Explainable machine learning methods and respiratory oscillometry for the diagnosis of respiratory abnormalities in sarcoidosis.

BACKGROUND: In this work, we developed many machine learning classifiers to assist in diagnosing respiratory changes associated with sarcoidosis, based on results from the Forced Oscillation Technique (FOT), a non-invasive method used to assess pulmonary mechanics. In addition to accurate results, there is a particular interest in their interpretability and explainability, so we used Genetic Programming since the classification is made with intelligible expressions and we also evaluate the feature importance in different experiments to find the more discriminative features. METHODOLOGY/PRINCIPAL FINDINGS: We used genetic programming in its traditional tree form and a grammar-based form. To check if interpretable results are competitive, we compared their performance to K-Nearest Neighbors, Support Vector Machine, AdaBoost, Random Forest, LightGBM, XGBoost, Decision Trees and Logistic Regressor. We also performed experiments with fuzzy features and tested a feature selection technique to bring even more interpretability. The data used to feed the classifiers come from the FOT exams in 72 individuals, of which 25 were healthy, and 47 were diagnosed with sarcoidosis. Among the latter, 24 showed normal conditions by spirometry, and 23 showed respiratory changes. The results achieved high accuracy (AUC > 0.90) in two analyses performed (controls vs. individuals with sarcoidosis and normal spirometry and controls vs. individuals with sarcoidosis and altered spirometry). Genetic Programming and Grammatical Evolution were particularly beneficial because they provide intelligible expressions to make the classification. The observation of which features were selected most frequently also brought explainability to the study of sarcoidosis. CONCLUSIONS: The proposed system may provide decision support for clinicians when they are struggling to give a confirmed clinical diagnosis. Clinicians may reference the prediction results and make better decisions, improving the productivity of pulmonary function services by AI-assisted workflow.

Determining airflow obstruction from tracheal sound analysis: simulated tests and evaluations in patients with acromegaly.

To evaluate the ability of tracheal sound analysis (TSA) to detect airflow obstruction, particularly in patients with acromegaly. A simulated analysis compared free airflow conditions with airflow through orifice plates 6, 8, 10 and 12 mm in diameter. Based on these results, TSA and spirometry examinations were performed on controls (n = 17) and patients with acromegaly (n = 17). The simulated study showed that airway obstruction and airflow values increased the values of power and a progressive displacement of the spectral distribution towards higher frequencies. In agreement with the simulation, airway obstruction in patients with acromegaly also resulted in increased values of power (p < 0.002) and displacement of the spectral distribution (p < 0.01). Significant associations were observed between the TSA parameters and the spirometry indices of obstruction (p < 0.02). In addition, the TSA parameters achieved adequate diagnostic accuracy (AUC ≥ 0.887). The present study provides evidence that TSA during resting breathing would provide adequate biomarkers of early upper airway changes in patients with acromegaly. TSA is carried out during spontaneous ventilation, requires little from the patient, and is fast and inexpensive. Taken together, these practical considerations and the results of the present study suggest that TSA may improve lung function tests for patients with acromegaly. Summary of the study, overall design flow and the main results obtained.

Does group-based high-intensity aerobic interval training improve the inflammatory status in patients with chronic heart failure?

BACKGROUND: Chronic heart failure (CHF) is a multifaceted syndrome associated with endothelial dysfunction and increased inflammation. Despite the existing controversies regarding the appropriate training modality, it is widely accepted that supervised cardiac rehabilitation (CR) interventions lead to proinflammatory biomarkers reduction and cellular adhesion molecules in patients with CHF. AIM: The aim of the study was to quantify the effects of 12-week group-based high-intensity aerobic interval training (HIAIT)/modified group-based HIAIT intervention (m-Ullevaal) vs. moderate continuous training (MICT) on serum levels of proinflammatory biomarkers. DESIGN: Single-blind, two-arm, prospective randomized controlled trial conducted on CHF outpatients performing group-based CR interventions throughout a 12-week period. SETTING: The setting of the study was the Medical Center of Outpatient Rehabilitation and Sports Medicine, Plovdiv, Bulgaria. POPULATION: The population included a total of 120 outpatients of both genders, mean age of 63.73±6.68 years, with stable CHF (NYHA classes II to IIIB, were randomly assigned to HIAIT/ m-Ullevaal (N.=60) or to MICT (N.=60) group. METHODS: Functional exercise capacity (FEC) of the eligible subjects was evaluated through 6-minute walk test (6MWT) and peak oxygen uptake. Blood samples were drawn at baseline, after 12 weeks follow-up for analyses of C-reactive protein (CRP), tumor necrosis factor-α (TNFα) and cellular adhesion molecules (CAM). RESULTS: Significant decreases in the serum levels of CRP (P=0.029), TNF-α (P=0.036), and vascular cell adhesion molecule-1 (VCAM-1) (P=0.040), were observed after 48 training sessions in the group-based HIAIT/m-Ullevaal intervention, except for intercellular adhesion molecule-1 (ICAM-1), which was higher in the MICT (P=0.034). FEC was significantly inversely related to CRP (r=-0.72, P<0.05), and the levels of VCAM-1 (r=-0.68, P<0.05). CONCLUSIONS: Both group-based CR interventions (HIAIT/m-Ullevaal and MICT) significantly reduced the serum levels of CRP, TNF- α, ICAM-1 and VCAM in patients with CHF. However, selected proinflammatory biomarkers changes and CAMs favorably decreased in the group-based HIAIT/m-Ullevaal intervention. The responses on serum levels of proinflammatory biomarkers and CAMs are dependent upon the type, intensity, and CR intervention duration. CLINICAL REHABILITATION IMPACT: The group-based high-intensity aerobic interval training reduces significantly the proinflammatory biomarkers and cellular adhesion molecules in patients with chronic heart failure.

Impulse Oscillometry Findings and Their Associations With Lung Ultrasound Signs in COVID-19 Survivors.

BACKGROUND: Because impulse oscillometry (IOS) can detect changes in the small airways and is safer to perform during the COVID-19 pandemic than other pulmonary function tests, it may have value in investigating pulmonary sequelae in COVID-19 survivors. This study evaluated the performance of IOS in detecting lung abnormalities in COVID-19 survivors and investigated the associations of the findings with those of lung ultrasound (LUS) and spirometry. METHODS: In this cross-sectional study, 117 subjects underwent IOS at a frequency range of 4-20 Hz 2 months after COVID-19 diagnosis. They also underwent spirometry and LUS, and their aeration scores were calculated. RESULTS: On IOS, the resonance frequency was > 12 Hz, and the area under the reactance curve was > 3.60 cm H2O/L/s in 70 (59.8%) and 55 (47.0%) subjects, respectively. A heterogeneity of resistance between R4 and R20 (R4-R20) > 20% was observed in 60 (51.3%) participants. Based on their abnormalities in resistive and reactive parameters, 76 (65.0%) participants had abnormal IOS. Spirometry abnormalities were detected in 40 (34.2%) cases. LUS was abnormal in 51 (43.6%) participants, and the median aeration score was 0 (0-8) points. Abnormal IOS was associated with abnormal LUS (P < .001) and abnormal spirometry (P = .002). Abnormal spirometry had a significant but weaker association with abnormal LUS (P = .031). In participants who reported hospitalization, abnormal IOS was associated with both abnormal LUS (P = .001) and abnormal spirometry (P = .006). In participants who did not report hospitalization, abnormal IOS was associated with abnormal LUS (P < .001) but not abnormal spirometry (P = .063). CONCLUSIONS: In COVID-19 survivors, IOS detected changes even when spirometry was normal. In these individuals, IOS parameters were more strongly associated with abnormalities on LUS than with abnormalities on spirometry.

Long-term pulmonary rehabilitation progressively reduces hospitalizations and mortality in patients with severe COPD: a 5-year follow-up.

BACKGROUND: Pulmonary rehabilitation (PR) is recognized as a multidisciplinary intervention designed to reduce symptoms, improve functional status, and prevent acute exacerbations in patients with chronic obstructive pulmonary disease (COPD). AIM: This study was aimed at evaluating the effects of a long-term PR program on the hospitalization rate and mortality of patients with severe and very severe COPD. DESIGN: Longitudinal, prospective study. SETTING: Pulmonary rehabilitation program at our institution. POPULATION: A cohort of 195 patients undergoing a PR program was followed up for 5 years. They were divided into three groups: control (PR<3 months), partial adherence (PR>6 and ≤18 months) and adherence (PR=24 months). METHODS: This was a prospective study where All patients were evaluated every 6 months (D0, D6, D12, D18 and D24, and mapped annually concerning hospitalizations and mortality). Data were analyzed by medians and interquartile ranges, and Kruskal-Wallis non-parametric comparative tests were applied. Comparisons of time to first admission and time to death were made using the Kaplan-Meier estimators, and the factors associated with these outcomes were modeled using semi-parametric Cox models. RESULTS: The results demonstrated a significant reduction in the rate of hospitalization and mortality. The protective effect seems to be dependent on the lengths of stay of patients in the PR program. CONCLUSIONS: A multi-disciplinary, long-term PR program with individually tailored 96-week supervised interventions, reduces hospitalization rates and mortality in patients with severe and very severe COPD in a 5-year follow-up period. This protective effect on hospitalization and mortality is obtained from at least 18 months of intervention. Patients who stay longer in the PR program appear to experience a longer protective effect at the end of treatment. CLINICAL REHABILITATION IMPACT: This long-term PR program for patients with severe and very severe COPD produced progressively favorable clinical effects, thus reducing the frequency of hospitalizations and mortality in this population.

Machine learning associated with respiratory oscillometry: a computer-aided diagnosis system for the detection of respiratory abnormalities in systemic sclerosis.

INTRODUCTION: The use of machine learning (ML) methods would improve the diagnosis of respiratory changes in systemic sclerosis (SSc). This paper evaluates the performance of several ML algorithms associated with the respiratory oscillometry analysis to aid in the diagnostic of respiratory changes in SSc. We also find out the best configuration for this task. METHODS: Oscillometric and spirometric exams were performed in 82 individuals, including controls (n = 30) and patients with systemic sclerosis with normal (n = 22) and abnormal (n = 30) spirometry. Multiple instance classifiers and different supervised machine learning techniques were investigated, including k-Nearest Neighbors (KNN), Random Forests (RF), AdaBoost with decision trees (ADAB), and Extreme Gradient Boosting (XGB). RESULTS AND DISCUSSION: The first experiment of this study showed that the best oscillometric parameter (BOP) was dynamic compliance, which provided moderate accuracy (AUC = 0.77) in the scenario control group versus patients with sclerosis and normal spirometry (CGvsPSNS). In the scenario control group versus patients with sclerosis and altered spirometry (CGvsPSAS), the BOP obtained high accuracy (AUC = 0.94). In the second experiment, the ML techniques were used. In CGvsPSNS, KNN achieved the best result (AUC = 0.90), significantly improving the accuracy in comparison with the BOP (p < 0.01), while in CGvsPSAS, RF obtained the best results (AUC = 0.97), also significantly improving the diagnostic accuracy (p < 0.05). In the third, fourth, fifth, and sixth experiments, different feature selection techniques allowed us to spot the best oscillometric parameters. They resulted in a small increase in diagnostic accuracy in CGvsPSNS (respectively, 0.87, 0.86, 0.82, and 0.84), while in the CGvsPSAS, the best classifier's performance remained the same (AUC = 0.97). CONCLUSIONS: Oscillometric principles combined with machine learning algorithms provide a new method for diagnosing respiratory changes in patients with systemic sclerosis. The present study's findings provide evidence that this combination may help in the early diagnosis of respiratory changes in these patients.

Differential diagnosis of asthma and restrictive respiratory diseases by combining forced oscillation measurements, machine learning and neuro-fuzzy classifiers.

To design machine learning classifiers to facilitate the clinical use and increase the accuracy of the forced oscillation technique (FOT) in the differential diagnosis of patients with asthma and restrictive respiratory diseases. FOT and spirometric exams were performed in 97 individuals, including controls (n = 20), asthmatic patients (n = 38), and restrictive (n = 39) patients. The first experiment of this study showed that the best FOT parameter was the resonance frequency, providing moderate accuracy (AUC = 0.87). In the second experiment, a neuro-fuzzy classifier and different supervised machine learning techniques were investigated, including k-nearest neighbors, random forests, AdaBoost with decision trees, and support vector machines with a radial basis kernel. All classifiers achieved high accuracy (AUC ≥ 0.9) in the differentiation between patient groups. In the third and fourth experiments, the use of different feature selection techniques allowed us to achieve high accuracy with only three FOT parameters. In addition, the neuro-fuzzy classifier also provided rules to explain the classification. Neuro-fuzzy and machine learning classifiers can aid in the differential diagnosis of patients with asthma and restrictive respiratory diseases. They can assist clinicians as a support system providing accurate diagnostic options.

Group-based cardiac rehabilitation interventions. A challenge for physical and rehabilitation medicine physicians: a randomized controlled trial.

BACKGROUND: In recent decades, many studies are focused on different training modalities comparison in patients with cardiac diseases. High intensity aerobic interval training (HIAIT) has been considered as an alternative approach to moderate-intensity continuous training (MICT) in rehabilitation of patients with chronic heart failure (CHF). AIM: To highlight the superiority of the modified group-based HIAIT intervention (m-Ullevaal) compared to the moderate-intensity continuous training (MICT), also to encourage physical and rehabilitation medicine (PRM) physicians to apply the m-Ullevaal intervention in routine cardiac rehabilitation (CR) practice. DESIGN: А single-blind, prospective randomized controlled trial. SETTING: Medical Center of Rehabilitation and Sports Medicine, Plovdiv, Bulgaria outpatients were enrolled. POPULATION: One hundred and twenty subjects of both genders, mean age of 63.73±6.68 years, with stable CHF, NYHA classes II to IIIB, were randomly assigned to m-Ullevaal group (N.=60) or to MICT (N.=60) group. Both CR protocols were conducted throughout a 12-week period. METHODS: Functional exercise capacity (FEC), assessed with six-minute walk test, and peak oxygen uptake (VO2peak), left ventricular ejection fraction (LVEF), m-Borg's perceived exertion scale (mBPES), and quality of life (QoL) were outcome measures evaluated. RESULTS: Significant improvement in FEC (P<0.001), LVEF (P<0.001), mBPES and QoL (P<0.001), was observed 12 weeks after both CR interventions (T2). However, the participants performed m-Ullevaal protocol achieved a greater improvement compared to those performed MICT (P<0.001). CONCLUSIONS: The m-Ullevaal protocol seems to be more beneficial and more effective compared to MICT. PRM physicians can efficiently apply the m-Ullevaal protocol in CHF patients rehabilitation. CLINICAL REHABILITATION IMPACT: Group-based HIAIT interventions can be widely applied by PRM physicians in CHF patients rehabilitation.

Predictive models for the six-minute walk test considering the walking course and physical activity level.

BACKGROUND: In recent decades, space limitations in the clinical environment have forced health professionals to administer the six-minute walk test (6MWT) using a 20-m or even a 10-m course. However, course length and physical activity level (PAL) affect the test outcomes. AIM: To develop a reference equation for the 6MWT that takes into account the effects of course length and PAL on the walking distance. DESIGN: Cross-sectional study. SETTING: Federal University of the State of Rio de Janeiro. POPULATION: Two hundred fifteen healthy adults. METHODS: All subjects performed the 6MWT on 10-, 20- and 30-m courses. Eight regression models were constructed considering the association between the six-minute walking distance (6MWD) and heart rate, perceived effort (scores from the Borg's Perceived Exertion Scale-BPES), PAL (classification according to the International Physical Activity Questionnaire, IPAQ), as well as anthropometric and demographic variables. The models were analyzed for the coefficients of determination (R2) and statistical significance at P<0.05. RESULTS: A nonlinear increase in the means of the 6MWDs obtained using the three course lengths was observed (591±70, 652±79 and 678±85 m for course lengths of 10, 20 and 30 m, respectively, with P<0.001). The 6MWD correlated positively with the following variables: sex (r=0.20), body height (r=0.30), IPAQ classification (r=0.14), ΔBPES rating (r=0.25) and Δheart rate (HR, r=0.23), with P<0.001 for all. In contrast, the 6MWD correlated negatively with age (r=-0.23) and Body Mass Index (BMI, r=-0.18), with P<0.001 for both. The regression model with the highest coefficient of determination (adjusted R2=0.36) included the following variables: sex, age, BMI, course length (CL), BPES, HR, and IPAQ. CONCLUSIONS: The length of the course strongly impacts individual performance on the 6MWT in a predominantly young adult population. Furthermore, IPAQ-assessed PAL is an important independent predictor of 6MWD. CLINICAL REHABILITATION IMPACT: The incorporation of course length in the prediction of 6MWD allows the use of a prediction equation that includes the effects of different course sizes. PAL should be used in the prediction of 6MWD.

Association of respiratory integer and fractional-order models with structural abnormalities in silicosis.

BACKGROUND AND OBJECTIVE: Integer and fractional-order models have emerged as powerful methods for obtaining information regarding the anatomical or pathophysiological changes that occur during respiratory diseases. However, the precise interpretation of the model parameters in light of the lung structural changes is not known. This study analyzed the associations of the integer and fractional-order models with structural changes obtained using multidetector computed tomography densitometry (MDCT) and pulmonary function analysis. METHODS: Integer and fractional-order models were adjusted to data obtained using the forced oscillation technique (FOT). The results obtained in controls (n = 20) were compared with those obtained in patients with silicosis (n = 32), who were submitted to spirometry, body plethysmograph, FOT, diffusing capacity of the lungs for carbon monoxide (DLCO), and MDCT. The diagnostic accuracy was also investigated using ROC analysis. RESULTS: The observed changes in the integer and fractional-order models were consistent with the pathophysiology of silicosis. The integer-order model showed association only between inertance and the non-aerated compartment (R = -0.69). This parameter also presented the highest associations with spirometry (R = 0.81), plethysmography (-0.61) and pulmonary diffusion (R = 0.53). Considering the fractional-order model, the increase in the poorly aerated and non-aerated regions presented direct correlations with the fractional inertance (R = 0.48), respiratory damping (R = 0.37) and hysteresivity (R = 0.54) and inverse associations with its fractional exponent (R = -0.62) and elastance (-0.35). Significant associations were also observed with spirometry (R = 0.63), plethysmography (0.37) and pulmonary diffusion (R = 0.51). Receiver operator characteristic analysis showed a higher accuracy in the FrOr model (0.908) than the eRIC model (0.789). CONCLUSIONS: Our study has shown clear associations of the integer and fractional-order parameters with anatomical changes obtained via MDCT and pulmonary function measurements. These findings help to elucidate the physiological interpretation of the integer and fractional-order parameters and provide evidence that these parameters are reflective of the abnormal changes in silicosis. We also observed that the fractional-order model showed smaller curve-fitting errors, which resulted in a higher diagnostic accuracy than that of the eRIC model. Taken together, these results provide strong motivation for further studies exploring the clinical and scientific use of these models in respiratory medicine.

Entropy Analysis for the Evaluation of Respiratory Changes Due to Asbestos Exposure and Associated Smoking.

Breathing is a complex rhythmic motor act, which is created by integrating different inputs to the respiratory centres. Analysing nonlinear fluctuations in breathing may provide clinically relevant information in patients with complex illnesses, such as asbestosis. We evaluated the effect of exposition to asbestos on the complexity of the respiratory system by investigating the respiratory impedance sample entropy (SampEnZrs) and recurrence period density entropy (RPDEnZrs). Similar analyses were performed by evaluating the airflow pattern sample entropy (SampEnV') and recurrence period density entropy (RPDEnV'). Groups of 34 controls and 34 asbestos-exposed patients were evaluated in the respiratory impedance entropy analysis, while groups of 34 controls and 30 asbestos-exposed patients were investigated in the analysis of airflow entropy. Asbestos exposition introduced a significant reduction of RPDEnV' in non-smoker patients (p < 0.0004), which suggests that the airflow pattern becomes less complex in these patients. Smoker patients also presented a reduction in RPDEnV' (p < 0.05). These finding are consistent with the reduction in respiratory system adaptability to daily life activities observed in these patients. It was observed a significant reduction in SampEnV' in smoker patients in comparison with non-smokers (p < 0.02). Diagnostic accuracy evaluations in the whole group of patients (including non-smokers and smokers) indicated that RPDEnV' might be useful in the diagnosis of respiratory abnormalities in asbestos-exposed patients, showing an accuracy of 72.0%. In specific groups of non-smokers, RPDEnV' also presented adequate accuracy (79.0%), while in smoker patients, SampEnV' and RPDEnV' presented adequate accuracy (70.7% and 70.2%, respectively). Taken together, these results suggest that entropy analysis may provide an early and sensitive functional indicator of interstitial asbestosis.

Selecting the best ventilator hyperinflation technique based on physiologic markers: A randomized controlled crossover study.

BACKGROUND: Ventilator hyperinflation (VHI) is effective in improving respiratory mechanics, secretion removal, and gas exchange in mechanically ventilated subjects; however, there are no recommendations for the best ventilator settings to perform the technique. OBJECTIVE: To compare six modes of VHI, concerning physiological markers of efficacy and safety criteria to support the selection of optimal settings. METHODS: Thirty mechanically ventilated patients underwent six modes of VHI in a randomized order. The delivered volume, expiratory flow bias criteria, overdistension, patient-ventilator asynchronies and hemodynamic variables were assessed during the interventions. RESULTS: Volume-controlled ventilation with inspiratory flow of 20 lpm (VC-CMV20) and pressure support ventilation (PSV) achieved the best effectiveness scores (P < 0.05). The target peak pressure of 40 cmH2O was associated with a high incidence of overdistension. PSV showed a lower incidence of patient-ventilator asynchronies. CONCLUSIONS: The modes VC-CMV20 and PSV are the most effective for VHI. Alveolar overdistension and patient-ventilator asynchronies must be considered when applying VHI.

The Role of Multidetector Computed Tomography and the Forced Oscillation Technique in Assessing Lung Damage in Adults With Cystic Fibrosis.

BACKGROUND: With increased survival rates and the consequent emergence of an adult population with cystic fibrosis (CF), developing novel tools for periodic evaluations of these patients has become a new challenge. Thus, we sought to determine the contribution of lung-volume quantification using multidetector computed tomography (CT) in adults with CF and to investigate the association between structural changes and functional abnormalities. METHODS: This was a cross-sectional study in which 21 adults with CF and 22 control subjects underwent lung-volume quantification using multidetector CT. Voxel densities were divided into 4 bands: -1,000 to -900 Hounsfield units (HU) (hyperaerated region), -900 to -500 HU (normally aerated region), -500 to -100 HU (poorly aerated region), and -100 to 100 HU (non-aerated region). In addition, all participants performed pulmonary function tests including spirometry, body plethysmography, diffusion capacity for carbon monoxide, and the forced oscillation technique. RESULTS: Adults with CF had more non-aerated regions and poorly aerated regions with lung-volume quantification using multidetector CT than controls. Despite these abnormalities, total lung volume measured by lung-volume quantification using multidetector CT did not differ between subjects and controls. Total lung capacity (TLC) measured by body plethysmography correlated with both total lung volume (rs = 0.71, P < .001) and total air volume (rs = 0.71, P < .001) as measured with lung-volume quantification using multidetector CT. While the hyperaerated regions correlated with the functional markers of gas retention in the lungs (increased residual volume (RV) and RV/TLC ratio), the poorly aerated regions correlated with the resistive parameters measured by the forced oscillation technique (increased intercept resistance and mean resistance). We also observed a correlation between normally aerated regions and highest pulmonary diffusion values (rs = 0.68, P < .001). CONCLUSIONS: In adults with CF, lung-volume quantification using multidetector CT can destimate the lung volumes of compartments with different densities and determine the aerated and non-aerated contents of the lungs; furthermore, lung-volume quantification using multidetector CT is clearly related to pulmonary function parameters.

Heart rate response and recovery in wheelchair tetraplegic rugby athletes: a pilot study.

BACKGROUND: Subjects with spinal cord injuries (SCI) have impaired autonomic cardiac regulation and increased risk of cardiovascular disease. In face of the insufficient research data on the autonomic control of physically active subjects with SCI, this study aimed at describing the chronotropic response, as well as the heart rate recovery behavior of a cohort of elite wheelchair rugby athletes. METHODS: This is a cross-sectional study including a convenience sample of 17 elite wheelchair rugby athletes with tetraplegia. The subjects underwent a maximal arm ergometry exercise test. Heart rate (HR) was computed at five time points: at rest (before the test), peak exercise, and 1, 2, and 3 minutes after exercise. Data distribution was assessed by using the Shapiro-Wilk Test and correlations were measured by Pearson's correlation coefficient. The level of statistical significance was set at P<0.05. RESULTS: The subjects presented with HR at rest=69.53±8.3 bpm; HR reserve=66.9±8.3%; Chronotropic Index=47.9±11.8%; HRR at 1'=15.2±7.5 bpm; HRR at 2'=25.2±7.4 bpm; HRR at 3'=37±8.4 bpm. 82.3% of the athletes had HRR at 1'>12 bpm, and 64.7% had HRR at 2"> 22 bpm. There were associations between duration of injury and HRR at 1' (r=-0.5; P=0.0398), peak HR (HRpeak) and total weekly training time (r=-0.591; P=0.0125) and HRpeak and weekly physical training time (r=-0.519; P=0.032). CONCLUSIONS: Tetraplegic elite athletes present with reduced chronotropic response. Most of them exhibit an HRR within the values considered normal for the general population.

High-accuracy detection of airway obstruction in asthma using machine learning algorithms and forced oscillation measurements.

BACKGROUND AND OBJECTIVES: The main pathologic feature of asthma is episodic airway obstruction. This is usually detected by spirometry and body plethysmography. These tests, however, require a high degree of collaboration and maximal effort on the part of the patient. There is agreement in the literature that there is a demand of research into new technologies to improve non-invasive testing of lung function. The purpose of this study was to develop automatic classifiers to simplify the clinical use and to increase the accuracy of the forced oscillation technique (FOT) in the diagnosis of airway obstruction in patients with asthma. METHODS: The data consisted of FOT parameters obtained from 75 volunteers (39 with obstruction and 36 without). Different supervised machine learning (ML) techniques were investigated, including k-nearest neighbors (KNN), random forest (RF), AdaBoost with decision trees (ADAB) and feature-based dissimilarity space classifier (FDSC). RESULTS: The first part of this study showed that the best FOT parameter was the resonance frequency (AUC = 0.81), which indicates moderate accuracy (0.70-0.90). In the second part of this study, the use of the cited ML techniques was investigated. All the classifiers improved the diagnostic accuracy. Notably, ADAB and KNN were very close to achieving high accuracy (AUC = 0.88 and 0.89, respectively). Experiments including the cross products of the FOT parameters showed that all the classifiers improved the diagnosis accuracy and KNN was able to reach a higher accuracy range (AUC = 0.91). CONCLUSIONS: Machine learning classifiers can help in the diagnosis of airway obstruction in asthma patients, and they can assist clinicians in airway obstruction identification.

Impact of a 6-month treatment with intragastric balloon on body composition and psychopathological profile in obese individuals with metabolic syndrome.

BACKGROUND: The aim of this study was to investigate the effects of a 6-month treatment with intragastric balloon (IGB) on body composition and depressive/anxiety symptoms in obese individuals with metabolic syndrome (MS). METHODS: Fifty patients (aged 18-50 years) with obesity and MS were selected for treatment with IGB for 6 months. Body composition was verified with dual-energy X-ray absorptiometry (DXA) at baseline and right after IGB removal. Anxiety/depressive symptoms were assessed with the Beck Depression Inventory (BDI) and the hospital anxiety and depression scale (HADS) at baseline and after 6 months of treatment. RESULTS: In total, 39 patients completed the study. After 6 months, there were significant decreases in weight (11.7 ± 9.6 kg, p < 0.0001) and waist circumference (9.3 ± 8.2 cm, p < 0.0001). Weight loss was also demonstrated by DXA and corresponded to decreases of 3.0 ± 3.4% in body fat percentage, 7.53 ± 7.62 kg in total body fat, and 3.70 ± 4.89 kg in lean body mass (p < 0.001 for all comparisons). Depressive symptoms scores decreased by a mean of 4.57 ± 10.6 points when assessed with the BDI (p = 0.002) and 1.82 ± 5.16 points when assessed with the HADS-Depression (p = 0.0345). Anxiety symptoms scores decreased by a mean of 1.84 ± 4.04 points when determined with the HADS-anxiety (p = 0.0066). The decrease in body fat percentage was the parameter that best correlated with improvements in depressive (p = 0.008) and anxiety symptoms (p = 0.014). CONCLUSIONS: In obese individuals with MS, fat mass reduction was associated with short-term improvements in depressive and anxiety symptoms. Trial Registration Registered at ClinicalTrials.gov, NCT01598233.

Currents issues in cardiorespiratory care of patients with post-polio syndrome.

METHOD: A search for papers was made in the databases Bireme, Scielo and Pubmed with the following keywords: post polio syndrome, cardiorespiratory and rehabilitation in English, French and Spanish languages. Although we targeted only seek current studies on the topic in question, only the relevant (double-blind, randomized-controlled and consensus articles) were considered. RESULTS AND DISCUSSION: Certain features of PPS such as generalized fatigue, generalized and specific muscle weakness, joint and/or muscle pain may result in physical inactivity deconditioning obesity and dyslipidemia. Respiratory difficulties are common and may result in hypoxemia. CONCLUSION: Only when evaluated and treated promptly, somE patients can obtain the full benefits of the use of respiratory muscles aids as far as quality of life is concerned.

Currents issues in cardiorespiratory care of patients with post-polio syndrome / Tópicos atuais no tratamento cardiorrespiratório de pacientes com síndrome pós-poliomielite

ABSTRACT Post-polio syndrome (PPS) is a condition that affects polio survivors years after recovery from an initial acute attack of the poliomyelitis virus. Most often, polio survivors experience a gradual new weakening in muscles that were previously affected by the polio infection. The actual incidence of cardiovascular diseases (CVDs) in individuals suffering from PPS is not known. However, there is a reason to suspect that individuals with PPS might be at increased risk. Method A search for papers was made in the databases Bireme, Scielo and Pubmed with the following keywords: post polio syndrome, cardiorespiratory and rehabilitation in English, French and Spanish languages. Although we targeted only seek current studies on the topic in question, only the relevant (double-blind, randomized-controlled and consensus articles) were considered. Results and Discussion Certain features of PPS such as generalized fatigue, generalized and specific muscle weakness, joint and/or muscle pain may result in physical inactivity deconditioning obesity and dyslipidemia. Respiratory difficulties are common and may result in hypoxemia. Conclusion Only when evaluated and treated promptly, somE patients can obtain the full benefits of the use of respiratory muscles aids as far as quality of life is concerned.

RESUMO Síndrome pós-polio (SPP) é uma condição que afeta sobreviventes da poliomielite aguda (PAA), anos após a recuperação de um ataque agudo inicial do vírus. Na maioria das vezes, os sobreviventes da polio começam a apresentar nova paresia gradual nos músculos que foram previamente afetados pela infecção. A incidência real de doenças cardiovasculares (DCV) em indivíduos que sofrem de SPP não é conhecida. Entretanto, há indícios para suspeitar de que sujeitos com SPP podem estar em maior risco. Método Realizou-se uma busca de artigos nas bases de dados: Bireme, Scielo e Pubmed, utilizando as seguintes palavras-chave: síndrome pós-poliomielite, função cardiorrespiratória e reabilitação, nos idiomas Inglês, Francês e Espanhol. Embora tenhamos selecionado um número expressivo de artigos, somente foram considerados os duplo-cegos, randomizados-controlados, além de consensos. Resultados e Discussão Certas características da SPP, tais como fadiga muscular, paresia, dor muscular e/ou articulares podem resultar em descondicionamento por inatividade física, além de obesidade e dislipidemia. Dificuldades respiratórias são comuns e podem resultar em hipoxemia. Conclusão Somente quando avaliados e tratados em tempo hábil, alguns pacientes são capazes de obter os benefícios do uso dos músculos respiratórios auxiliares em termos de qualidade de vida.

Forced oscillation, integer and fractional-order modeling in asthma.

The purpose of this study was to evaluate the use of fractional-order (FrOr) modeling in asthma. To this end, three FrOr models were compared with traditional parameters and an integer-order model (InOr). We investigated which model would best fit the data, the correlation with traditional lung function tests and the contribution to the diagnostic of airway obstruction. The data consisted of forced oscillation (FO) measurements obtained from healthy (n=22) and asthmatic volunteers with mild (n=22), moderate (n=19) and severe (n=19) obstructions. The first part of this study showed that a FrOr was the model that best fit the data (relative distance: FrOr=4.3±2.4; InOr=5.1±2.6%). The correlation analysis resulted in reasonable (R=0.36) to very good (R=0.77) associations between FrOr parameters and spirometry. The closest associations were observed between parameters related to peripheral airway obstruction, showing a clear relationship between the FrOr models and lung mechanics. Receiver-operator analysis showed that FrOr parameters presented a high potential to contribute to the detection of the mild obstruction in a clinical setting. The accuracy [area under the Receiver Operating Characteristic curve (AUC)] observed in these parameters (AUC=0.954) was higher than that observed in traditional FO parameters (AUC=0.732) and that obtained from the InOr model (AUC=0.861). Patients with moderate and severe obstruction were identified with high accuracy (AUC=0.972 and 0.977, respectively). In conclusion, the results obtained are in close agreement with asthma pathology, and provide evidence that FO measurement associated with FrOr models is a non-invasive, simple and radiation-free method for the detection of biomechanical abnormalities in asthma.

CT pulmonary densitovolumetry in patients with acromegaly: a comparison between active disease and controlled disease.

OBJECTIVE: Our purpose was to compare the findings of CT pulmonary densitovolumetry and pulmonary function in patients with active acromegaly and controlled acromegaly and, secondarily, to correlate these findings. METHODS: 11 patients with active acromegaly, 18 patients with controlled acromegaly and 17 control subjects, all non-smokers, underwent quantification of lung volume using multidetector CT (Q-MDCT) and pulmonary function tests. RESULTS: Patients with active acromegaly had larger total lung mass (TLM) values than the controls and larger amounts of non-aerated compartments than the other two groups. Patients with active acromegaly also had larger amounts of poorly aerated compartments than the other two groups, a difference that was observed in both total lung volume (TLV) and TLM. TLV as measured by inspiratory Q-MDCT correlated significantly with total lung capacity, whereas TLV measured using expiratory Q-MDCT correlated significantly with functional residual capacity. CONCLUSION: Patients with active acromegaly have more lung mass and larger amounts of non-aerated and poorly aerated compartments. There is a relationship between the findings of CT pulmonary densitovolumetry and pulmonary function test parameters. ADVANCES IN KNOWLEDGE: Although the nature of our results demands further investigation, our data suggest that both CT pulmonary densitovolumetry and pulmonary function tests can be used as useful tools for patients with acromegaly by assisting in the prediction of disease activity.