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.

Clinical significance and applications of oscillometry.

Recently, "Technical standards for respiratory oscillometry" was published, which reviewed the physiological basis of oscillometric measures and detailed the technical factors related to equipment and test performance, quality assurance and reporting of results. Here we present a review of the clinical significance and applications of oscillometry. We briefly review the physiological principles of oscillometry and the basics of oscillometry interpretation, and then describe what is currently known about oscillometry in its role as a sensitive measure of airway resistance, bronchodilator responsiveness and bronchial challenge testing, and response to medical therapy, particularly in asthma and COPD. The technique may have unique advantages in situations where spirometry and other lung function tests are not suitable, such as in infants, neuromuscular disease, sleep apnoea and critical care. Other potential applications include detection of bronchiolitis obliterans, vocal cord dysfunction and the effects of environmental exposures. However, despite great promise as a useful clinical tool, we identify a number of areas in which more evidence of clinical utility is needed before oscillometry becomes routinely used for diagnosing or monitoring respiratory disease.

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.

Technical standards for respiratory oscillometry.

Oscillometry (also known as the forced oscillation technique) measures the mechanical properties of the respiratory system (upper and intrathoracic airways, lung tissue and chest wall) during quiet tidal breathing, by the application of an oscillating pressure signal (input or forcing signal), most commonly at the mouth. With increased clinical and research use, it is critical that all technical details of the hardware design, signal processing and analyses, and testing protocols are transparent and clearly reported to allow standardisation, comparison and replication of clinical and research studies. Because of this need, an update of the 2003 European Respiratory Society (ERS) technical standards document was produced by an ERS task force of experts who are active in clinical oscillometry research.The aim of the task force was to provide technical recommendations regarding oscillometry measurement including hardware, software, testing protocols and quality control.The main changes in this update, compared with the 2003 ERS task force document are 1) new quality control procedures which reflect use of "within-breath" analysis, and methods of handling artefacts; 2) recommendation to disclose signal processing, quality control, artefact handling and breathing protocols (e.g. number and duration of acquisitions) in reports and publications to allow comparability and replication between devices and laboratories; 3) a summary review of new data to support threshold values for bronchodilator and bronchial challenge tests; and 4) updated list of predicted impedance values in adults and children.

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.

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.

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.

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.

Forced oscillations and respiratory system modeling in adults with cystic fibrosis.

BACKGROUND: The Forced Oscillation Technique (FOT) has the potential to increase our knowledge about the biomechanical changes that occur in Cystic Fibrosis (CF). Thus, the aims of this study were to investigate changes in the resistive and reactive properties of the respiratory systems of adults with CF. METHODS: The study was conducted in a group of 27 adults with CF over 18 years old and a control group of 23 healthy individuals, both of which were assessed by the FOT, plethysmography and spirometry. An equivalent electrical circuit model was also used to quantify biomechanical changes and to gain physiological insight. RESULTS AND DISCUSSION: The CF adults presented an increased total respiratory resistance (p < 0.0001), increased resistance curve slope (p<0.0006) and reduced dynamic compliance (p<0.0001). In close agreement with the physiology of CF, the model analysis showed increased peripheral resistance (p<0.0005) and reduced compliance (p < 0.0004) and inertance (p<0.005). Significant reasonable to good correlations were observed between the resistive parameters and spirometric and plethysmographic indexes. Similar associations were observed for the reactive parameters. Peripheral resistance, obtained by the model analysis, presented reasonable (R=0.35) to good (R=0.64) relationships with plethysmographic parameters. CONCLUSIONS: The FOT adequately assessed the biomechanical changes associated with CF. The model used provides sensitive indicators of lung function and has the capacity to differentiate between obstructed and non-obstructed airway conditions. The FOT shows great potential for the clinical assessment of respiratory mechanics in adults with CF.

Machine learning algorithms and forced oscillation measurements to categorise the airway obstruction severity in chronic obstructive pulmonary disease.

The purpose of this study was to develop automatic classifiers to simplify the clinical use and increase the accuracy of the forced oscillation technique (FOT) in the categorisation of airway obstruction level in patients with chronic obstructive pulmonary disease (COPD). The data consisted of FOT parameters obtained from 168 volunteers (42 healthy and 126 COPD subjects with four different levels of obstruction). The first part of this study showed that FOT parameters do not provide adequate accuracy in identifying COPD subjects in the first levels of obstruction, as well as in discriminating between close levels of obstruction. In the second part of this study, different supervised machine learning (ML) techniques were investigated, including k-nearest neighbour (KNN), random forest (RF) and support vector machines with linear (SVML) and radial basis function kernels (SVMR). These algorithms were applied only in situations where high categorisation accuracy [area under the Receiver Operating Characteristic curve (AUC)≥0.9] was not achieved with the FOT parameter alone. It was observed that KNN and RF classifiers improved categorisation accuracy. Notably, in four of the six cases studied, an AUC≥0.9 was achieved. Even in situations where an AUC≥0.9 was not achieved, there was a significant improvement in categorisation performance (AUC≥0.83). In conclusion, machine learning classifiers can help in the categorisation of COPD airway obstruction. They can assist clinicians in tracking disease progression, evaluating the risk of future disease exacerbations and guiding therapy.

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

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.

Machine learning algorithms and forced oscillation measurements applied to the automatic identification of chronic obstructive pulmonary disease.

The purpose of this study is to develop a clinical decision support system based on machine learning (ML) algorithms to help the diagnostic of chronic obstructive pulmonary disease (COPD) using forced oscillation (FO) measurements. To this end, the performances of classification algorithms based on Linear Bayes Normal Classifier, K nearest neighbor (KNN), decision trees, artificial neural networks (ANN) and support vector machines (SVM) were compared in order to the search for the best classifier. Four feature selection methods were also used in order to identify a reduced set of the most relevant parameters. The available dataset consists of 7 possible input features (FO parameters) of 150 measurements made in 50 volunteers (COPD, n = 25; healthy, n = 25). The performance of the classifiers and reduced data sets were evaluated by the determination of sensitivity (Se), specificity (Sp) and area under the ROC curve (AUC). Among the studied classifiers, KNN, SVM and ANN classifiers were the most adequate, reaching values that allow a very accurate clinical diagnosis (Se > 87%, Sp > 94%, and AUC > 0.95). The use of the analysis of correlation as a ranking index of the FOT parameters, allowed us to simplify the analysis of the FOT parameters, while still maintaining a high degree of accuracy. In conclusion, the results of this study indicate that the proposed classifiers may contribute to easy the diagnostic of COPD by using forced oscillation measurements.

Airflow pattern complexity and airway obstruction in asthma.

The scientific and clinical value of a measure of complexity is potentially enormous because complexity appears to be lost in the presence of illness. The authors examined the effect of elevated airway obstruction on the complexity of the airflow (Q) pattern of asthmatic patients analyzing the airflow approximate entropy (ApEnQ). This study involved 11 healthy controls, 11 asthmatics with normal spirometric exams, and 40 asthmatics with mild (14), moderate (14), and severe (12) airway obstructions. A significant (P < 0.02) reduction in the ApEnQ was observed in the asthmatic patients. This reduction was significantly correlated with spirometric indexes of airway obstruction [FEV(1) (%): R = 0.31, P = 0.013] and the total respiratory impedance (R = -0.39; P < 0.002). These results are in close agreement with pathophysiological fundamentals and suggest that the airflow pattern becomes less complex in asthmatic patients, which may reduce the adaptability of the respiratory system to perform the exercise that is associated with daily life activities. This analysis was able to identify respiratory changes in patients with mild obstruction with an adequate accuracy (83%). Higher accuracies were obtained in patients with moderate and severe obstructions. The analysis of airflow pattern complexity by the ApEnQ was able to provide new information concerning the changes associated with asthma. In addition, this analysis was also able to contribute to the detection of the adverse effects of asthma. Because these measurements are easy to perform, such a technique may represent an alternative and/or a complement to other conventional exams to help the clinical evaluations of asthmatic patients.

A telemedicine instrument for remote evaluation of tremor: design and initial applications in fatigue and patients with Parkinson's disease.

INTRODUCTION: A novel system that combines a compact mobile instrument and Internet communications is presented in this paper for remote evaluation of tremors. The system presents a high potential application in Parkinson's disease and connects to the Internet through a TCP/IP protocol. Tremor transduction is carried out by accelerometers, and the data processing, presentation and storage were obtained by a virtual instrument. The system supplies the peak frequency (fp), the amplitude (Afp) and power in this frequency (Pfp), the total power (Ptot), and the power in low (1-4 Hz) and high (4-7 Hz) frequencies (Plf and Phf, respectively). METHODS: The ability of the proposed system to detect abnormal tremors was initially demonstrated by a fatigue study in normal subjects. In close agreement with physiological fundamentals, the presence of fatigue increased fp, Afp, Pfp and Pt (p < 0.05), while the removal of fatigue reduced all the mentioned parameters (p < 0.05). The system was also evaluated in a preliminary in vivo test in parkinsonian patients. Afp, Pfp, Ptot, Plf and Phf were the most accurate parameters in the detection of the adverse effects of this disease (Se = 100%, Sp = 100%), followed by fp (Se = 100%, Sp = 80%). Tests for Internet transmission that realistically simulated clinical conditions revealed adequate acquisition and analysis of tremor signals and also revealed that the user could adequately receive medical recommendations. CONCLUSIONS: The proposed system can be used in a wide spectrum of telemedicine scenarios, enabling the home evaluation of tremor occurrence under specific medical treatments and contributing to reduce the costs of the assistance offered to these patients.

Swallowing detection by sonic and subsonic frequencies: a comparison.

The detection of swallowing events by acoustic means represents an important tool to assess and diagnose swallowing disorders as well as to objectively monitor ingestive behavior of individuals. Acoustic sensors used to register swallowing sounds may also capture sound artifacts arising from intrinsic speech and external noise affecting the detection. In this paper we tested if subsonic frequencies are less prone to artifacts from speech, chewing and other intrinsic sounds than sonic frequencies. A simple method using a throat and an ambient microphone was employed to compare the swallowing detection accuracy by acoustic signals acquired in the sonic (20-2500 Hz) and subsonic (≤ 5 Hz) ranges. Averaged recall values were higher than 85% for both ranges. However, averaged precision values of 50% for subsonic frequencies and of 42% for sonic frequencies were caused by a high number of false positives. These results indicated no significant difference between averaged precision values which may suggest that subsonic frequencies were not less prone to intrinsic sound artifacts than frequencies in the sonic range. Further examination with the addition of a signal classification layer is proposed as a future step to confirm this statement.

An internet-based system for home monitoring of respiratory muscle disorders.

Home telemonitoring is of great interest in respiratory medicine where large numbers of people have long term conditions. We developed a telemedicine instrument for home monitoring of patients with disturbed respiratory muscles. The instrument measures the maximum inspiratory pressure (Pimax), the inspiratory time constant (τ(i)) and connects to the Internet through TCP/IP protocol. The instrument was evaluated by means of a comparative analysis in 18 normal individuals and 15 COPD patients. In close agreement with the pathophysiology, a reduction in Pimax (p < 0.0001) and an increase in τ(i) (p < 0.001) was observed in COPD patients. We concluded that the developed system could be a useful tool for the evaluation of inspiratory muscle and for the implementation of telemedicine services, contributing to reduce the costs of the assistance offered to patients with respiratory diseases.

Automatic identification of Chronic Obstructive Pulmonary Disease Based on forced oscillation measurements and artificial neural networks.

The purpose of this study is to develop an automatic classifier based on Artificial Neural Networks (ANNs) to help the diagnostic of Chronic Obstructive Pulmonary Disease (COPD) using forced oscillation measurements (FOT). The classifier inputs are the parameters provided by the FOT and the output is the indication if the parameters indicate COPD or not. The available dataset consists of 7 possible input features (FOT parameters) of 90 measurements made in 30 volunteers. Two feature selection methods (the analysis of the linear correlation and forward search) were used in order to identify a reduced set of the most relevant parameters. Two different training strategies for the ANNs were used and the performance of resulting networks were evaluated by the determination of accuracy, sensitivity (Se), specificity (Sp) and AUC. The ANN classifiers presented high accuracy (Se > 0.9, Se > 0.9 and AUC > 0.9) both in the complete and the reduce sets of FOT parameters. This indicates that ANNs classifiers may contribute to easy the diagnostic of COPD using forced oscillation measurements.