Search

We recently developed a model-based method for analyzing multiple breath nitrogen washout data that does not require identification of Phase-III. In the present study, we assessed the effect of irregular breathing patterns on the intra-subject variabilities of the model parameters. Nitrogen fraction at the mouth was measured in 18 healthy and 20 asthmatic subjects during triplicate performances of multiple breath nitrogen washout, during controlled (target tidal volume 1 L at 8-12 breaths per minute) and free (unrestricted) breathing. The parameters Scond, Sacin and functional residual capacity (FRC) were obtained by conventional analysis of the slope of Phase-III. Fitting the model to the washout data provided functional residual capacity (FRCM), dead space volume (VD), the coefficient of variation of regional specific ventilation ([Formula: see text]), and the model equivalent of Sacin (Sacin-M). Intra-participant coefficients of variation for the model parameters for both health and asthma were FRCM < 5.2%, VD < 5.4%, [Formula: see text] < 9.0%, and Sacin-M < 45.6% for controlled breathing, and FRCM < 4.6%, VD < 5.3%, [Formula: see text] < 13.2%, and Sacin-M < 103.2% for free breathing. The coefficients of variation limits for conventional parameters were FRC < 6.1%, with Scond < 73.6% and Sacin < 49.2% for controlled breathing and Scond < 35.0% and Sacin < 74.4% for free breathing. The model-fitting approach to multiple breath nitrogen washout analysis provides a measure of regional ventilation heterogeneity in [Formula: see text] that is less affected by irregularities in the breathing pattern than its corresponding Phase-III slope analysis parameter Scond.

Landscape fires are increasing in frequency and severity globally. In Australia, extreme bushfires cause a large and increasing health and socioeconomic burden for communities and governments. People with asthma are particularly vulnerable to the effects of landscape fire smoke (LFS) exposure. Here, we present a position statement from the Thoracic Society of Australia and New Zealand. Within this statement we provide a review of the impact of LFS on adults and children with asthma, highlighting the greater impact of LFS on vulnerable groups, particularly older people, pregnant women and Aboriginal and Torres Strait Islander peoples. We also highlight the development of asthma on the background of risk factors (smoking, occupation and atopy). Within this document we present advice for asthma management, smoke mitigation strategies and access to air quality information, that should be implemented during periods of LFS. We promote clinician awareness, and the implementation of public health messaging and preparation, especially for people with asthma.

We recently developed a model-based method for analyzing multiple breath nitrogen washout data that does not require identification of Phase-III. In the present study, we assessed the effect of irregular breathing patterns on the intra-subject variabilities of the model parameters. Nitrogen fraction at the mouth was measured in 18 healthy and 20 asthmatic subjects during triplicate performances of multiple breath nitrogen washout, during controlled (target tidal volume 1 L at 8-12 breaths per minute) and free (unrestricted) breathing. The parameters Scond, Sacin and functional residual capacity (FRC) were obtained by conventional analysis of the slope of Phase-III. Fitting the model to the washout data provided functional residual capacity (FRCM), dead space volume (VD), the coefficient of variation of regional specific ventilation ([Formula: see text]), and the model equivalent of Sacin (Sacin-M). Intra-participant coefficients of variation for the model parameters for both health and asthma were FRCM < 5.2%, VD < 5.4%, [Formula: see text] < 9.0%, and Sacin-M < 45.6% for controlled breathing, and FRCM < 4.6%, VD < 5.3%, [Formula: see text] < 13.2%, and Sacin-M < 103.2% for free breathing. The coefficients of variation limits for conventional parameters were FRC < 6.1%, with Scond < 73.6% and Sacin < 49.2% for controlled breathing and Scond < 35.0% and Sacin < 74.4% for free breathing. The model-fitting approach to multiple breath nitrogen washout analysis provides a measure of regional ventilation heterogeneity in [Formula: see text] that is less affected by irregularities in the breathing pattern than its corresponding Phase-III slope analysis parameter Scond.

INTRODUCTION: The multiple breath nitrogen washout (MBNW) test provides important clinical information in obstructive airways diseases. Recently, a significant cross-sensitivity error in the O2 and CO2 sensors of a widely used commercial MBNW device (Exhalyzer D, Eco Medics AG, Duernten, Switzerland) was detected, which leads to overestimation of N2 concentrations. Significant errors in functional residual capacity (FRC) and lung clearance index (LCI) have been reported in infants and children. This study investigated the impact in adults, and on additional important indices reflecting conductive (S cond) and acinar (S acin) ventilation heterogeneity, in health and disease. METHODS: Existing MBNW measurements of 27 healthy volunteers, 20 participants with asthma and 16 smokers were reanalysed using SPIROWARE V 3.3.1, which incorporates an error correction algorithm. Uncorrected and corrected indices were compared using paired t-tests and Bland-Altman plots. RESULTS: Correction of the sensor error significantly lowered FRC (mean difference 9%) and LCI (8-10%) across all three groups. S cond was higher following correction (11%, 14% and 36% in health, asthma and smokers, respectively) with significant proportional bias. S acin was significantly lower following correction in the asthma and smoker groups, but the effect was small (2-5%) and with no proportional bias. DISCUSSION: The O2 and CO2 cross-sensitivity sensor error significantly overestimated FRC and LCI in adults, consistent with data in infants and children. There was a high degree of underestimation of S cond but minimal impact on S acin. The presence of significant proportional bias indicates that previous studies will require reanalysis to confirm previous findings and to allow comparability with future studies.

Due to climate change, bushfires are becoming a more frequent and more severe phenomenon which contributes to poor health effects associated with air pollution. In pregnancy, environmental exposures can have lifelong consequences for the fetus, but little is known about these consequences in the context of bushfire smoke exposure. In this review we summarise the current knowledge in this area, and propose a potential mechanism linking bushfire smoke exposure in utero to poor perinatal and respiratory outcomes in the offspring. Bushfire smoke exposure is associated with poor pregnancy outcomes including reduced birth weight and an increased risk of prematurity. Some publications have outlined the adverse health effects on young children, particularly in relation to emergency department presentations and hospital admissions for respiratory problems, but there are no studies in children who were exposed to bushfire smoke in utero. Prenatal stress is likely to occur as a result of catastrophic bushfire events, and stress is known to be associated with poor perinatal and respiratory outcomes. Changes to DNA methylation are potential epigenetic mechanisms linking both smoke particulate exposure and prenatal stress to poor childhood respiratory health outcomes. More research is needed in large pregnancy cohorts exposed to bushfire events to explore this further, and to design appropriate mitigation interventions, in this area of global public health importance.

Objective: Offspring born to mothers with asthma in pregnancy are known to have lower lung function which tracks with age. Human group 2 innate lymphoid cells (ILC2) accumulate in foetal lungs, at 10-fold higher levels compared to adult lungs. However, there are no data on foetal ILC2 numbers and the association with respiratory health outcomes such as lung function in early life. We aimed to investigate cord blood immune cell populations from babies born to mothers with asthma in pregnancy. Methods: Cord blood from babies born to asthmatic mothers was collected, and cells were stained in whole cord blood. Analyses were done using traditional gating approaches and computational methodologies (t-distributed stochastic neighbour embedding and PhenoGraph algorithms). At 6 weeks of age, the time to peak tidal expiratory flow as a percentage of total expiratory flow time (tPTEF/tE%) was determined as well as Lung Clearance Index (LCI), during quiet natural sleep. Results: Of 110 eligible infants (March 2017 to November 2019), 91 were successfully immunophenotyped (82.7%). Lung function was attempted in 61 infants (67.0%), and 43 of those infants (70.5% of attempted) had technically acceptable tPTEF/tE% measurements. Thirty-four infants (55.7% of attempted) had acceptable LCI measurements. Foetal ILC2 numbers with increased expression of chemoattractant receptor-homologous molecule (CRTh2), characterised by two distinct analysis methodologies, were associated with poorer infant lung function at 6 weeks of age.”. Conclusion: Foetal immune responses may be a surrogate variable for or directly influence lung function outcomes in early life.

Objective: Offspring born to mothers with asthma in pregnancy are known to have lower lung function which tracks with age. Human group 2 innate lymphoid cells (ILC2) accumulate in foetal lungs, at 10-fold higher levels compared to adult lungs. However, there are no data on foetal ILC2 numbers and the association with respiratory health outcomes such as lung function in early life. We aimed to investigate cord blood immune cell populations from babies born to mothers with asthma in pregnancy. Methods: Cord blood from babies born to asthmatic mothers was collected, and cells were stained in whole cord blood. Analyses were done using traditional gating approaches and computational methodologies (t-distributed stochastic neighbour embedding and PhenoGraph algorithms). At 6 weeks of age, the time to peak tidal expiratory flow as a percentage of total expiratory flow time (tPTEF/tE%) was determined as well as Lung Clearance Index (LCI), during quiet natural sleep. Results: Of 110 eligible infants (March 2017 to November 2019), 91 were successfully immunophenotyped (82.7%). Lung function was attempted in 61 infants (67.0%), and 43 of those infants (70.5% of attempted) had technically acceptable tPTEF/tE% measurements. Thirty-four infants (55.7% of attempted) had acceptable LCI measurements. Foetal ILC2 numbers with increased expression of chemoattractant receptor-homologous molecule (CRTh2), characterised by two distinct analysis methodologies, were associated with poorer infant lung function at 6 weeks of age." Conclusion: Foetal immune responses may be a surrogate variable for or directly influence lung function outcomes in early life.

Current cystic fibrosis (CF) treatment strategies are primarily focused on oral/inhaled anti-inflammatories and antibiotics, resulting in a considerable treatment burden for CF patients. Therefore, combination treatments consisting of anti-inflammatories with antibiotics could reduce the CF treatment burden. However, there is an imperative need to understand the potential drug-drug interactions of these combination treatments to determine their efficacy. Thus, this study aimed to determine the interactions of the anti-inflammatory agent Ibuprofen with each of the CF-approved inhaled antibiotics (Tobramycin, Colistin and its prodrug colistimethate sodium/Tadim) and anti-bacterial and anti-inflammatory efficacy. Chemical interactions of the Ibuprofen:antibiotic combinations were elucidated using High-Resolution Mass-Spectrometry (HRMS) and 1H NMR. HRMS showed pairing of Ibuprofen and Tobramycin, further confirmed by 1H NMR whilst no pairing was observed for either Ibuprofen:Colistin or Ibuprofen:Tadim combinations. The anti-bacterial activity of the combinations against Pseudomonas aeruginosa showed that neither paired nor non-paired Ibuprofen:antibiotic therapies altered the anti-bacterial activity. The anti-inflammatory efficacy of the combination therapies was next determined at two different concentrations (Low and High) using in vitro models of NuLi-1 (healthy) and CuFi-1 (CF) cell lines. Differential response in the anti-inflammatory efficacy of Ibuprofen:Tobramycin combination was observed between the two concentrations due to changes in the structural conformation of the paired Ibuprofen:Tobramycin complex at High concentration, confirmed by 1H NMR. In contrast, the non-pairing of the Ibuprofen:Colistin and Ibuprofen:Tadim combinations showed a significant decrease in IL-8 secretion at both the concentrations. Importantly, all antibiotics alone showed anti-inflammatory properties, highlighting the inherent anti-inflammatory properties of these antibiotics.

The lack of comparability in indices of ventilation heterogeneity between free- and controlled-breathing MBNW protocols is confirmed in asthma https://bit.ly/3lmri4A.

The lack of comparability in indices of ventilation heterogeneity between free- and controlled-breathing MBNW protocols is confirmed in asthma https://bit.ly/3lmri4A.

Objective: Offspring born to mothers with asthma in pregnancy are known to have lower lung function which tracks with age. Human group 2 innate lymphoid cells (ILC2) accumulate in foetal lungs, at 10-fold higher levels compared to adult lungs. However, there are no data on foetal ILC2 numbers and the association with respiratory health outcomes such as lung function in early life. We aimed to investigate cord blood immune cell populations from babies born to mothers with asthma in pregnancy. Methods: Cord blood from babies born to asthmatic mothers was collected, and cells were stained in whole cord blood. Analyses were done using traditional gating approaches and computational methodologies (t-distributed stochastic neighbour embedding and PhenoGraph algorithms). At 6 weeks of age, the time to peak tidal expiratory flow as a percentage of total expiratory flow time (tPTEF/tE%) was determined as well as Lung Clearance Index (LCI), during quiet natural sleep. Results: Of 110 eligible infants (March 2017 to November 2019), 91 were successfully immunophenotyped (82.7%). Lung function was attempted in 61 infants (67.0%), and 43 of those infants (70.5% of attempted) had technically acceptable tPTEF/tE% measurements. Thirty-four infants (55.7% of attempted) had acceptable LCI measurements. Foetal ILC2 numbers with increased expression of chemoattractant receptor-homologous molecule (CRTh2), characterised by two distinct analysis methodologies, were associated with poorer infant lung function at 6 weeks of age." Conclusion: Foetal immune responses may be a surrogate variable for or directly influence lung function outcomes in early life.

Despite ototoxicity being a prevalent consequence of cisplatin chemotherapy, little guidance exists on interventions to prevent this permanent and progressive adverse event. To develop a clinical practice guideline for the prevention of cisplatin-induced ototoxicity in children and adolescents with cancer, we convened an international, multidisciplinary panel of experts and patient advocates to update a systematic review of randomised trials for the prevention of cisplatin-induced ototoxicity. The systematic review identified 27 eligible adult and paediatric trials that evaluated amifostine, sodium diethyldithiocarbamate or disulfiram, systemic sodium thiosulfate, intratympanic therapies, and cisplatin infusion duration. Regarding systemic sodium thiosulfate, the panel made a strong recommendation for administration in non-metastatic hepatoblastoma, a weak recommendation for administration in other non-metastatic cancers, and a weak recommendation against its routine use in metastatic cancers. Amifostine, sodium diethyldithiocarbamate, and intratympanic therapy should not be routinely used. Cisplatin infusion duration should not be altered as a means to reduce ototoxicity. Further research to determine the safety of sodium thiosulfate in patients with metastatic cancer is encouraged.

PURPOSE: To develop a clinical practice guideline for systemic antifungal prophylaxis in pediatric patients with cancer and hematopoietic stem-cell transplantation (HSCT) recipients. METHODS: Recommendations were developed by an international multidisciplinary panel that included a patient advocate. We conducted a systematic review of systemic antifungal prophylaxis in children and adults with cancer and HSCT recipients. The Grading of Recommendations Assessment, Development, and Evaluation approach was used to make strong or weak recommendations and to classify level of evidence as high, moderate, low, or very low. The panel considered directness of the data to pediatric patients. RESULTS: There were 68 randomized trials included in the systematic review, of which 6 (9%) were conducted in a solely pediatric population. Strong recommendations were made to administer systemic antifungal prophylaxis to children and adolescents receiving treatment of acute myeloid leukemia, to those undergoing allogeneic HSCT pre-engraftment, and to those receiving systemic immunosuppression for graft-versus-host disease treatment. A strong recommendation was made to administer a mold-active agent with an echinocandin or a mold-active azole when systemic antifungal prophylaxis is warranted. For children younger than 13 years of age, an echinocandin, voriconazole, or itraconazole is suggested. Posaconazole may also be used in those age 13 years or older. A strong recommendation against routine administration of amphotericin as systemic antifungal prophylaxis was made. CONCLUSION: We developed a clinical practice guideline for systemic antifungal prophylaxis administration in pediatric patients with cancer and HSCT recipients. Implementation and assessment of guideline-concordant rates and impacts are important future steps.

BACKGROUND: Bacteremia and other invasive bacterial infections are common among children with cancer receiving intensive chemotherapy and in pediatric recipients of hematopoietic stem cell transplantation (HSCT). Systemic antibacterial prophylaxis is one approach that can be used to reduce the risk of these infections. Our purpose was to develop a clinical practice guideline (CPG) for systemic antibacterial prophylaxis administration in pediatric patients with cancer and those undergoing HSCT. METHODS: An international and multidisciplinary panel was convened with representation from pediatric hematology/oncology and HSCT, pediatric infectious diseases (including antibiotic stewardship), nursing, pharmacy, a patient advocate, and a CPG methodologist. The panel used the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) approach to generate recommendations based on the results of a systematic review of the literature. RESULTS: The systematic review identified 114 eligible randomized trials of antibiotic prophylaxis. The panel made a weak recommendation for systemic antibacterial prophylaxis for children receiving intensive chemotherapy for acute myeloid leukemia and relapsed acute lymphoblastic leukemia (ALL). Weak recommendations against the routine use of systemic antibacterial prophylaxis were made for children undergoing induction chemotherapy for ALL, autologous HSCT and allogeneic HSCT. A strong recommendation against its routine use was made for children whose therapy is not expected to result in prolonged severe neutropenia. If used, prophylaxis with levofloxacin was recommended during severe neutropenia. CONCLUSIONS: We present a CPG for systemic antibacterial prophylaxis administration in pediatric cancer and HSCT patients. Future research should evaluate the long-term effectiveness and adverse effects of prophylaxis.

Asthma and COPD make up the majority of obstructive airways diseases (OADs), which affects ∼11% of the population. The main drugs used to treat OADs have not changed in the past five decades, with advancements mainly comprising variations on existing treatments. The recent biologics are beneficial to only specific subsets of patients. Part of this may lie in our inability to adequately characterise the tremendous heterogeneity in every aspect of OAD. The field is currently moving towards the concept of personalised medicine, based on a focus on treatable traits that are objective, measurable and modifiable. We propose extending this concept via the use of emerging clinical tools for comprehensive physiological phenotyping. We describe, based on published data, the evidence for the use of functional imaging, gas washout techniques and oscillometry, as well as potential future applications, to more comprehensively assess and predict treatment response in OADs. In this way, we hope to demonstrate how physiological phenotyping tools will improve the way in which drugs are prescribed, but most importantly, will facilitate development of new drugs for OADs.

Asthma and COPD make up the majority of obstructive airways diseases (OADs), which affects ∼11% of the population. The main drugs used to treat OADs have not changed in the past five decades, with advancements mainly comprising variations on existing treatments. The recent biologics are beneficial to only specific subsets of patients. Part of this may lie in our inability to adequately characterise the tremendous heterogeneity in every aspect of OAD. The field is currently moving towards the concept of personalised medicine, based on a focus on treatable traits that are objective, measurable and modifiable. We propose extending this concept via the use of emerging clinical tools for comprehensive physiological phenotyping. We describe, based on published data, the evidence for the use of functional imaging, gas washout techniques and oscillometry, as well as potential future applications, to more comprehensively assess and predict treatment response in OADs. In this way, we hope to demonstrate how physiological phenotyping tools will improve the way in which drugs are prescribed, but most importantly, will facilitate development of new drugs for OADs.

Background: Respiratory viruses are a common cause of infection in immunosuppressed children undergoing cancer therapy. Pulmonary sequelae have been documented following respiratory viral infections (RVIs) in hematopoietic stem cell transplant (HSCT) recipients; however potential late effects in children undergoing nonmyeloablative chemotherapy have not been investigated. Aim: To evaluate the long-term pulmonary morbidity of respiratory viral infections during chemotherapy in children with acute lymphoblastic leukemia (ALL). Methods: Childhood ALL survivors, aged 7 to 18 years, greater than 6 months posttreatment were recruited. Exclusion criteria included HSCT or proven bacterial/fungal respiratory infection during treatment. Subjects were classified into “viral” or “control” groups according to retrospective medical records that documented the presence of laboratory-proven RVIs during chemotherapy. Symptom questionnaires (Liverpool, ISAAC) and lung function testing (spirometry, plethysmography, diffusing capacity, forced oscillation technique to ATS/ERS standards) were then performed cross-sectionally at the time of recruitment. Results: Fifty-four patients (31 viral, 23 control) were recruited: median (range) age 11.2 (7.2-18.1) years, and at 4.9 (0.5-13) years posttherapy. Abnormalities were detected in 17 (31%) individuals (8 viral, 9 control), with the most common being DLCO impairment (3 viral, 4 control) and reduced respiratory reactance at 5 Hz (5 viral, 6 control). Children with RVIs during chemotherapy reported more current respiratory symptoms, particularly wheeze (odds ratio [OR], 3.0; 95% confidence interval [CI]: 0.9-10.0; P =.09) and cough (OR, 2.7; 95% CI: 0.8-9.5; P =.11). No differences in lung function tests were observed between the two groups. Conclusions: Our study found children with RVIs during chemotherapy developed more long-term respiratory symptoms than controls; however, differences did not reach statistical significance. No differences

PURPOSE: The aim of this work was to develop a clinical practice guideline for the prevention and treatment of Clostridium difficile infection (CDI) in children and adolescents with cancer and pediatric hematopoietic stem-cell transplantation (HSCT) patients. METHODS: An international multidisciplinary panel of experts in pediatric oncology and infectious diseases with patient advocate representation was convened. We performed systematic reviews of randomized controlled trials for the prevention or treatment of CDI in any population and considered the directness of the evidence to children with cancer and pediatric HSCT patients. We used the Grading of Recommendations Assessment, Development, and Evaluation approach to generate recommendations. RESULTS: The panel made strong recommendations to administer either oral metronidazole or oral vancomycin for the initial treatment of nonsevere CDI and oral vancomycin for the initial treatment of severe CDI. Fidaxomicin may be considered in the setting of recurrent CDI. The panel suggested that probiotics not be routinely used for the prevention of CDI, and that monoclonal antibodies and probiotics not be routinely used for the treatment of CDI. A strong recommendation to not use fecal microbiota transplantation was made in this population. We identified key knowledge gaps and suggested directions for future research. CONCLUSION: We present a guideline for the prevention and treatment of CDI in children and adolescents with cancer and pediatric HSCT patients. Future research should include randomized controlled trials that involve children with cancer and pediatric HSCT patients to improve the management of CDI in this population.

© 2017 the American Physiological Society. The forced oscillation technique (FOT) can provide unique and clinically relevant lung function information with little cooperation with subjects. However, FOT has higher variability than spirometry, possibly because strategies for quality control and reducing artifacts in FOT measurements have yet to be standardized or validated. Many quality control procedures rely on either simple statistical filters or subjective evaluation by a human operator. In this study, we propose an automated artifact removal approach based on the resistance against flow profile, applied to complete breaths. We report results obtained from data recorded from children and adults, with and without asthma. Our proposed method has 76% agreement with a human operator for the adult data set and 79% for the pediatric data set. Furthermore, we assessed the variability of respiratory resistance measured by FOT using within-session variation (wCV) and between-session variation (bCV). In the asthmatic adults test data set, our method was again similar to that of the manual operator for wCV (6.5 vs. 6.9%) and significantly improved bCV (8.2 vs. 8.9%). Our combined automated breath removal approach based on advanced feature extraction offers better or equivalent quality control of FOT measurements compared with an expert operator and computationally more intensive methods in terms of accuracy and reducing intrasubject variability. NEW &NOTEWORTHY The forced oscillation technique (FOT) is gaining wider acceptance for clinical testing; however, strategies for quality control are still highly variable and require a high level of subjectivity. We propose an automated, complete breath approach for removal of respiratory artifacts from FOT measurements, using feature extraction and an interquartile range filter. Our approach offers better or equivalent performance compared with an expert operator, in terms of accuracy and reducing intrasubject variability.

© 2016 IEEE. Goal: Respiratory artefact removal for the forced oscillation technique can be treated as an anomaly detection problem. Manual removal is currently considered the gold standard, but this approach is laborious and subjective. Most existing automated techniques used simple statistics and/or rejected anomalous data points. Unfortunately, simple statistics are insensitive to numerous artefacts, leading to low reproducibility of results. Furthermore, rejecting anomalous data points causes an imbalance between the inspiratory and expiratory contributions. Methods: From a machine learning perspective, such methods are unsupervised and can be considered simple feature extraction. We hypothesize that supervised techniques can be used to find improved features that are more discriminative and more highly correlated with the desired output. Features thus found are then used for anomaly detection by applying quartile thresholding, which rejects complete breaths if one of its features is out of range. The thresholds are determined by both saliency and performance metrics rather than qualitative assumptions as in previous works. Results: Feature ranking indicates that our new landmark features are among the highest scoring candidates regardless of age across saliency criteria. F1-scores, receiver operating characteristic, and variability of the mean resistance metrics show that the proposed scheme outperforms previous simple feature extraction approaches. Our subject-independent detector, 1IQR-SU, demonstrated approval rates of 80.6% for adults and 98% for children, higher than existing methods. Conclusion: Our new features are more relevant. Our removal is objective and comparable to the manual method. Significance: This is a critical work to automate forced oscillation technique quality control.

A critical task in forced oscillation technique (FOT), a promising lung function test, is to remove respiratory artefacts. Manual removal by specialists is widely used but time-consuming and subjective. Most existing automated techniques have involved simple thresholding methods in an unsupervised manner. Breath cycles can be classified by a binary classification model (classes: artefactual and accepted). While attempting to use off-the-shelf sorting algorithms (e.g., one-class support vector machine, knearest neighbours, and adaptive boosting ensemble), we noticed their poor detection performance. This may result from the dependence of samples as found in physiological studies of the lung function that challenges the learning process. Specifically, statistics of breaths that we recorded may change from one to another patient and even within the same recording of a patient. We introduce an additional feature engineering step that is an intermediate module to decorrelate samples, called feature learning (using Wilcoxon signed rank tests). To that end, we collected FOT recordings from various groups of patients (paediatric and adult including healthy and asthmatics). Artefacts in this work were recorded naturally and processed in a complete-breath approach. Performance metrics include evaluations on preservation of “accepted” breaths in the filtered output (including F1- score, throughput, and approval rate). Our experiment found that our feature engineering steps significantly improve the artefact removal performance of all implemented classifiers especially with feature inputs selected by mutual information criterion.

© 2016 IEEE. A critical task in forced oscillation technique (FOT), a promising lung function test, is to remove respiratory artefacts. Manual removal by specialists is widely used but time- consuming and subjective. Most existing automated techniques have involved simple thresholding methods in an unsupervised manner. Breath cycles can be classified by a binary classification model (classes: artefactual and accepted). While attempting to use off-the-shelf sorting algorithms (e.g., one-class support vector machine, knearest neighbours, and adaptive boosting ensemble), we noticed their poor detection performance. This may result from the dependence of samples as found in physiological studies of the lung function that challenges the learning process. Specifically, statistics of breaths that we recorded may change from one to another patient and even within the same recording of a patient. We introduce an additional feature engineering step that is an intermediate module to decorrelate samples, called feature learning (using Wilcoxon signed rank tests). To that end, we collected FOT recordings from various groups of patients (paediatric and adult including healthy and asthmatics). Artefacts in this work were recorded naturally and processed in a complete-breath approach. Performance metrics include evaluations on preservation of "accepted" breaths in the filtered output (including F1- score, throughput, and approval rate). Our experiment found that our feature engineering steps significantly improve the artefact removal performance of all implemented classifiers especially with feature inputs selected by mutual information criterion.

© 2016 IEEE. A critical task in forced oscillation technique (FOT), a promising lung function test, is to remove respiratory artefacts. Manual removal by specialists is widely used but time- consuming and subjective. Most existing automated techniques have involved simple thresholding methods in an unsupervised manner. Breath cycles can be classified by a binary classification model (classes: artefactual and accepted). While attempting to use off-the-shelf sorting algorithms (e.g., one-class support vector machine, knearest neighbours, and adaptive boosting ensemble), we noticed their poor detection performance. This may result from the dependence of samples as found in physiological studies of the lung function that challenges the learning process. Specifically, statistics of breaths that we recorded may change from one to another patient and even within the same recording of a patient. We introduce an additional feature engineering step that is an intermediate module to decorrelate samples, called feature learning (using Wilcoxon signed rank tests). To that end, we collected FOT recordings from various groups of patients (paediatric and adult including healthy and asthmatics). Artefacts in this work were recorded naturally and processed in a complete-breath approach. Performance metrics include evaluations on preservation of "accepted" breaths in the filtered output (including F1- score, throughput, and approval rate). Our experiment found that our feature engineering steps significantly improve the artefact removal performance of all implemented classifiers especially with feature inputs selected by mutual information criterion.

A critical task in forced oscillation technique (FOT), a promising lung function test, is to remove respiratory artefacts. Manual removal by specialists is widely used but time-consuming and subjective. Most existing automated techniques have involved simple thresholding methods in an unsupervised manner. Breath cycles can be classified by a binary classification model (classes: artefactual and accepted). While attempting to use off-the-shelf sorting algorithms (e.g., one-class support vector machine, knearest neighbours, and adaptive boosting ensemble), we noticed their poor detection performance. This may result from the dependence of samples as found in physiological studies of the lung function that challenges the learning process. Specifically, statistics of breaths that we recorded may change from one to another patient and even within the same recording of a patient. We introduce an additional feature engineering step that is an intermediate module to decorrelate samples, called feature learning (using Wilcoxon signed rank tests). To that end, we collected FOT recordings from various groups of patients (paediatric and adult including healthy and asthmatics). Artefacts in this work were recorded naturally and processed in a complete-breath approach. Performance metrics include evaluations on preservation of “accepted” breaths in the filtered output (including F1- score, throughput, and approval rate). Our experiment found that our feature engineering steps significantly improve the artefact removal performance of all implemented classifiers especially with feature inputs selected by mutual information criterion.