Chronic Obstructive Pulmonary Disease Research Articles

Spontaneous breathing trials should be adapted for each patient according to the critical illness. A new individualised approach: the GLOBAL WEAN study.

Spontaneous breathing trials (SBT) evaluate the patient's capacity to maintain inspiratory effort after extubation. SBT practices are heterogeneous and not individualised. The objective of this study was to assess which SBT best reproduces inspiratory effort after extubation in five critical illnesses. In this multicentre randomized cross-over study, adult intensive care unit patients under invasive mechanical ventilation for at least 24-h and ready for extubation, underwent three 15-min SBTs in random order: pressure support ventilation level of 7-cmH2O with positive end-expiratory pressure (PEEP) level of 0-cmH2O (PSV7PEEP0), PSV 0-cmH2O with PEEP 0-cmH2O (PSV0PEEP0) and T-piece trial. Primary outcome was the variation of pressure-time-product per minute (PTPmin) between each SBT and 20-min after extubation. Five categories of critical illnesses were selected: abdominal surgery, brain injury, chest trauma, chronic obstructive pulmonary disease (COPD) and miscellaneous. Five hundred measures of effort from 100 patients were analysed. PTPmin (cmH2O s/min, median and interquartile range, IQR) was 256 (208-321) after extubation, 192 (127-281) at the end of PSV7PEEP0 (p < 0.001 in comparison to after extubation), 291 (235-347) at the end of PSV0PEEP0 and 262 (198-338) at the end of T-piece (both no different from after extubation). One method of SBT in patients with brain injury (PSV0PEEP0), two in abdominal surgery (PSV0PEEP0 and T-piece) and miscellaneous patients (PSV7PEEP0 and T-piece) and all three methods in chest trauma and COPD exacerbation patients replicated reasonably accurately the postextubation effort to breathe. Unassisted SBTs, namely PSV0PEEP0 and T-piece trial, are the most appropriate to replicate the postextubation effort to breathe.

Future Considerations and Areas for Innovation for Pulmonary Rehabilitation in Chronic Obstructive Lung Disease Patients.

Pulmonary rehabilitation is an effective therapy that improves day-to-day symptoms and quality of life in patients with chronic obstructive pulmonary disease. In this review, we look at the role of virtual programs, implementation of artificial intelligence, emerging areas of improvement within the educational components of programs, and the benefit of advanced practice providers in directorship roles.

Defining Postinduction Hemodynamic Instability With an Automated Classification Model.

Postinduction hypotension (PIH) may be associated with increased morbidity and mortality. In earlier studies, the definition of PIH is solely based on different absolute or relative thresholds. However, the time-course (eg, how fast blood pressure drops during induction) is rarely incorporated, whereas it might represent the hemodynamic instability of a patient. We propose a comprehensive model to distinguish hemodynamically unstable from stable patients by combining blood pressure thresholds with the magnitude and speed of decline. This prospective study included 375 adult elective noncardiac surgery patients. Noninvasive blood pressure was continuously measured between 5 minutes before up to 15 minutes after the first induction agent had been administered. An expert panel rated whether the patient experienced clinically relevant hemodynamic instability or not. Interrater correlation coefficient and intraclass correlation were computed to check for consistency between experts. Next, an automated classification model for clinically relevant hemodynamic instability was developed using mean, maximum, minimum systolic, mean, diastolic arterial blood pressure (SAP, MAP, and DAP, respectively) and their corresponding time course of decline. The model was trained and tested based on the hemodynamic instability labels provided by the experts. In total 78 patients were classified as having experienced hemodynamic instability and 279 as not. The hemodynamically unstable patients were significantly older (7 years, 95% confidence interval (CI), 4-11, P < .001), with a higher prevalence of chronic obstructive pulmonary disease (COPD) (3% higher, 95% CI, 1-8, P = .036). Before induction, hemodynamically unstable patients had a higher SAP (median (first-third quartile): 161 (145-175) mm Hg vs 150 (134-166) mm Hg, P < .001) compared to hemodynamic stable patients. Interrater agreement between experts was 0.92 (95% CI, 0.89-0.94). The random forest classifier model showed excellent performance with an area under the receiver operating curve (AUROC) of 0.96, a sensitivity of 0.84, and specificity of 0.94. Based on the high sensitivity and specificity, the developed model is able to differentiate between clinically relevant hemodynamic instability and hemodynamic stable patients. This classification model will pave the way for future research concerning hemodynamic instability and its prevention.

Effect of the Covid-19 pandemic on hospitalizations for non-Covid-19-pneumonia and exacerbations of chronic obstructive pulmonary diseases in Switzerland: comparison of national data between 2020/2021 and 2015–2019

BackgroundProtective measures applied during the Covid-19 pandemic had a marked impact on the incidence of pneumonia. However, systematic data are lacking for hospitalizations for pneumonia and acute exacerbations of chronic obstructive lung diseases (AECOPD) not caused by SARS-CoV-2 in Switzerland. We aimed to compare the incidences of hospitalization for these entities between 2020/2021 and prepandemic years.MethodsThis retrospective study examined all nationwide hospitalizations for non-Covid-19-pneumonia and AECOPD listed as primary diagnoses based on ICD-10 codes between 2015 and 2021 in a publicly available hospitalization database of the Swiss Federal Statistical Office. Hospitalizations for acute coronary syndrome (ACS) and stroke were used as controls. Changes of monthly incidences of hospitalizations, length of stay (LOS) and mortality were compared between 2020/2021 and the average of 2015–2019.ResultsThe incidences of hospitalizations for AECOPD and for pneumonia showed seasonal variations from 2015 to 2019 followed by significant and almost identical decreases in 2020/2021 (incidence rate ratio [IRR] 0.59, 95% CI: 0.45–0.77, p < 0.001, and IRR: 0.62, 95% CI: 0.52–0.74, p < 0.001, respectively). Hospital-mortality was slightly higher in 2020/2021 for AECOPD (2015–2019: 3.8%; 2020/2021: 4.2%, odds ratio [OR] 1.24, 95% CI: 1.07–1.44, p = 0.004) and for pneumonia (2015–2019: 4.5%, 2020/2021: 4.6%, odds ratio [OR] 1.17, 95% CI: 1.07–1.28, p < 0.001). Median LOS slightly decreased for AECOPD (2015–2019: 8 [IQR: 5–14] days; 2020/2021: 7 [IQR: 4–13] days, Wilcoxon test: p < 0.001) but slightly increased for pneumonia (2015–2019: 7 [IQR: 4–11] days; 2020/2021: 7 [IQR: 4–13] days, Wilcoxon test: p < 0.001). Throughout 2020/2021, there were no significant fluctuations observed in the incidences of ACS and stroke. (IRR: 0.98, 95% CI: 0.83–1.16, p = 0.810, IRR: 0.96, 95% CI: 0.81–1.14, p = 0.636, respectively).ConclusionThe first two years of the Covid-19 pandemic showed a marked decrease in incidences in AECOPD and non-Covid-19 pneumonia hospitalizations in Switzerland. It is likely that this effect is associated with the society-based, at first vigorous, social distancing measures.

Cardiovascular Risk Assessment in Chronic Obstructive Pulmonary Disease Patients

Cardiovascular Risk Assessment in Chronic Obstructive Pulmonary Disease Patients

Short-term effects on physical activity level with web-based self-management support in people with COPD: a randomised controlled trial

We aimed to evaluate short-term effects of a web-based self-management support on objectively measured physical activity (PA) compared to usual care in people with chronic obstructive pulmonary disease (COPD). We conducted a pragmatic randomised controlled trial including people with stable COPD within primary healthcare. Participants were randomised to intervention group, IG (access to the COPD Web, an interactive website to support self-management with focus on PA), or to control group, CG (usual care). Primary outcome at 3 months was change in accelerometry-measured daily steps analysed with ANCOVA, and secondary outcomes were self-reported PA, disease-related symptoms, and quality of life. Missing data in intention-to-treat (ITT) analyses were multiply imputed. One hundred and forty-six participants (n = 73/group), mean (SD) age 69.5 (6.7) years, FEV1pred 60.7 (19.1)% were included. The ITT analysis showed no significant difference in steps between the groups: 1295 steps (95% CI: [−365, 2955], p = 0.12), while the complete case analysis (n = 98) revealed a significant difference of 1492 steps (95% CI: [374, 2609], p = 0.01) in favour of IG. A significant increase in self-reported PA was seen in IG in both the ITT and complete case analysis. In summary, access to the COPD Web was insufficient to increase short-term PA level compared to usual care. However, among participants with complete step data, a clinically relevant effect on daily steps exceeding the minimal important difference was observed, partly explained by higher baseline PA than among dropouts. This indicates that access to the COPD Web may increase PA levels for some people with COPD.

Diffusion capacity and static hyperinflation as markers of disease progression predict 3-year mortality in COPD: Results from COSYCONET.

Chronic obstructive pulmonary disease (COPD) exhibits diverse patterns of disease progression, due to underlying disease activity. We hypothesized that changes in static hyperinflation or KCO % predicted would reveal subgroups with disease progression unidentified by preestablished markers (FEV1, SGRQ, exacerbation history) and associated with unique baseline biomarker profiles. We explored 18-month measures of disease progression associated with 18-54-month mortality, including changes in hyperinflation parameters and transfer factor, in a large German COPD cohort. Analysing data of 1364 patients from the German observational COSYCONET-cohort, disease progression and improvement patterns were assessed for their impact on mortality via Cox hazard regression models. Association of biomarkers and COPD Assessment test items with phenotypes of disease progression or improvement were evaluated using logistic regression and random forest models. Increased risk of 18-54-month mortality was linked to decrease in KCO % predicted (7.5% increments) and FEV1 (20 mL increments), increase in RV/TLC (2% increments) and SGRQ (≥6 points), and an exacerbation grade of 2 at 18 months. Decrease in KCO % predicted ≥7.5% and an increase of RV/TLC ≥2% were the most frequent measures of 18-month disease progression occurring in ~52% and ~46% of patients, respectively. IL-6 and CRP thresholds exhibited significant associations with medium- and long-term disease measures. In a multicentric cohort of COPD, new markers of current disease activity predicted mid-term mortality and could not be anticipated by baseline biomarkers.

The prevalence of respiratory symptoms and diseases and declined lung function among foundry workers.

Foundry workers are occupationally exposed to a variety of inhalable chemical substances. Occupational exposure to vapors, gases, dusts, and fumes can lead to adverse health effects on the respiratory system and cause chronic respiratory diseases, such as interstitial lung diseases (ILDs), chronic obstructive lung disease (COPD), chronic bronchitis, and emphysema. Research on respiratory symptoms, diseases, and lung function in foundry workers over the past few decades has been limited. The aim of this cross-sectional study was to assess the prevalence of respiratory symptoms and diseases and declined lung function of current foundry workers, ex-foundry workers, and unexposed controls. We assessed respiratory symptoms, diseases, and lung function among 335 current foundry workers, 64 ex-foundry workers, and 161 unexposed controls. The cumulative dust exposure (mg-y) of each participant was calculated, and the median cumulative dust exposure according to the main places of exposure was determined. A higher prevalence of chronic bronchitis, as reported in a questionnaire, was found among current and ex-foundry workers compared to unexposed controls, even after adjusting for pack-years of smoking (p = 0.009). Additionally, cough and wheezing in adulthood without respiratory infection, and chronic rhinitis symptoms were more common among current and ex-foundry workers compared to unexposed controls. These differences remained significant even after adjusting for pack-years of smoking and body mass index (BMI) (p = 0.007 and p < 0.001, respectively). Impaired lung function was more prevalent among both ex-foundry workers (29.7%) and current foundry workers (15.5%) compared to the unexposed controls (8.7%), with the difference remaining significant even after adjusting for the pack-years of smoking and BMI (p = 0.009). According to the questionnaire, the number of physician-diagnosed cases of chronic obstructive pulmonary disease (COPD) or chronic bronchitis was unexpectedly low compared to the indications from the symptom questionnaire and lung function test results, suggesting a potential underdiagnosis. The prevalence of silicosis was low (0.8%) among current and ex-foundry workers. Respiratory symptoms are common among foundry workers. Current and ex-foundry workers exhibited lower lung function in spirometry compared to unexposed controls. There is a potential underdiagnosis of COPD and chronic bronchitis among foundry workers.

Pulmonary embolism work-up in chronic obstructive pulmonary disease exacerbations: what is the best strategy for clinicians?

Acute exacerbations of chronic obstructive pulmonary disease (COPD) are important events in the natural course of COPD, as they increase morbidity and mortality. Acute pulmonary embolism may mimic the symptoms of COPD exacerbations. However, the exact prevalence of pulmonary embolism in unexplained exacerbations of COPD is unclear based on the current data. This review provides a practical approach to patients with COPD complaining of worsening respiratory symptoms. A randomized clinical trial has shown that a routine pulmonary embolism diagnostic work-up does not improve care of patients with acute exacerbations of COPD. However, review of the recent literature suggests that a nonnegligible proportion of otherwise unexplained exacerbations of COPD may be caused by pulmonary embolism. To date, nevertheless, there are limited studies developing and validating clinical models that might aid in the identification of patients requiring additional tests for the diagnosis of pulmonary embolism. Until new evidence becomes available, we believe that a routine diagnostic strategy for pulmonary embolism is not appropriate for patients with acute exacerbations of COPD. Recommendations for routine pulmonary embolism diagnostic work-up necessitate further development of prognostic models and conduct of clinical trials that assess important health outcomes.

The effect of patients' socioeconomic status in rehabilitation centers on the efficiency and performance.

Patients' socioeconomic status on hospitals' efficiency in controlling for clinical component characteristics may have a role that has few been studied in rehabilitation centers. Because of the national health insurance system, rehabilitation centers are free of charge. To answer whether a patient's socioeconomic status (SES) is associated with efficiency and performance, we use a counterfactual analysis to get the patient's SES effect "as if" the patient's case was identical to whatever hospital. We restrained the data to patients from public acute care units where the decision on rehabilitation sector admission is based on availability, limiting bias by confounding factors. Besides, an analysis of six pathologies led to the same results. An exhaustive, detailed administrative database on rehabilitation center stays in France. To define the patients' socioeconomic status, we use two sources of data: the information collected at the time of the patient's entry into rehabilitation care and the information collected during the patient's stay in acute care. This double information avoids possible loss of socio-economic details between the two admissions. Patients recruited were exhaustively admitted over the year 2018 for stroke, chronic obstructive pulmonary disease, heart failure, or total hip replacement in France in the acute care unit and then in a rehab center. Mainly the elderly population. Information on patients' demography, comorbidities, and SES are coded due to the reimbursement system. Different dimensions controlling for factors (hospital ownership, patient clinical characteristics, rehabilitation care specificities, medical staff detailed information, and patients' socioeconomic status), were progressively added to control for any differences in baseline data between the two groups. We assess rehabilitation centers' efficiency by combining selected outcome quality indicators (Physical score improvement, Cognitive score improvement, Mortality, Return-to-home). The specific Providers' Activity Index is used to get the performance index. The performance of healthcare institutions is correlated not only to the case mix of their patients but also to the socioeconomic status of the patients admitted. The performance needs to be seen in light of patients' socioeconomic status. The data reveals that patients' socioeconomic status affects rehabilitation care efficiency and performance. In controlling patients' socioeconomic status, for-profit rehabilitation hospitals seemed more efficient than public ones.

Automated CT-based Decoupling of the Effects of Airway Narrowing and Wall Thinning on Airway Counts in Chronic Obstructive Pulmonary Disease.

We examine pathways of airway alteration due to wall thinning, narrowing, and obliteration at different COPD severity stages using CT-derived airway metrics. Ex-smokers (N = 649; age mean±std: 69 ± 6years; 52% male) from the COPDGene Iowa cohort (September 2013-July 2017) were studied. Total airway count (TAC), peripheral TAC beyond 7th generation (TACp), and airway wall thickness (WT) were computed from chest CT scans using previously validated automated methods. Causal relationships among demographic, smoking, spirometry, COPD severity, airway counts, WT, and scanner variables were analyzed using causal inference techniques including direct acyclic graphs (DAGs) to quantitatively assess multi-pathway alterations of airways in COPD. TAC, TACp, and WT were significantly lower (p < 0.0001) in mild, moderate, and severe COPD compared to the preserved lung function group. TAC (TACp) losses attributed to narrowing and obliteration of small airways were 4.59, 13.29, and 32.58% (4.64, 17.82, and 45.51%) in mild, moderate, and severe COPD, while the losses attributed to wall thinning were 8.24, 17.01, and 22.95% (12.79, 25.66, and 33.95%) in respective groups. Different pathways of airway alteration in COPD are observed using CT-derived automated airway metrics. Wall thinning is a dominant contributor to both TAC and TACp loss in mild and moderate COPD while narrowing and obliteration of small airways is dominant in severe COPD. This automated CT-based study shows that wall thinning dominates airway alteration in mild and moderate COPD while narrowing and obliteration of small airways leads the alteration process in severe COPD.

Development and validation of a nomogram for predicting bacterial infections in patients with acute exacerbation of chronic obstructive pulmonary disease

Development and validation of a nomogram for predicting bacterial infections in patients with acute exacerbation of chronic obstructive pulmonary disease

Animal models of chronic obstructive pulmonary disease: a systematic review

Animal models of chronic obstructive pulmonary disease: a systematic review

Establishment of a prediction model for venous thromboembolism in patients with acute exacerbation of chronic obstructive pulmonary disease based on serum homocysteine levels and Wells scores: a retrospective cohort study

BackgroundWe evaluated the diagnostic value of homocysteine (Hcy) levels combined with the Wells score and established a prediction model for venous thromboembolism (VTE) occurrence in patients with acute exacerbations of chronic obstructive pulmonary disease (AECOPD) based on the Hcy level and the Wells score.Patients and methodsClinical information from 914 patients with AECOPD was retrospectively collected in our hospital from June 2020 to October 2023. Receiver operating characteristic curves were plotted to evaluate the diagnostic ability of Hcy concentrations combined with Wells scores and the prediction ability of the model. Univariate and multivariate logistic regressions were used to explore the effects of Hcy levels and the Wells score on VTE occurrence. A nomogram was established for individual risk evaluation.ResultsHcy levels and Wells scores were significantly greater in the VTE group than in the non-VTE group (P < 0.001). The diagnostic ability of Hcy levels combined with the Wells score was greater than that Hcy levels or the Wells score alone. The AUC of the combined parameters was 0.935, with a sensitivity of 0.864 and a specificity of 0.855. Multivariate logistic regression indicated that elevated Hcy levels (OR:5.17, 95%CI: 3.76–7.09, P < 0.001) and Wells score (OR: 5.26, 95%CI: 3.22–8.59, P < 0.001) were independently associated with the risk of developing VTE in AECOPD patients. Decision curve analysis indicated that the net benefit of the nonadherence prediction nomogram was greater than that of the models adjusted for no or all variables, with a threshold of approximately 0.1-1.0.ConclusionsThe established prediction model can be used to evaluate an individual’s risk of developing VTE on the basis of the Hcy level, Wells score, and clinical parameters. AECOPD patients may benefit from the early intervention based on estimated risk probability.

Association of chronic obstructive pulmonary disease with risk of lung cancer in individuals aged 40 years and older: A cross-sectional study based on NHANES 2013-2018.

It remains unclear whether chronic obstructive pulmonary disease (COPD) is an independent risk factor for lung cancer after excluding confounding factors such as smoking, age, sex, body mass index (BMI), comorbidities, etc. Data from 11,440 participants (≥ 40 years old) in the National Health and Nutrition Examination Survey (NHANES) 2013-2018 were analyzed. Weighted multivariable logistic regression models were used to assess the association between COPD and lung cancer risk. Subgroup analyses were based on age, sex, BMI, and smoking. This study included 660 patients with COPD and 10,780 participants without COPD. The prevalence of lung cancer was significantly higher in patients with COPD compared to participants without COPD (3.39% vs 0.14%). After adjusting for confounding factors, COPD was associated with a significantly increased risk of lung cancer (OR, 12.24, 95% CI, 4.99-30.06, p < 0.001). This association remained significant in all subgroups, particularly in individuals aged > 65 years (OR, 20.05, 95% CI, 6.85-58.72, p < 0.001), smokers (OR, 19.38, 95% CI, 2.02-185.66, p = 0.010), males (OR, 17.39, 95% CI, 5.28-57.31, p < 0.001), individuals who quit smoking within 10 years (OR, 12.86, 95% CI, 2.59, 63.99, p = 0.002), and individuals with a BMI > 25 kg/m2 (OR, 14.56, 95% CI, 3.88-54.69, p < 0.001). COPD is an independent risk factor for lung cancer, especially in certain subgroups. The combination of COPD and smoking greatly amplifies the lung cancer risk. These findings highlight the importance of early lung cancer screening in patients with COPD.

Comorbidities, Tobacco Exposure, and Geography: Added Risk Factors of Heat and Cold Wave Related Mortality among United States Veterans with COPD.

Understanding the health risks associated with extreme weather events is needed to inform policies to protect vulnerable populations. To address this need, we estimated heat and cold wave related mortality risks in a cohort of veteran patients with chronic obstructive pulmonary disease (COPD) and explored disparities among strata of comorbidities, tobacco exposure, and urbanicity. We designed a time stratified case-crossover study among deceased patients with COPD between 2016 to 2021 in the Veterans Health Administration system. Distributed lag models with conditional logistic regression estimated incidence rate ratios (IRR) of heat and cold wave associated mortality risk from lag days 0 to 3 for heatwaves and 0 to 7 for cold waves. Attributable risks (AR) per 100,000 patients were also calculated. Of the 377,545 deceased patients with COPD, the largest heatwave related mortality risk was in patients with COPD and asthma, AR: 14,016 (95% CI: -326, 30,706) across lag days 0 to 3. The largest cold wave related mortality burden was in patients with COPD with no other reported comorbidities, AR: 1,704 (95% CI: 759, 2,686) across lag days 0 to 7. Patients residing in urban settings had the greatest heatwave, AR: 1,062 (95% CI: (576, 1,559), and cold wave AR: 1,261 (95% CI: 440, 2,105) related mortality risk (across lag days 0 to 1 and 0 to 7 respectively). There were no differences in mortality risk by tobacco exposure. Our findings show individuals with COPD are susceptible to heat and cold waves. This information can inform clinical practice and public health policy about the mortality risk vulnerable populations experience with respect to extreme weather conditions. Furthermore, our results may be used in the development and refinement of future extreme weather warning systems designed for public health purposes.

Personalized COPD Care: The Future of Precision-Based Therapies

Chronic obstructive pulmonary disease (COPD) is a progressive respiratory illness characterized by long-standing respiratory symptoms and airflow limitation. It is a major contributor to respiratory disease-related deaths and currently ranked as the sixth leading cause of mortality in the United States. Approved pharmacological therapies for the stable disease primarily consist of inhaled short and long-acting bronchodilators, inhaled corticosteroids, azithromycin, and roflumilast. In recent years, significant progress has been made in the management of COPD through the identification of different COPD phenotypes and endotypes, which allows for a more personalized treatment approach. While earlier studies investigating targeted therapies were less promising, recent data on drugs targeting type 2 inflammatory pathways have shown promising results in carefully selected patients. In this article, we will review the available data on targeted therapies as well as the ongoing clinical studies of novel targeted therapies for COPD. Understanding and implementing these advancements hold promise for improving outcomes and quality of life for individuals living with COPD.

High performance method for COPD features extraction using complex network.

Objectives. The paper proposes a novel methodology for the classification of Chronic Obstructive Pulmonary Disease (COPD) utilizing respiratory sound attributes.Methods. The approach involves segmenting respiratory sounds into individual breaths and conducting extensive studies on this dataset. Spectral Transforms, various Wavelet Transforms are applied to capture distinct signal features. Complex Network is also employed to extract characteristic elements, generating novel representations of spectrogram data based on graph factors, including entropy, density, and position. The normalized and enriched data is then used to develop COPD classifiers using six machine learning algorithms, fine-tuning with appropriate training details and hyperparameter tuning.Results. Our results demonstrate robust performance, with ROC curves consistently exhibiting an Area Under the Curve (AUC) > 96% across different time-frequency transformations. Notably, the Random Forest algorithm achieves an AUC of 99.67%, outperforming other algorithms. Moreover, the Wavelet Daubechies 2 (Db2) consistently approaches 98% accuracy, particularly noteworthy in conjunction with the Naive Bayes algorithm.Conclusion. This study diagnosis patients through spectrogram images extracted from lung sounds. The application of Inverse Transforms, Complex Network, and Optimized Classification Algorithms yielded results beyond expectations. This methodology provides a promising approach for accurate COPD diagnosis, leveraging Machine Learning techniques applied to respiratory sound analysis.

Machine learning approach to flare-up detection and clustering in chronic obstructive pulmonary disease (COPD) patients.

Chronic obstructive pulmonary disease (COPD) is a prevalent and preventable condition that typically worsens over time. Acute exacerbations of COPD significantly impact disease progression, underscoring the importance of prevention efforts. This observational study aimed to achieve two main objectives: (1) identify patients at risk of exacerbations using an ensemble of clustering algorithms, and (2) classify patients into distinct clusters based on disease severity. Data from portable medical devices were analyzed post-hoc using hyperparameter optimization with Self-Organizing Maps (SOM), Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Isolation Forest, and Support Vector Machine (SVM) algorithms, to detect flare-ups. Principal Component Analysis (PCA) followed by KMeans clustering was applied to categorize patients by severity. 25 patients were included within the study population, data from 17 patients had the required reliability. Five patients were identified in the highest deterioration group, with one clinically confirmed exacerbation accurately detected by our ensemble algorithm. Then, PCA and KMeans clustering grouped patients into three clusters based on severity: Cluster 0 started with the least severe characteristics but experienced decline, Cluster 1 consistently showed the most severe characteristics, and Cluster 2 showed slight improvement. Our approach effectively identified patients at risk of exacerbations and classified them by disease severity. Although promising, the approach would need to be verified on a larger sample with a larger number of recorded clinically verified exacerbations.

A Framework for Detecting Pulmonary Diseases from Lung Sound Signals Using a Hybrid Multi-Task Autoencoder-SVM Model

Research focuses on the efficacy of Multi-Task Autoencoder (MTAE) models in signal classification due to their ability to handle many tasks while improving feature extraction. However, researchers have not thoroughly investigated the study of lung sounds (LSs) for pulmonary disease detection. This paper introduces a new framework that utilizes an MTAE model to detect lung diseases based on LS signals. The model integrates an autoencoder and a supervised classifier, simultaneously optimizing both classification accuracy and signal reconstruction. Furthermore, we propose a hybrid approach that combines an MTAE and a Support Vector Machine (MTAE-SVM) to enhance performance. We evaluated our model using LS signals from a publicly available database from King Abdullah University Hospital. The model attained an accuracy of 89.47% for four classes (normal, pneumonia, asthma, and chronic obstructive pulmonary disease) and 90.22% for three classes (normal, pneumonia, and asthma cases). Using the MTAE-SVM, the accuracy was further improved to 91.49% for four classes and 93.08% for three classes, respectively. The results indicate that the MTAE and MTAE-SVM have a considerable potential for detecting pulmonary diseases from lung sound signals. This could aid in the creation of more user-friendly and effective diagnostic tools.