Search Results (72)

A critical factor contributing to the burden of childhood asthma is the lack of effective self-management in homecare settings. Artificial intelligence (AI) and lung sound monitoring could help address this gap. Yet, existing AI-driven auscultation tools focus on wheeze detection and often rely on subjective human labels. To improve the early detection of asthma worsening in children in homecare setting, we trained and evaluated a Deep Learning model based on spirometry-labelled lung sounds recordings to detect asthma exacerbation. A single-center prospective observational study was conducted between November 2020 and September 2022 at a tertiary pediatric pulmonology department. Electronic stethoscopes were used to record lung sounds before and after bronchodilator administration in outpatients. In the same session, children also underwent spirometry, which served as the reference standard for labelling the lung sound data. Model performance was assessed on an internal validation set using receiver operating characteristic (ROC) curves. A total of 16.8 h of lung sound recordings from 151 asthmatic pediatric outpatients were collected. The model showed promising discrimination performance, achieving an AUROC of 0.763 in the training set, but performance in the validation set was limited (AUROC = 0.398). This negative result demonstrates that acoustic features alone may not provide sufficient diagnostic information for the early detection of asthma attacks, especially in mostly asymptomatic outpatients typical of homecare settings. It also underlines the challenges introduced by differences in how digital stethoscopes process sounds and highlights the need to define the severity threshold at which acoustic monitoring becomes informative, and clinically relevant for home management. Full article

Background/Objectives: Correct inhalation technique (IT) is crucial in the management of airway obstructive diseases. However, inhaler misuse among patients is frequent. The aim of the study was to assess IT and analyze factors influencing inhalation errors in adults with asthma and COPD. Methods: This single-center case–control study involved 180 adults with asthma or COPD. IT was evaluated using a checklist of common errors, a four-grade dedicated scale, and peak inspiratory flow. Patients with correct and incorrect IT were compared across multiple factors, including demographics, disease duration and severity, motivation for treatment, spirometry results, cognitive function, visual or hearing disorders and prior training in inhaler use. Results: A total of 115 patients with asthma and 65 patients with COPD were analyzed. Among them, only 59 patients (32.8%) were treated with 1 inhaler. Sixty-eight patients (37.8%) used all their inhalers properly. Correct IT was observed more frequently among DPI compared to MDI users (p < 0.001). Only 76 patients (42.2%) reported previous training in IT. No differences were found between correct and incorrect inhaler users (MDI or DPI) regarding age, gender, education, treatment motivation, visual or hearing impairments or cognitive disorders. Among MDI users, those with correct IT more often read the drug leaflet (p = 0.015). Among DPI users, proper technique was associated with better self-assessment (p = 0.046) and a higher rate of prior inhalation training (p = 0.001). Conclusions: Most adults with asthma or COPD do not use their inhalers properly, particularly patients using MDI. Insufficient education in the field of proper IT is still a burning issue. Full article

Introduction: Asthma is a chronic airway inflammatory disease characterized by variable airflow limitation and intermittent symptoms. In well-controlled asthma, auscultation and spirometry often appear normal, making diagnosis challenging. Moreover, bronchial provocation tests carry a risk of inducing acute bronchoconstriction. This study aimed to develop a non-invasive, objective, and reproducible diagnostic method using machine learning-based lung sound analysis for the early detection of asthma, even during stable periods. Methods: We designed a machine learning algorithm to classify controlled asthma patients and healthy individuals using respiratory sounds recorded with a digital stethoscope. We enrolled 120 participants (60 asthmatic, 60 healthy). Controlled asthma was defined according to Global Initiative for Asthma (GINA) criteria and was supported by normal spirometry, no pathological auscultation findings, and no exacerbations in the past three months. A total of 3600 respiratory sound segments (each 3 s long) were obtained by dividing 90 s recordings from 120 participants (60 asthmatic, 60 healthy) into non-overlapping clips. The samples were analyzed using Mel-Frequency Cepstral Coefficients (MFCCs) and Tunable Q-Factor Wavelet Transform (TQWT). Significant features selected with ReliefF were used to train Quadratic Support Vector Machine (SVM) and Narrow Neural Network (NNN) models. Results: In 120 participants, pulmonary function test (PFT) results in the asthma group showed lower FEV1 (86.9 ± 5.7%) and FEV1/FVC ratios (86.1 ± 8.8%) compared to controls, but remained within normal ranges. Quadratic SVM achieved 99.86% accuracy, correctly classifying 99.44% of controls and 99.89% of asthma cases. Narrow Neural Network achieved 99.63% accuracy. Sensitivity, specificity, and F1-scores exceeded 99%. Conclusion: This machine learning-based algorithm provides accurate asthma diagnosis, even in patients with normal spirometry and clinical findings, offering a non-invasive and efficient diagnostic tool. Full article

This study analyzed the relationship between pesticide exposure with respiratory symptoms and lung function among small-scale farm workers in rural communities of Sucre, Bolivia. A cross-sectional study was conducted including 277 farmers and 214 non-farmers ≥ 16 years. Pesticide exposure and respiratory symptoms were assessed by questionnaire, and lung function was assessed by spirometry. Logistic regression models were used to estimate odds ratios and 95% confidence intervals for associations between pesticide exposure and respiratory symptoms, while multiple linear regression was employed to estimate associations with lung function. The adjusted regression models indicated a positive association between pesticide exposure and chronic cough or phlegm (aOR 1.22; 95% CI 1.0 to 1.5), chest tightness (1.14; 1.0 to 1.3), and nasal allergies (1.21; 1.0 to 1.4). Also, pesticide exposure showed a slight positive association with FVC (β = 0.04; 95% CI = 0.01 to 0.07). Agricultural work (vs. non-agricultural work) showed a dual effect; on the one hand, it showed a negative association with lung function (FEV1/FVC (%): −1.57; 95% CI = −3.25 to −0.11); on the other hand, it seemed to be a protective factor for nasal allergies (aOR 0.31; 95% CI 0.1–0.8). Our study suggests an association between pesticide exposure and respiratory symptoms and farm work with lung function parameters. The results underscore the need to enhance programs that regulate and train farmers on the use of pesticides, thereby reducing health effects on workers and agricultural and neighboring communities. Full article

Background: Living donor liver transplantation (LDLT) poses significant physiological challenges, especially during early postoperative recovery. While the long-term benefits of structured rehabilitation are well documented, data on short-term effects—particularly during the critical early inpatient phase—remain limited. This study aimed to evaluate the short-term impact of a structured exercise program on cardiopulmonary function, respiratory muscle strength, physical performance, oxidative stress markers, and quality of life in LDLT recipients. Methods: Four LDLT recipients (2 males, 2 females; mean age 48.00 ± 18.35 years) underwent a 4-week inpatient rehabilitation protocol. Weeks 1–2 involved conventional care, while weeks 3–4 included structured exercise consisting of early mobilization and inspiratory muscle training. Outcome measures included cardiopulmonary exercise testing (CPET), spirometry, maximal inspiratory and expiratory pressures (PImax, PEmax), 6 min walk distance (6MWD), lower limb muscle strength, Chronic Liver Disease Questionnaire (CLDQ), and serum oxidative stress markers (total antioxidant capacity [TAC] and malondialdehyde [MDA]). Results: All patients demonstrated postoperative declines in VO₂ peak, PImax, PEmax, and TAC. Structured exercise yielded clinically meaningful improvements in respiratory muscle strength, notably in female and younger participants. Two younger patients showed increased 6MWD; however, no patient regained preoperative VO₂ peak. TAC levels decreased following the intervention, and MDA levels remained stable in most cases. Conclusions: A two-week structured exercise program during early postoperative recovery may provide partial benefits in respiratory muscle strength and physical performance but is insufficient to restore full cardiopulmonary function in LDLT recipients. Longer rehabilitation periods may be necessary to achieve preoperative recovery levels. Full article

Limited data exist on the underlying physiological phenomena of aerobic training; the impulse oscillometry method, allowing the assessment of small airways and lung periphery in addition to standard lung function testing, might be a useful addition to rehabilitation programs. Background/Objectives: This study aimed to determine the immediate effect of a structured low-intensity aerobic training program on small airway function in healthy volunteers to explore potential implications for long-term COPD care. Methods: Thirty-six healthy volunteers were recruited between May 2024 and January 2025; each participant underwent a lung function testing session, followed by low/moderate-intensity aerobic exercise, and, after 15 min, by a second impulse oscillometry assessment. Results: There was a statistically significant reduction in airway resistance following the physical exertion for the whole group (mean difference 0.03 kPa/L/s, 95%CI 0–0.6 kPa/L/s); significantly lower values were recorded for the reactance component X5 (0.02 kPa/L/s, 95%CI 0–0.4 kPa/L/s) for the normal weight subgoup (n = 24). These results, corroborated with literature data, suggest optimization of the distribution of the airflow and possibly alteration of the elastic properties of the thoracic structures following even low-intensity effort. Conclusions: Low-intensity upper body strength and aerobic training seem to have an immediate respiratory beneficial effect on healthy volunteers manifested as a reduction in airway resistance. The underlying mechanism might be related to improved contractility of respiratory muscles, but changes in lung parenchyma elasticity may also be involved, possibly reflecting modifications of ventilation heterogeneity. Impulse oscillometry may be superior to spirometry in monitoring the effects of aerobic training, considering the additional data it provides, and could be used to optimize and personalize rehabilitation protocols. Full article

Background: It is thought that swimming might elicit remarkable chronic lung function improvements that were not observed in land-based sports. However, there is no consensus on whether this is mainly attributable to genetic predisposition or specific training. This study aimed to characterize athletes’ lung function according to their swimming experience. Methods: The sample consisted of 45 male athletes, including 15 swimmers, 15 triathletes, and 15 runners. Spirometry tests were conducted under four conditions: seated on land, prone on land, seated while immersed in water, and prone while immersed in water. The tests were performed on the pool deck and pool, with the order of conditions randomized for each participant. Conclusions: The results of this study do not support the idea that there is a window of opportunity for greater lung function adaptations during childhood due to swim training. The accumulated years of swim training are the reason for the increased measurements of FVC and FEV₁ of swimmers. The immersed seated condition measures differences in lung function more accurately relative to swim training experience. Swim training appears to primarily enhance FVC in healthy athletes, while in allergic and asthmatic athletes, it mainly promotes improvements in FEV₁/FVC and FEF_25–75%. Full article

Background/Objectives: Chronic obstructive pulmonary disease (COPD) remains a condition with high morbidity, mortality, and misdiagnosis. The gold standard pulmonary function testing with spirometry has limited availability. This study seeks to test a novel diagnostic test based on auscultatory mapping of pulmonary dynamics. This NIH-funded study aimed to develop a COPD detection technology, using mobile phone auscultation, for situations in which spirometry is not available. Methods: This prospective study collected mobile phone auscultation data on patients presenting for spirometry and evaluation by a pulmonologist. All subjects had same-day or recent (less than 6 months) spirometry in one PFT laboratory. After informed consent, the subjects underwent respiratory auscultation using a selection of mobile phone brands. The auscultation methods included normal breathing observed at the left axillary site and egophony observed at the right supra clavicular fossa. The team created models from the recordings using Time Series Dynamics (TSD), proprietary software that uses computational nonlinear dynamics to characterize the respiratory biofluid dynamics implied by the acoustic data. Results: We enrolled a total of 108 patients (34.3% male), from 19 to 85 years of age (median 61 years). Among the patients, 64 (59.3%) subjects identified as White, 43 (39.8%) as Black, and 1 as Asian. Among the two cohorts with diverse comorbidities, 52 subjects had confirmed COPD and 56 did not. The cohorts differed significantly in age and body mass index, but not in race, number of comorbidities, or COPD assessment test scores. They had significant differences in forced expiratory volume in 1 s (FEV1), the FEV1/FVC (forced vital capacity) ratio, but not FVC. The recordings from the egophonic and axillary sites were initially modeled separately and then combined in a single composite model. The modeling produced excellent results with 90%+ AUC and sensitivity in both the test and train sets relative to the gold standard. Conclusions: Evidence suggests that a mobile phone auscultation device can accurately determine COPD diagnosis. In frontline applications where the availability of gold standard pulmonary function testing is limited, the device could improve the detection of COPD, a condition with significant over- and under-diagnosis. Future trials will investigate the ability of patients to self-record. Success would support remote COPD testing using transmitted telehealth recording data, bringing diagnosis to patients in underserved populations. Full article

Background: Chronic obstructive pulmonary disease (COPD) is projected to be the third-leading cause of death by 2030. Traditional spirometry for the monitoring of the forced expiratory volume in one second (FEV1) can provoke discomfort and anxiety. This study aimed to validate AI models using daily audio recordings as an alternative for FEV1 estimation in home settings. Methods: Twenty-three participants with moderate to severe COPD recorded daily audio readings of standardized texts and measured their FEV1 using spirometry over nine months. Participants also recorded biomarkers (heart rate, temperature, oxygen saturation) via tablet application. Various machine learning models were trained using acoustic features extracted from 2053 recordings, with K-nearest neighbor, random forest, XGBoost, and linear models evaluated using 10-fold cross-validation. Results: The K-nearest neighbors model achieved a root mean square error of 174 mL/s on the validation data. The limit of agreement (LoA) ranged from −333.21 to 347.26 mL/s. Despite an error range of −1252 to 1435 mL/s, most predictions fell within the LoA, indicating good performance in estimating the FEV1. Conclusions: The predictive model showed promising results, with a narrower LoA compared to traditional unsupervised spirometry methods. The AI models effectively used audio to predict the FEV1, suggesting a viable non-invasive approach for COPD monitoring that could enhance patient comfort and accessibility in home settings. Full article

Background and Objectives: Individuals with chronic obstructive pulmonary disease (COPD) often exhibit some degree of intolerance to physical exercise and several limitations in daily activities. Therefore, the objective of this study was to conduct a scoping review on the characteristics—frequency, intensity, time, and type (FITT)—and the effects of exercise programs on quality of life and functional capacity in individuals with COPD. Materials and Methods: The present review included 21 studies that were scoping-reviewed to describe their main findings and training characteristics. Results: The participants across studies ranged in age from ~39 to 76 years with mild to very severe COPD stages. The results showed that, among all studies, eleven used cardiorespiratory training (e.g., walking or cycling), five used strength training (e.g., exercises with elastic bands or traditional resistance training), and five implemented combined training (i.e., cardiorespiratory and strength exercises). Conclusions: Overall, all training protocols improved aerobic capacity (cardiorespiratory training), strength (resistance training), and both capacities together (combined training). In conclusion, this review provided complementary insights to existing exercise prescription guidelines, particularly concerning cardiorespiratory, strength, and combined training in individuals with COPD. However, the methodologies of the training protocols varied widely, and detailed descriptions of FITT components were often incomplete or lacking clarity, especially regarding the specific exercises used. Future research should include more comprehensive spirometry variables such as forced expiratory volume 1 or forced vital capacity, as these are critical for determining COPD stages. Thus, there is a clear need for more high-quality research with robust methodological design in the context of exercise interventions for individuals with COPD. Full article

Objectives: The aim of this study was to evaluate the effectiveness of respiratory muscle training in runners in relation to gender and trainers (PowerBreathe and Threshold). Methods: This study comprised 32 athletes training in middle-distance running at a high sports level. The subjects were divided into groups depending on the applied breathing training (IMT): group IMT on the PowerBreath, group IMT on the Threshold, and the control group labeled sham-IMT. The following tests were performed on each athlete: spirometry, maximal inspiratory pressure, expiratory pressure, and physical performance. Results: A significant increase in the levels of the parameters VO₂/kg, PEF, PI_max, and PE_max, as well as a decrease in lactic acid levels and an increase in lactate threshold in both sexes, were observed as a result of the training on the PowerBreathe device. There were no significant differences in the levels of the parameters VO₂/kg, PEF, PI_max, lactic acid, and lactate threshold in either sex after Threshold training. A significant increase in PE_max was found in the Threshold device training group. Conclusions: Most of the assessed parameters of physical fitness and lung ventilation function, along with the respiratory muscle strength of women and men running middle distances, increased significantly after the use of IMT on PowerBreathe, and these results were maintained in the third stud, in contrast to the use of IMT on Threshold, with which there was no significant improvement. Full article

Background/Objectives: The methacholine bronchial provocation test (MBPT) is a diagnostic test frequently used to evaluate airway hyper-reactivity. MBPT is essential for diagnosing asthma; however, it can be time-consuming and resource-intensive. This study aimed to develop an artificial intelligence (AI) model to predict the MBPT results using forced expiratory volume in one second (FEV₁) and bronchodilator test measurements from spirometry. Methods: a dataset of spirometry measurements, including Pre- and Post-bronchodilator FEV₁, was used to train and validate the model. Results: Among the evaluated models, the multilayer perceptron (MLP) achieved the highest area under the curve (AUC) of 0.701 (95% CI: 0.676–0.725), accuracy of 0.758, and an F1-score of 0.853. Logistic regression (LR) and a support vector machine (SVM) demonstrated comparable performance with AUC values of 0.688, while random forest (RF) and extreme gradient boost (XGBoost) achieved slightly lower AUC values of 0.669 and 0.672, respectively. Feature importance analysis of the MLP model identified key contributing features, including Pre-FEF_25–75 (%), Pre-FVC (L), Post FEV₁/FVC, Change-FEV₁ (L), and Change-FEF_25–75 (%), providing insight into the interpretability and clinical applicability of the model. Conclusions: These results highlight the potential of the model to utilize readily available spirometry data, particularly FEV₁ and bronchodilator responses, to accurately predict MBPT results. Our findings suggest that AI-based prediction can improve asthma diagnostic workflows by minimizing the reliance on MBPT and enabling faster and more accessible assessments. Full article

Background/Objectives: Both aging and chronic obstructive pulmonary disease (COPD) are strongly associated with changes in the metabolome; however, it is unknown whether there are common aging/COPD metabolomic signatures and if accelerated aging is associated with COPD. Methods: Plasma from 5704 subjects from the Genetic Epidemiology of COPD study (COPDGene) and 2449 subjects from Subpopulations and intermediate outcome measures in COPD study (SPIROMICS) were profiled using the Metabolon global metabolomics platform (1013 annotated metabolites). Post-bronchodilator spirometry measures of airflow obstruction (forced expiratory volume at one second (FEV₁)/forced vital capacity (FVC) < 0.7) were used to define COPD. Elastic net regression was trained on never and former smokers with normal spirometry and no emphysema to create a metabolomic age score which was validated in SPIROMICS subjects. Results: Our metabolic age score was strongly associated with chronic age in the validation cohort (correlation coefficient = 0.8). COPD subjects with accelerated aging (>7 years difference between metabolic and actual age) had more severe disease compared with those who had decelerated aging (<−7 years difference between metabolic and actual age). COPD and aging metabolites were shared more than expected (p < 0.001), with amino acid and glutathione metabolism among pathways overrepresented. Conclusions: These findings suggest a common mechanism between aging and COPD and that COPD is associated with accelerated metabolic aging. Full article

Background: Coronary artery bypass grafts (CABGs) and cardiac valve replacement surgeries (CVRSs) are common lifesaving cardiac surgeries. They are linked to an increased risk of postoperative pulmonary complications (PPCs). This review scopes the effects of inspiratory muscle training (IMT) on adult patients, considering mainly exercise capacity, lung function, and the occurrence of PPCs. Methods: This scoping review was built using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR). Four databases were searched in May 2024. Three reviewers independently screened the articles. The data were extracted and summarised in text and tables. Results: Five studies were included in the final analysis, where IMT was compared to sham or placebo IMT, and some studies added an exercise program to both groups. PeakVO₂, the six-minute walking test (6MWT), maximal inspiratory pressure (MIP), quality of life (QoL), PPCs, and spirometry outcomes showed significant improvements between the intervention group (IG) and control group (CG) and intragroup over time. Conclusions: IMT can be a non-conventional training method to prevent respiratory muscle weakness. It can be applied in pre- or post-surgical contexts, potentially affecting exercise capacity and quality of life in adult patients undergoing cardiac surgery. Full article

Background: Respiratory complications in patients with amyotrophic lateral sclerosis (ALS), due to the involvement of respiratory muscles, are the leading cause of death, and respiratory physiotherapy (RP) focuses on addressing these complications. Objectives: The objective was to evaluate the effectiveness of an RP intervention that combines the four specific techniques (inspiratory muscle training, lung volume recruitment, manually assisted coughing, and diaphragmatic breathing training) in patients with ALS. Methods: A quasi-experimental study was carried out, and a specific RP programme was implemented in 15 patients with ALS (12 sessions, 30 min/session, one session/week, duration of three months), based on directed ventilation techniques, lung volume recruitment, manually assisted coughing, and the use of incentive spirometry and a cough assist device, along with a daily home exercise programme. Respiratory functions were assessed (pre- and post-intervention, with follow-up at three months) using Forced Vital Capacity (FVC) and Peak Expiratory Cough Flow (PECF); functionality was assessed using the Revised ALS Functional Rating Scale (ALSFRS-R) and the Modified Barthel Index by Granger. Results: FVC experienced an increase after three months of the intervention initiation (p = 0.30), which was not sustained at the three-month follow-up after the intervention ended. All other variables remained practically constant after treatment, with their values decreasing at follow-up. Conclusion: A specific RP intervention could have beneficial effects on respiratory functions, potentially preventing pulmonary infections and hospitalisations in patients with ALS. It may improve FVC and help stabilize the patient's functional decline. Considering the progressive and degenerative nature of the disease, this finding could support the usefulness of these techniques in maintaining respiratory function. Full article