Daniel Sánchez Morillo

An Accelerometer-Based Device for Sleep Apnea Screening

This paper presents a body-fixed-sensor-based approach to assess potential sleep apnea patients. A trial involving 15 patients at a sleep unit was undertaken. Vibration sounds were acquired from an accelerometer sensor fixed with a noninvasive mounting on the suprasternal notch of subjects resting in supine position. Respiratory, cardiac, and snoring components were extracted by means of digital signal processing techniques. Mainly, the following biomedical parameters used in new sleep apnea diagnosis strategies were calculated: heart rate, heart rate variability, sympathetic and parasympathetic activity, respiratory rate, snoring rate, pitch associated with snores, and airflow indirect quantification. These parameters were compared to those obtained by means of polysomnography and an accurate microphone. Results demonstrated the feasibility of implementing an accelerometry-based portable device as a simple and cost-effective solution for contributing to the screening of sleep apnea-hypopnea syndrome and other breathing disorders.

Computer-aided diagnosis of pneumonia in patients with chronic obstructive pulmonary disease

BACKGROUND Early diagnosis of pneumonia and discrimination between this disease and chronic obstructive pulmonary disease (COPD) exacerbations in patients with COPD are crucial for optimal clinical management and treatment. OBJECTIVES To examine the use of computerized analysis of respiratory sounds, a hybrid system based on principal component analysis (PCA) and probabilistic neural networks (PNNs), to aid the detection of coexisting pneumonia in patients with COPD. METHODS AND MATERIALS A convenience sample of 58 patients with COPD (25 patients hospitalized for community-acquired pneumonia and 33 owing to acute exacerbation of COPD) was studied. Auscultations were performed by the patients themselves on their suprasternal notch. Short-time Fourier transform analysis was used to extract features from the recorded respiratory sounds, PCA was selected for dimensionality reduction and a PNN was trained as classifier. 10-Fold cross-validation and receiver operating characteristic curve analysis were used to estimate the system performance. RESULTS Based on the cross-validation results, a sensitivity and a specificity of 72% and 81.8%, respectively, were achieved in validation data. The operating point was selected to maximize the specificity and sensitivity pair in the training set. DISCUSSION The results strongly suggest that electronic self-auscultation at a single location (suprasternal notch) can support diagnosis of pneumonia in patients with COPD. CONCLUSIONS A simple, cost-effective method has been proposed to aid decision-making in areas with no radiological facilities available and in resource-constrained settings, and could have a great diagnostic impact on telemedicine applications.

Computerized analysis of respiratory sounds during COPD exacerbations

Acute exacerbation of chronic obstructive pulmonary disease (AECOPD) is a major event in the natural course of the disease, and is associated with significant mortality and socioeconomic impact. Abnormal respiratory sounds are commonly present in patients with AECOPD. Computerized analysis of these sounds can assist in diagnosis and in evaluation during follow-up. Exploratory data analysis methods were applied to respiratory sounds in these patients when they were hospitalized because of exacerbation. Two different patterns of presentation and evolution of respiratory sounds in AECOPD were found and described from the method of computerized respiratory sound analysis and unsupervised clustering that was devised. Based on the findings of the study, remote monitoring of respiratory sounds may be useful for the detection and/or follow-up of COPD exacerbation.

Mapping the Human Body for Vibrations using an Accelerometer

In this paper, an accelerometer is used to measure the vibration of the neck and thorax, in order to detect important signals that can be used in the diagnosis of sleep apnoea. Accelerations produced by the heart signals, the breathing movement and the snoring sounds are detected by an accelerometer attached to the skin. Mean power levels of the signal in different frequency bands are used to map the surface of the neck and thorax, where the accelerometer has been positioned in 15 different locations. A program in Matlab is used to fit this surface plot. Getting an adequate location for the accelerometer is a clear help to the diagnosis of sleep apnea.

Poincaré analysis of an overnight arterial oxygen saturation signal applied to the diagnosis of sleep apnea hypopnea syndrome

The analysis of oxygen desaturations is a basic variable in polysomnographic studies for the diagnosis of sleep apnea. Several algorithms operating in the time domain already exist for sleep apnea detection via pulse oximetry, but in a disadvantageous way--they achieve either a high sensitivity or a high specificity. The aim of this study was to assess whether an alternative analysis of arterial oxygen saturation (SaO2) signals from overnight pulse oximetry could yield essential information on the diagnosis of sleep apnea hypopnea syndrome (SAHS). SaO2 signals from 117 subjects were analyzed. The population was divided into a learning dataset (70 patients) and a test set (47 patients). The learning set was used for tuning thresholds among the applied Poincaré quantitative descriptors. Results showed that the presence of apnea events in SAHS patients caused an increase in the SD1 Poincaré parameter. This conclusion was assessed prospectively using the test dataset. 90.9% sensitivity and 84.0% specificity were obtained in the test group. We conclude that Poincaré analysis could be useful in the study of SAHS, contributing to reduce the demand for polysomnographic studies in SAHS screening.

Automated frequency domain analysis of oxygen saturation as a screening tool for SAHS

Sleep apnea-hypopnea syndrome (SAHS) is significantly underdiagnosed and new screening systems are needed. The analysis of oxygen desaturation has been proposed as a screening method. However, when oxygen saturation (SpO(2)) is used as a standalone single channel device, algorithms working in time domain achieve either a high sensitivity or a high specificity, but not usually both. This limitation arises from the dependence of time-domain analysis on absolute SpO(2) values and the lack of standardized thresholds defined as pathological. The aim of this study is to assess the degree of concordance between SAHS screening using offline frequency domain processing of SpO(2) signals and the apnea-hypopnea index (AHI), and the diagnostic performance of such a new method. SpO(2) signals from 115 subjects were analyzed. Data were divided in a training data set (37) and a test set (78). Power spectral density was calculated and related to the desaturation index scored by physicians. A frequency desaturation index (FDI) was then estimated and its accuracy compared to the classical desaturation index and to the apnea-hypopnea index. The findings point to a high diagnostic agreement: the best sensitivity and specificity values obtained were 83.33% and 80.44%, respectively. Moreover, the proposed method does not rely on absolute SpO(2) values and is highly robust to artifacts.

Monitoring and Analysis of Cardio Respiratory and Snoring Signals by using an Accelerometer

In this paper we present a system based on a sensor of acceleration for acquisition and monitoring of diverse physiological signals, by extracting respiratory, cardiac and snoring components inside the main source. Digital signal processing techniques used frequently in Biomedical Engineering have been used. The acceleration produced by the cardiac signals, the respiratory movements and the vibrations generated by the snores are detected with help of an accelerometer placed on the skin of the subject in not invasive way. The presented device allows the monitoring of several biomedical parameters: heart rate (HR), heart rate variability (HRV), Sympathetic, parasympathetic and baroreflex activity, respiratory rhythms and their variations (bradypnea - tachypnea), snoring and abdominal-thoracic efforts. A simple and effective method and device [1] is provided for helping to the diagnosis of Sleep Apnea-Hypopnea Syndrome (SAHS) and other breathing disorders.

Radial-Basis-Function Based Prediction of COPD Exacerbations

Chronic Obstructive Pulmonary Disease (COPD) is a very serious progressive lung disease with a high socioeconomic impact and prevalence levels worldwide. Admissions for acute exacerbation of respiratory symptoms (AECOPD) have the highest proportion of economic and human cost. During a 6-months field trial in a group of 16 patients, a novel electronic questionnaire for the early detection of COPD exacerbations was evaluated. Data mining strategies were applied. A Radial Basis Function (RBF) network classifier was trained and validated and its accuracy in detecting AECOPD was assessed. 94% (31 out of 33) AECOPD were early detected. Sensitivity and specificity were 73.8% and 87.0% respectively and area under the ROC curve was 0.82. The system was able to early detect AECOPD with 5.3 ± 2.1 days prior to the day in which the patients required medical attention.

Automatic Classification of Respiratory Sounds Phenotypes in COPD Exacerbations

During the last few years, different COPD phenotypes are being defined. Despite being one of the basic characteristics of exacerbations, studies on changes and peculiarities of respiratory sounds during an exacerbation episode have been barely studied. A computerized analysis of respiratory sounds recorded in patients hospitalized because of acute respiratory symptoms was performed. It was aimed to be applied in the classification of COPD exacerbations only using the auscultation data registered after the admission. The analyzed exacerbations were classified into two categories according to the initial conditions and the evolution of the exacerbation in terms of its acoustic characteristics. Multi-parametric analysis using features extracted in the time-frequency domain was applied and a RBF network was trained and validated for classifying. Based on the cross-validation results, sensitivity of 78.4% and specificity of 81.3% were achieved. The proposed method could contribute to extend the knowledge of respiratory sounds during COPD exacerbations and to provide additional information of the disease as a basis for improving the impact on the patient.