Publications

Obstructive sleep apnea (OSA) is a prevalent disease, but most patients remain undiagnosed and untreated. Recently, mHealth tools are being proposed to screen OSA patients at home. In this work, we analyzed full-night audio signals recorded with a smartphone microphone. Our objective was to develop an automatic detector to identify silence events (apneas or hypopneas) and compare its performance to a commercial portable system for OSA diagnosis (ApneaLink™, ResMed). To do that, we acquired signals from three subjects with both systems simultaneously. A sleep specialist marked the events on smartphone and ApneaLink signals. The automatic detector we developed, based on the sample entropy, identified silence events similarly than manual annotation. Compared to ApneaLink, it was very sensitive to apneas (detecting 86.2%) and presented an 83.4% positive predictive value, but it missed about half the hypopnea episodes. This suggests that during some hypopneas the flow reduction is not reflected in sound. Nevertheless, our detector accurately recognizes silence events, which can provide valuable respiratory information related to the disease. These preliminary results show that mHealth devices and simple microphones are promising non-invasive tools for personalized sleep disorders management at home.

JTD Keywords: Detectors, Manuals, Sleep apnea, Microphones, Labeling, Hospitals

Home hospitalization (HH) is presented as a healthcare alternative capable of providing high standards of care when patients no longer need hospital facilities. Although HH seems to lower healthcare costs by shortening hospital stays and improving patient's quality of life, the lack of continuous observation at home may lead to complications in some patients. Since blood tests have been proven to provide relevant prognosis information in many diseases, this paper analyzes the impact of different sampling methods on the prediction of HH outcomes. After a first exploratory analysis, some variables extracted from routine blood tests performed at the moment of HH admission, such as hemoglobin, lymphocytes or creatinine, were found to unmask statistically significant differences between patients undergoing successful and unsucessful HH stays. Then, predictive models were built with these data, in order to identify unsuccessful cases eventually needing hospital facilities. However, since these hospital admissions during HH programs are rare, their identification through conventional machine-learning approaches is challenging. Thus, several sampling strategies designed to face class imbalance were herein overviewed and compared. Among the analyzed approaches, over-sampling strategies, such as ROSE (Random Over-Sampling Examples) and conventional random over-sampling, showed the best performances. Nevertheless, further improvements should be proposed in the future so as to better identify those patients not benefiting from HH.

JTD Keywords: Hospitals, Blood, Training, Standards, Diseases, Prognostics and health management

Changes in the left ventricle function produce alternans in the hemodynamic and electric behavior of the cardiovascular system. A total of 49 cardiomyopathy patients have been studied based on the blood pressure signal (BP), and were classified according to the left ventricular ejection fraction (LVEF) in low risk (LR: LVEF>35%, 17 patients) and high risk (HR: LVEF≤35, 32 patients) groups. We propose to characterize these patients using a linear and a nonlinear methods, based on the spectral estimation and the recurrence plot, respectively. From BP signal, we extracted each systolic time interval (STI), upward systolic slope (BPsl), and the difference between systolic and diastolic BP, defined as pulse pressure (PP). After, the best subset of parameters were obtained through the sequential feature selection (SFS) method. According to the results, the best classification was obtained using a combination of linear and nonlinear features from STI and PP parameters. For STI, the best combination was obtained considering the frequency peak and the diagonal structures of RP, with an area under the curve (AUC) of 79%. The same results were obtained when comparing PP values. Consequently, the use of combined linear and nonlinear parameters could improve the risk stratification of cardiomyopathy patients.

JTD Keywords: Feature extraction, Blood pressure, Heart rate, Estimation, Data mining, Covariance matrices, Hospitals

Aging population is a major concern that is reflected in the increase of chronic diseases. Heart Failure (HF) is one of the most common chronic diseases of elderly people that is punctuated with acute episodes, which result in hospitalization. The periodic modulation of the amplitude of the breathing pattern is proved to be one of the multiple symptoms of an acute episode, and thus, the features extracted from its characterization contribute in the improvement of the first diagnosis of the clinical practice. The main objective of this study is to evaluate if the features extracted from the breathing pattern along with common clinical variables are reliable enough to detect Periodic Breathing (PB). A dataset of 44 elderly patients containing clinical information and a short record of electrocardiogram and respiratory flow signal was used to train two machine learning classification methods: Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA). All the available clinical parameters within the dataset along with the parameters characterizing the respiratory pattern were used to classify the observations into two groups. SVM classification was optimized and performed using a = -8 and C = 10.04 giving an accuracy of 88.2 % sensitivity of 90 % and specificity of 85.7 % Similar results were achieved with LDA classifying with an accuracy of 82.4 %, a sensitivity of 81.8% and specificity of 83.3 % PB has been accurately detected using both classifiers.

JTD Keywords: Support vector machines, Feature extraction, Training, Senior citizens, Standards, Training data, Hospitals

One objective of mechanical ventilation is the recovery of spontaneous breathing as soon as possible. Remove the mechanical ventilation is sometimes more difficult that maintain it. This paper proposes the study of respiratory flow signal of patients on weaning trials process by autoregressive moving average model (ARMA), through the location of poles and zeros of the model. A total of 151 patients under extubation process (T-tube test) were analyzed: 91 patients with successful weaning (GS), 39 patients that failed to maintain spontaneous breathing and were reconnected (GF), and 21 patients extubated after the test but before 48 hours were reintubated (GR). The optimal model was obtained with order 8, and statistical significant differences were obtained considering the values of angles of the first four poles and the first zero. The best classification was obtained between GF and GR, with an accuracy of 75.3% on the mean value of the angle of the first pole.

JTD Keywords: Analytical models, Biological system modeling, Computational modeling, Estimation, Hospitals, Poles and zeros, Ventilation, Autoregressive moving average processes, Patient care, Patient monitoring, Pneumodynamics, Poles and zeros, Ventilation, ARMA model, T-tube test, Autoregressive moving average model, Extubation process, Mechanical ventilation, Optimal model, Patient classification, Respiratory flow signal, Roots, Spontaneous breathing, Weaning trials

Sleep in patients with Sleep Apnea-Hypopnea Syndrome (SAHS) is frequently interrupted with arousals. Increased amounts of arousals result in shortening total sleep time and repeated sleep-arousal change can result in sleep fragmentation. According to the American Sleep Disorders Association (ASDA) an arousal is a marker of sleep disruption representing a detrimental and harmful feature for sleep. The nature of arousals and its role on the regulation of the sleep process raises controversy and has sparked the debate in the last years. In this work, we analyzed and compared the EEG spectral content of respiratory and spontaneous arousals on a database of 45 SAHS subjects. A total of 3980 arousals (1996 respiratory and 1984 spontaneous) were analyzed. The results showed no differences between the spectral content of the two kinds of arousals. Our findings raise doubt as to whether these two kinds of arousals are truly triggered by different organic mechanisms. Furthermore, they may also challenge the current beliefs regarding the underestimation of the importance of spontaneous arousals and their contribution to sleep fragmentation in patients suffering from SAHS.

JTD Keywords: Adaptive filters, Correlation, Databases, Electroencephalography, Hospitals, Sleep apnea, Electroencephalography, Medical signal processing, Pneumodynamics, Sleep, EEG spectral content, Organic mechanism, Respiratory, Sleep apnea hypopnea syndrome, Sleep fragmentation, Spectral content, Spontaneous arousal