal transcriptomic data. However, the scattering of these datasets across platforms, along with inconsistent metadata and preprocessing procedure, hinders AI-driven discovery. To address these challenges, we developed the Human Respiratory Viral Immunization LongitudinAl Gene Expression (HR-VILAGE-3K3M) repository: an AI-ready, rigorously curated dataset that integrates 14,136 RNA-seq profiles from 3,178 subjects across 66 studies encompassing over 2.56 million cells. Spanning vaccination, inoculation, and mixed exposures, the dataset includes microarray, bulk RNA-seq, and single-cell RNA-seq from whole blood, PBMCs, and nasal swabs, sourced from GEO, ImmPort, and ArrayExpress. We harmonized subject-level metadata, standardized outcome measures, applied unified preprocessing pipelines with rigorous quality control, and aligned all data to official gene symbols. To demonstrate the utility of HR-VILAGE-3K3M, we performed predictive modeling of vaccine responders and evaluated batch-effect correction methods. Beyond these initial demonstrations, it supports diverse systems immunology applications and benchmarking of feature selection and transfer learning algorithms. Its scale and heterogeneity also make it ideal for pretraining foundation models of the human immune response and for advancing multimodal learning frameworks. As the largest longitudinal transcriptomic resource for human respiratory viral immunization, it provides an accessible platform for reproducible AI-driven research, accelerating systems immunology and vaccine development against emerging viral threats.

Xiaolei Xu, Chaoyue Niu, Guy J. Brown et al.

Obstructive sleep apnoea (OSA) is a prevalent condition with significant health consequences, yet many patients remain undiagnosed due to the complexity and cost of over-night polysomnography. Acoustic-based screening provides a scalable alternative, yet performance is limited by environmental noise and the lack of physiological context. Respiratory effort is a key signal used in clinical scoring of OSA events, but current approaches require additional contact sensors that reduce scalability and patient comfort. This paper presents the first study to estimate respiratory effort directly from nocturnal audio, enabling physiological context to be recovered from sound alone. We propose a latent-space fusion framework that integrates the estimated effort embeddings with acoustic features for OSA detection. Using a dataset of 157 nights from 103 participants recorded in home environments, our respiratory effort estimator achieves a concordance correlation coefficient of 0.48, capturing meaningful respiratory dynamics. Fusing effort and audio improves sensitivity and AUC over audio-only baselines, especially at low apnoea-hypopnoea index thresholds. The proposed approach requires only smartphone audio at test time, which enables sensor-free, scalable, and longitudinal OSA monitoring.

Seung Gyu Jeong, Sung Woo Nam, Seong Kwan Jung et al.

Respiratory auscultation is crucial for early detection of pediatric pneumonia, a condition that can quickly worsen without timely intervention. In areas with limited physician access, effective auscultation is challenging. We present a smartphone-based system that leverages built-in microphones and advanced deep learning algorithms to detect abnormal respiratory sounds indicative of pneumonia risk. Our end-to-end deep learning framework employs domain generalization to integrate a large electronic stethoscope dataset with a smaller smartphone-derived dataset, enabling robust feature learning for accurate respiratory assessments without expensive equipment. The accompanying mobile application guides caregivers in collecting high-quality lung sound samples and provides immediate feedback on potential pneumonia risks. User studies show strong classification performance and high acceptance, demonstrating the system's ability to facilitate proactive interventions and reduce preventable childhood pneumonia deaths. By seamlessly integrating into ubiquitous smartphones, this approach offers a promising avenue for more equitable and comprehensive remote pediatric care.

Prescott C. Alexander, Thomas J. Harris, Joy Kitson et al.

The recent history of respiratory pathogen epidemics, including those caused by influenza and SARS-CoV-2, has highlighted the urgent need for advanced modeling approaches that can accurately capture heterogeneous disease dynamics and outcomes at the national scale, thereby enhancing the effectiveness of resource allocation and decision-making. In this paper, we describe Epicast 2.0, an agent-based model that utilizes a highly detailed, synthetic population and high-performance computing techniques to simulate respiratory pathogen transmission across the entire United States. This model replicates the contact patterns of over 320 million agents as they engage in daily activities at school, work, and within their communities. Epicast 2.0 supports vaccination and an array of non-pharmaceutical interventions that can be promoted or relaxed via highly granular, user specified policies. We illustrate the model's capabilities using a wide range of outbreak scenarios, highlighting the model's varied dynamics as well as its extensive support for policy exploration. This model provides a robust platform for conducting what if scenario analysis and providing insights into potential strategies for mitigating the impacts of infectious diseases.

Mira Moukheiber, Lama Moukheiber, Dana Moukheiber et al.

In critical care settings, where precise and timely interventions are crucial for health outcomes, evaluating disparities in patient outcomes is essential. Current approaches often fail to fully capture the impact of respiratory support interventions on individuals affected by social determinants of health. While attributes such as gender, race, and age are commonly assessed and provide valuable insights, they offer only a partial view of the complexities faced by diverse populations. In this study, we focus on two clinically motivated tasks: prolonged mechanical ventilation and successful weaning. Additionally, we conduct fairness audits on the models' predictions across demographic groups and social determinants of health to better understand health inequities in respiratory interventions within the intensive care unit. Furthermore, we release a temporal benchmark dataset, verified by clinical experts, to facilitate benchmarking of clinical respiratory intervention tasks.

Zhengtu Li, Beini Xu, Jie Liu

Background: Acute fibrinous and organizing pneumonia (AFOP) is a rare form of pneumonia, is characterized by the deposition of fibrin in alveoli, the formation of fibrin spheres, and deposition of fibrin in alveolar junctions and bronchioles adjacent to or adjacent to the alveoli, forming institutional loose connective tissue.The clinical characteristics of AFOP lack specificity. We report a special case of AFOP that may be associated with Candida, so as to improve our understanding and diagnosis of AFOP. Result: In this patient who was early misdiagnosed with community-acquired pneumonia (CAP), the empirical anti-infective treatment was ineffective, and various infectious and non-infectious factors were excluded. Flexible bronchoscopy was subsequently performed, and metagenomics Next Generation Sequencing (mNGS) of Bronchoalveolar lavage fluid (BALF) showed Candida albicans, and further ultrasound interventional percutaneous and lung puncture biopsy was performed to diagnose AFOP according to pathology, while mNGS of lung pathological tissue also suggested Candid. The patient recovered well on corticosteroids. Conclusion: The clinical manifestation, laboratory examination and imaging examination of AFOP has no specificity, lung biopsy and pathological examination should be carried out to make a clear diagnosis by comprehensively considering the clinical manifestations, auxiliary examination, pathology and other aspects of the patients. After definite diagnosis, it is still necessary to rule out various diseases and environmental exposure and further classify them as idiopathic or secondary, so as to choose monotherapy or combination therapy.

Mariana Isadora Ribeiro Vieira, Mônica Versiani Nunes Pinheiro de Queiroz, Maria Borges Rabelo de Santana et al.

ABSTRACT Objective: To determine whether polymorphisms of the IL10 and IL17 genes are associated with severe asthma control and bronchodilator reversibility in children and adolescents with severe asthma. Methods: This was a cross-sectional study, nested within a prospective cohort study of patients with severe asthma. Two outcomes were evaluated: asthma control and bronchodilator reversibility. We extracted DNA from peripheral blood and genotyped three single nucleotide polymorphisms: rs3819024 and rs2275913 in the IL17A gene; and rs3024498 in the IL10 gene. For the association analyses, we performed logistic regression in three genetic models (allelic, additive, and dominant). Results: The rs3024498 C allele in the IL10 gene was associated with failure to achieve asthma control despite regular treatment (p = 0.02). However, the G allele of the IL17A rs3819024 polymorphism was associated with failure to respond to stimulation with a b2 agonist. The rs2275913 polymorphism of the IL17A gene showed no relationship with asthma control or bronchodilator reversibility. Conclusions: In pediatric patients with severe asthma, the IL10 polymorphism appears to be associated with failure to achieve clinical control, whereas the IL17A polymorphism appears to be associated with a worse bronchodilator response. Knowledge of the involvement of these polymorphisms opens future directions for pharmacogenetic studies and for the implementation of individualized therapeutic management of severe asthma in pediatric patients.

Jose Mª Díaz, Maria del Mar García, Macarena Segura et al.

Mani Kant Kumar, Bipin kumar, Vikas kumar et al.

Introduction Status of child health in a country is reflected in various morbidity and mortality indicators and their changes over a period of time. India is home to 19% of the world’s children and like any other country, the morbidity profile is not static in India and keeps on changing with overall development in socioeconomic and environmental status as well as child health care awareness/facilities in the community. So, the proper documentation of the same is also of great importance for proper health care planning. Aim and Objective This study aimed to determine the patterns of morbidity, mortality in pediatric patients (1 month to 15 years) in a tertiary care centre, Jamuhar in South West Bihar. Methodology This was a retrospective study conducted in a tertiary care hospital, Jamuhar of South West Bihar. Medical records of 2019 children admitted in the department of Pediatrics between 1st May 2019 to 30th April 2020 were reviewed. The data on morbidity patterns in children due to different diseases, causes of death in different age groups, age and gender distribution of pediatric age group mortality, mean time interval between admission and death of children were collected. Result In our study, we enrolled 2019 patients, those who were admitted in the study period. Most common 39.6 % (800 patients) morbidity was acute respiratory infection. Among respiratory illnesses, acute bronchiolitis was the most common respiratory morbidity 601 (75.12%). Second most common morbidity was associated with Gastrointestinal system illness 386 (19.12 %) patients, out of which acute diarrheal diseases accounted for 347(89.89 %). Third most common morbidity was Central nervous system illness 347(17.18%). In our study, the mortality rate of hospitalized pediatric patients was 2.67%, which is comparable to any other hospital of developing countries. In this study we found most common causes of mortality were sepsis and septic shock 48% followed by acute respiratory infection 29.62%. Conclusion In this study we concluded that 3 most common causes of morbidities among 1 month to 15 years age group patients were acute respiratory infection, acute diarrheal illness and acute encephalitis syndrome. Three most common cause of death were sepsis and septic shock, acute bronchiolitis and acute encephalitic syndrome.

June-Woo Kim, Miika Toikkanen, Sangmin Bae et al.

Recent advancements in AI have democratized its deployment as a healthcare assistant. While pretrained models from large-scale visual and audio datasets have demonstrably generalized to this task, surprisingly, no studies have explored pretrained speech models, which, as human-originated sounds, intuitively would share closer resemblance to lung sounds. This paper explores the efficacy of pretrained speech models for respiratory sound classification. We find that there is a characterization gap between speech and lung sound samples, and to bridge this gap, data augmentation is essential. However, the most widely used augmentation technique for audio and speech, SpecAugment, requires 2-dimensional spectrogram format and cannot be applied to models pretrained on speech waveforms. To address this, we propose RepAugment, an input-agnostic representation-level augmentation technique that outperforms SpecAugment, but is also suitable for respiratory sound classification with waveform pretrained models. Experimental results show that our approach outperforms the SpecAugment, demonstrating a substantial improvement in the accuracy of minority disease classes, reaching up to 7.14%.

June-Woo Kim, Miika Toikkanen, Yera Choi et al.

Respiratory sound classification (RSC) is challenging due to varied acoustic signatures, primarily influenced by patient demographics and recording environments. To address this issue, we introduce a text-audio multimodal model that utilizes metadata of respiratory sounds, which provides useful complementary information for RSC. Specifically, we fine-tune a pretrained text-audio multimodal model using free-text descriptions derived from the sound samples' metadata which includes the gender and age of patients, type of recording devices, and recording location on the patient's body. Our method achieves state-of-the-art performance on the ICBHI dataset, surpassing the previous best result by a notable margin of 1.17%. This result validates the effectiveness of leveraging metadata and respiratory sound samples in enhancing RSC performance. Additionally, we investigate the model performance in the case where metadata is partially unavailable, which may occur in real-world clinical setting.

Shahran Rahman Alve, Muhammad Zawad Mahmud, Samiha Islam et al.

Artificial intelligence and deep learning are increasingly applied in the clinical domain, particularly for early and accurate disease detection using medical imaging and sound. Due to limited trained personnel, there is a growing demand for automated tools to support clinicians in managing rising patient loads. Respiratory diseases such as cancer and diabetes remain major global health concerns requiring timely diagnosis and intervention. Auscultation of lung sounds, combined with chest X-rays, is an established diagnostic method for respiratory illness. This study presents a Deep Convolutional Neural Network (CNN)-based approach for the analysis of respiratory sound data to detect Chronic Obstructive Pulmonary Disease (COPD). Acoustic features extracted with the Librosa library, including Mel-Frequency Cepstral Coefficients (MFCCs), Mel-Spectrogram, Chroma, Chroma (Constant Q), and Chroma CENS, were used in training. The system also classifies disease severity as mild, moderate, or severe. Evaluation on the ICBHI database achieved 96% accuracy using 10-fold cross-validation and 90% accuracy without cross-validation. The proposed network outperforms existing methods, demonstrating potential as a practical tool for clinical deployment.

ZHAO Yue, FAN Junyan, SHEN Jiaying et al.

ObjectiveTo determine the influence of COVID-19 prevention and control on the epidemic characteristics and dynamics of notifiable infectious diseases in the first quarters， Zhejiang Province， and to explore more effective countermeasures against infectious diseases.MethodsDescriptive epidemiology was conducted to determine the change in notifiable infectious diseases during the prevention and control of COVID-19 in Zhejiang Province by retrieving the data of notifiable infectious diseases from 2017 to 2022 in the Chinese information system for disease control and prevention. Cumulative reported new cases of notifiable infectious diseases in the first quarters of 2017‒2019 were compared with that of 2020‒2022.ResultsA total of 546 753 cases of notifiable infectious diseases were newly reported in the first quarters of 2017‒2019， with an average incidence of 321.92/105. In contrast， a total of 509 908 cases of notifiable infectious diseases were newly reported in the first quarters of 2020‒2022， during which the COVID-19 epidemic occurred， with an average incidence of 270.39/105. The incidence in 2020‒2022 significantly declined by 51.53/105， compared with that in 2017‒2019 （χ²=8 072.06， P<0.001）. In the first quarters of 2020‒2022， the average incidence of zoonotic diseases and vector-borne diseases decreased by more than 50%. In addition， the incidence of respiratory， enteric， blood-borne， and sexually transmitted diseases declined to certain degree.ConclusionThe decline in the newly reported cases of non-COVID-19 notifiable infectious diseases in the first quarters of 2020‒2022 indicates that the countermeasures against COVID-19 epidemic， such as multi-disease co-prevention， multi-sectoral collaboration， societal mobilization and personal hygiene and protection， may also decrease the incidence of multiple infectious diseases. It suggests the countermeasures are effective， which would provide evidence for routine prevention and control of infectious diseases in future.

D K Arvind, S Maiya

According to the Lancet report on the global burden of disease published in October 2020, air pollution is among the five highest risk factors for global health, reducing life expectancy on average by 20 months. This paper describes a data-driven method for establishing causal relationships within and between two multivariate time series data streams derived from wearable sensors: personal exposure to airborne particulate matter of aerodynamic sizes less than 2.5um (PM2.5) gathered from the Airspeck monitor worn on the person and continuous respiratory rate (breaths per minute) measured by the Respeck monitor worn as a plaster on the chest. Results are presented for a cohort of 113 asthmatic adolescents using the PCMCI+ algorithm to learn the short-term causal relationships between lags of \pm exposure and respiratory rate. We consider causal effects up to a maximum delay of 8 hours, using data at both a 1 minute and 15 minute resolution in different experiments. For the first time a personalised exposure-response relationship between PM2.5 exposure and respiratory rate has been demonstrated to exist for short-term effects in asthmatic adolescents during their everyday lives. Our results lead to recommendations for work on specific open problems in causal discovery, to increase the feasibility of this approach for similar epidemiology studies in the future.

Mi Zhou, Jie Ouyang, Guoqing Zhang et al.

Abstract Background Tripartite motif (TRIM) family genes get involved in the pathogenesis and development of various biological processes; however, the prognostic value of TRIM genes for idiopathic pulmonary fibrosis (IPF) needs to be explored. Methods We acquired gene expression based on bronchoalveolar lavage (BAL) cells and clinical data of three independent IPF cohorts in the GSE70866 dataset from the Gene expression omnibus (GEO) database. Differentially expressed TRIM genes (DETGs) between IPF patients and healthy donors were identified and used to establish a risk signature by univariate and multivariate Cox regression analysis in the training cohort. The risk signature was further validated in other IPF cohorts, and compared with previously published signatures. Moreover, we performed functional enrichment analysis to explore the potential mechanisms. Eventually, the quantitative real time PCR was conducted to validate the expressions of the key genes in BAL from 12 IPF patients and 12 non-IPF controls from our institution. Results We identified 4 DETGs including TRIM7, MEFV, TRIM45 and TRIM47 significantly associated with overall survival (OS) of IPF patients (P < 0.05). A multiple stepwise Cox regression analysis was performed to construct a 4-TRIM-gene prognostic signature. We categorized IPF patients into one low-risk group and the other high-risk group as per the average risk value of the TRIM prognostic signature in the training and validation cohorts. The IPF individuals in the low-risk group demonstrated an obvious OS advantage compared with the high-risk one (P < 0.01). The time-dependent receiver operating characteristic approach facilitated the verification of the predictive value of the TRIM prognostic signature in the training and validation cohorts, compared with other published signatures. A further investigation of immune cells and IPF survival displayed that higher proportion of resting memory CD4+ T cells and resting mast cells harbored OS advantage over lower proportion, however lower proportion of neutrophils, activated dendritic cells and activated NK cells indicated worse prognosis. Conclusion The TRIM family genes are significant for the prognosis of IPF and our signature could serve as a robust model to predict OS.

Soo Jin Na, Ryoung-Eun Ko, Jimyoung Nam et al.

Background: Patients who need prolonged mechanical ventilation (MV) have high resource utilization and relatively poor outcomes. The pathophysiologic mechanisms leading to weaning failure in this group may be complex and multifactorial. The aim of this study was to investigate the factors associated with prolonged weaning based on the Weaning Outcome according to a New Definition (WIND) classification. Methods: This is a prospective observational study with consecutive adult patients receiving MV for at least two calendar days in medical intensive care units from 1 November 2017 to 30 September 2020. Eligible patients were divided in a non-prolonged weaning group, including short and difficult weaning, and in a prolonged weaning group according to the WIND classification. The risk factors at the time of first separation attempt associated with prolonged weaning were analyzed using a multivariable logistic regression model. Results: Of the total 915 eligible patients, 172 (18.8%) patients were classified as prolonged weaning. A higher proportion of the prolonged weaning group had previous histories of endotracheal intubation, chronic lung disease, and hematologic malignancies. When compared with the non-prolonged weaning group, the median duration of MV before the first spontaneous breathing trial (SBT) was longer and the proportion of tracheostomized patients was higher in prolonged weaning group. In addition, the prolonged weaning group used higher peak inspiratory pressures and yielded lower PaO 2 /FiO 2 ratios at the day of the first SBT compared with the non-prolonged weaning group. In multivariate analyses, the duration of MV before first SBT (adjusted odds ratio [OR] = 1.14, 95% confidence interval [CI] = 1.06–1.22, p  < 0.001), tracheostomy state (adjusted OR = 1.95, 95% CI = 1.04–3.63, p  = 0.036), PaO 2 /FiO 2 ratio (adjusted OR = 1.00, 95% CI = 0.99–1.00, p  = 0.023), and need for renal replacement therapy (adjusted OR = 2.68, 95% CI = 1.16–6.19, p  = 0.021) were independently associated with prolonged weaning. After the exclusion of patients who underwent tracheostomy before the SBTs, similar results were obtained. Conclusion: Longer duration of MV before the first SBT, tracheostomy status, poor oxygenation, and need for renal replacement therapy at the time of first SBT can predict prolonged weaning. Trial registration: ClinicalTrials.gov Identifier NCT05134467.