Login to your account

Username *
Password *
Remember Me

Blog With Right Sidebar

    Vous êtes ici :  
  1. Accueil
  2. Blog With Right Sidebar

An improved method of early diagnosis of smoking-induced respiratory changes using machine learning algorithms.

Related Articles

An improved method of early diagnosis of smoking-induced respiratory changes using machine learning algorithms.

Comput Methods Programs Biomed. 2013 Aug 17;

Authors: Amaral JL, Lopes AJ, Jansen JM, Faria AC, Melo PL

Abstract
The purpose of this study was to develop an automatic classifier to increase the accuracy of the forced oscillation technique (FOT) for diagnosing early respiratory abnormalities in smoking patients. The data consisted of FOT parameters obtained from 56 volunteers, 28 healthy and 28 smokers with low tobacco consumption. Many supervised learning techniques were investigated, including logistic linear classifiers, k nearest neighbor (KNN), neural networks and support vector machines (SVM). To evaluate performance, the ROC curve of the most accurate parameter was established as baseline. To determine the best input features and classifier parameters, we used genetic algorithms and a 10-fold cross-validation using the average area under the ROC curve (AUC). In the first experiment, the original FOT parameters were used as input. We observed a significant improvement in accuracy (KNN=0.89 and SVM=0.87) compared with the baseline (0.77). The second experiment performed a feature selection on the original FOT parameters. This selection did not cause any significant improvement in accuracy, but it was useful in identifying more adequate FOT parameters. In the third experiment, we performed a feature selection on the cross products of the FOT parameters. This selection resulted in a further increase in AUC (KNN=SVM=0.91), which allows for high diagnostic accuracy. In conclusion, machine learning classifiers can help identify early smoking-induced respiratory alterations. The use of FOT cross products and the search for the best features and classifier parameters can markedly improve the performance of machine learning classifiers.

PMID: 24001924 [PubMed - as supplied by publisher]

Usefulness of Colored 3D Imaging of Respiratory Impedance in Asthma.

Related Articles

Usefulness of Colored 3D Imaging of Respiratory Impedance in Asthma.

Allergy Asthma Immunol Res. 2013 Sep;5(5):322-8

Authors: Shirai T, Mori K, Mikamo M, Shishido Y, Akita T, Morita S, Asada K, Fujii M, Suda T, Chida K

Abstract
PURPOSE: Recently, the clinical application of the forced oscillation technique (FOT) has progressed with the spread of commercially available FOT devices, including the impulse oscillation system and MostGraph. We investigated the usefulness of color 3D imaging of respiratory impedance in asthma using MostGraph.
METHODS: Whole-breath and within-breath respiratory system resistance (Rrs) and reactance (Xrs) were measured in 78 patients with asthma. Color 3D images were classified into three patterns: the chronic obstructive pulmonary disease (COPD)-like pattern (high values of Rrs and Xrs with a marked respiratory cycle and frequency dependence), the asthma pattern (moderately high Rrs over the entire frequency and a respiratory cycle with slight Xrs changes), and a normal-like pattern (low Rrs and Xrs with few within-breath changes). The classification was performed by three researchers, who were unaware of the clinical information, and the clinical characteristics were compared among the three groups.
RESULTS: Color 3D imaging provided a COPD-like pattern in 25 patients, an asthma pattern in 39 patients, and a normal-like pattern in 14 patients. Patients with the COPD-like pattern were predominantly female with a higher body mass index, lower forced expiratory volume in 1 second (FEV1) and forced vital capacity (FVC), and higher Rrs and Xrs values (whole-breath and within-breath variation). Those with the normal pattern had higher FEV1 and FVC, and a lower single-breath nitrogen washout slope. There were no differences in asthma control or exhaled nitric oxide levels among the three groups.
CONCLUSIONS: These results suggest that color 3D imaging of respiratory impedance may show asthma phenotypes.

PMID: 24003390 [PubMed]

Information needs among patients with chronic obstructive pulmonary disease at their first hospital admission: priorities and correlates.

Related Articles

Information needs among patients with chronic obstructive pulmonary disease at their first hospital admission: priorities and correlates.

J Clin Nurs. 2013 Sep 5;

Authors: Guo SE, Huang CY, Hsu HT

Abstract
AIMS AND OBJECTIVES: To better understand chronic obstructive pulmonary disease patients' informational needs and associated factors using the Predisposing, Reinforcing and Enabling Causes in Educational Diagnosis and Evaluation model.
BACKGROUND: Despite the increase in the incidence of chronic obstructive pulmonary disease, little research has been carried out on the information needs from a patient perspective.
DESIGN: A cross-sectional, correlational design was used.
METHODS: A convenience sample of 107 subjects was recruited from four Taiwanese hospitals. Multiple regression analyses were conducted to identify the total informational needs and related factors.
RESULTS: Major findings were that (1) patients' top informational need was daily care, and (2) variables associated with the total information needs were younger age, greater health internal locus of control, less dyspnoea severity and greater social support.
CONCLUSIONS: Patients' perceived chronic obstructive pulmonary disease informational needs are not congruent with the information received from healthcare professionals.
RELEVANCE TO CLINICAL PRACTICE: Healthcare professionals need to be sensitive to the fact that treatment-related information was not the top priority of patients with chronic obstructive pulmonary disease. Healthcare professionals also need to target the special subpopulation of chronic obstructive pulmonary disease patients with greater total informational need to maximise educational impact.

PMID: 24004333 [PubMed - as supplied by publisher]

The combination of umeclidinium bromide and vilanterol in the management of chronic obstructive pulmonary disease: current evidence and future prospects.

The defining feature of chronic obstructive pulmonary disease (COPD) is progressive airflow limitation that causes air trapping and hyperinflation. The increasing hyperinflation results in dyspnea along with associated inability to engage in the activities of daily living.

The American Thoracic Society (ATS), European Respiratory Society (ERS) and Global Initiative for Chronic Obstructive Lung Disease (GOLD) treatment guidelines all place bronchodilators as the foundation of pharmacological management of COPD. In patients with moderate-to-very-severe respiratory impairment, adding regular treatment with one or more long-acting bronchodilators is recommended [long-acting β2-agonists (LABAs) or long-acting muscarinic antagonists (LAMAs)].

A growing body of evidence shows that LAMA and LABA co-administration is more effective than either drug class alone in managing stable COPD to improve lung function, symptoms and health status. Recently, new drug applications (NDAs) for a fixed-dose combination (FDC) of umeclidinium (UMEC), a LAMA, and vilanterol (VI), a LABA, at UMEC/VI doses of 125/25 and 62.5/25 µg have been submitted by sponsors to the US Food and Drug Administration (FDA) and to the European Medicines Agency (EMA). Thus, UMEC/VI has become the first FDC LAMA/LABA product that has reached a regulatory approval stage. Other LAMA/LABA once-daily combinations coming through development include FDCs of tiotropium and olodaterol, glycopyrronium and indacaterol, and twice-daily aclidinium and formoterol.

The aim of this review is to explore currently available data for once-daily UMEC/VI in the context of the evolving standards of COPD management.

Predictors of cardiovascular disease in asthma and chronic obstructive pulmonary disease.

Cardiovascular disease (CVD) is a common comorbidity in patients with chronic airway obstruction, and is associated with systemic inflammation and airway obstruction. The aim of this study was to evaluate the predictors of CVD in two different conditions causing chronic airway obstruction, asthma and COPD.

METHODS: Lung function tests, clinical and echocardiographic data were assessed in 229 consecutive patients, 100 with asthma and 129 with COPD. CVD was classified into: pressure overload (PO) and volume overload (VO). Sub-analysis of patients with ischemic heart disease (IHD) and pulmonary hypertension (PH) was also performed.

RESULTS: CVD was found in 185 patients (81%: 51% COPD and 30% asthmatics) and consisted of PO in 42% and of VO in 38% patients. COPD patients, as compared to asthmatics, had older age, more severe airway obstruction, higher prevalence of males, of smokers, and of CVD (91% vs 68%), either PO (46% vs 38%) or VO (45% vs 30%). CVD was associated with older age and more severe airway obstruction both in asthma and COPD. In the overall patients the predictive factors of CVD were age, COPD, and male sex; those of PO were COPD, BMI, VC, FEV1 and MEF50 and those of VO were age, VC and MEF50. In asthma, the predictors of CVD were VC, FEV1, FEV1 /VC%, and PaO2, those of PO were VC, FEV1 and FEV1 /VC%, while for VO there was no predictor. In COPD the predictors of CVD were age, GOLD class and sex, those of VO age, VC and MEF50, and that of PO was BMI. Sub-analysis showed that IHD was predicted by COPD, age, BMI and FEV1, while PH (found only in 25 COPD patients), was predicted by VO (present in 80% of the patients) and FEV1. In subjects aged 65 years or more the prevalence of CVD, PO and VO was similar in asthmatic and COPD patients, but COPD patients had higher prevalence of males, smokers, IHD, PH, lower FEV1 and higher CRP.

CONCLUSIONS: The results of this study indicate that cardiovascular diseases are frequent in patients with chronic obstructive disorders, particularly in COPD patients. The strongest predictors of CVD are age and airway obstruction. COPD patients have higher prevalence of ischemic heart disease and pulmonary hypertension. In the elderly the prevalence of PO and VO in asthma and COPD patients is similar.

Search

Search