Miguel Altuve

On-line apnea-bradycardia detection using hidden semi-Markov models

In this work, we propose a detection method that exploits not only the instantaneous values, but also the intrinsic dynamics of the RR series, for the detection of apnea-bradycardia episodes in preterm infants. A hidden semi-Markov model is proposed to represent and characterize the temporal evolution of observed RR series and different pre-processing methods of these series are investigated. This approach is quantitatively evaluated through synthetic and real signals, the latter being acquired in neonatal intensive care units (NICU). Compared to two conventional detectors used in NICU our best detector shows an improvement of around 13% in sensitivity and 7% in specificity. Furthermore, a reduced detection delay of approximately 3 seconds is obtained with respect to conventional detectors.

A New On-Line Electrocardiographic Records Database and Computer Routines for Data Analysis

Gathering experimental data to test computer methods developed during a research is a hard work. Nowadays, some databases have been stored online that can be freely downloaded, however there is not a wide range of databases yet and not all pathologies are covered. Researchers with low resources are in need of more data they can consult for free. To cope with this we present an on-line portal containing a compilation of ECG databases recorded over the last two decades for research purposes. The first version of this portal contains four databases of ECG records: ischemic cardiopathy (72 patients, 3-lead ECG each), ischemic preconditioning (20 patients, 3-lead ECG each), diabetes (51 patients, 8-lead ECG each) and metabolic syndrome (25 subjects, 12-lead ECG each). In addition, one computer program and three routines are provided in order to correctly read the signals, and two digital filters along with two ECG waves detectors are provided for further processing. This portal will be constantly growing, other ECG databases and signal processing software will be uploaded. With this project, we give the scientific community a resource to avoid hours of data collection and to develop free software.

Multivariate ECG analysis for apnoea–bradycardia detection and characterisation in preterm infants

An analysis of the information content of new features derived from the electrocardiogram of preterm infants is presented. Beat detection and segmentation methods, specifically adapted to this population through evolutionary algorithms, led to an improved sensitivity and positive predictive value. RR interval, R -wave amplitude and QRS duration time-series were extracted at rest ( T 1), before ( T 2), during ( T 3) and after ( T 4) apnoea-bradycardia episodes. Significant variations for T 1- T 2 vs. T 1- T 3 and T 1- T 3 vs. T 1- T 4 were observed. Results reveal changes in the R-wave amplitude and QRS duration at the onset and termination of apnoea-bradycardia episodes which could be useful for their detection and characterisation.

Analysis of the QRS complex for apnea-bradycardia characterization in preterm infants

This work presents an analysis of the information content of new features derived from the electrocardiogram (ECG) for the characterization of apnea-bradycardia events in preterm infants. Automatic beat detection and segmentation methods have been adapted to the ECG signals from preterm infants, through the application of two evolutionary algorithms. ECG data acquired from 32 preterm infants with persistent apnea-bradycardia have been used for quantitative evaluation. The adaptation procedure led to an improved sensitivity and positive predictive value, and a reduced jitter for the detection of the R-wave, QRS onset, QRS offset, and iso-electric level. Additionally, time series representing the RR interval, R-wave amplitude and QRS duration, were automatically extracted for periods at rest, before, during and after apnea-bradycardia episodes. Significant variations (p<0.05) were observed for all time-series when comparing the difference between values at rest versus values just before the bradycardia event, with the difference between values at rest versus values during the bradycardia event. These results reveal changes in the R-wave amplitude and QRS duration, appearing at the onset and termination of apnea-bradycardia episodes, which could be potentially useful for the early detection and characterization of these episodes.

Evolutionary Optimization of ECG Feature Extraction Methods: Applications to the Monitoring of Adult Myocardial Ischemia and Neonatal Apnea Bradycardia Events

Although a significant bibliography exists on the application of signal processing methods to ECG signals, the optimal configuration of these methods so as to maximize their performance on clinical data is a complex problem that is seldom covered in the literature. This is particularly the case for the signal processing chains proposed for the detection and segmentation of individual beats, which are often characterized by a significant number or parameters (filter cut-off frequencies, thresholds, etc.). In this chapter we propose an automated method, based on evolutionary computing, to optimize these parameters in a joint fashion. A brief state of the art on current ECG segmentation methods is presented and a complete signal processing chain, adapted to the detection and segmentation of ECG signals is proposed. The evolutionary optimization method is described and applied to two different monitoring applications: the detection of myocardial ischemia episodes on adult patients and the characterization of apnea-bradycardia events on preterm infants.

Adaptation of five indirect insulin sensitivity evaluation methods to three populations: metabolic syndrome, athletic and normal subjects.

Insulin sensitivity is determined using direct or indirect methods. Indirect methods are less invasive than direct methods, but have lower accuracy. The accuracy is set through the Spearmans rank correlation coefficient between the indirect method and a direct method. Since the set of parameters of each indirect method has been set empirically, different values of insulin sensitivity have been reported when they are applied on different populations. In this paper, five indirect methods (Avignon, HOMA-IR, QUICKI, Raynaud, and Matsuda) used to determine insulin sensitivity were adapted to three different populations: athletics, metabolic syndrome and normal subjects. The parameters of each method were varied in a range of values until the optimal value that gives the best correlation coefficient with a gold standard was obtained. Results show that the adaptation procedure led to an improved correlation coefficient. Additionally, the method of Matsuda was the most accurate, followed by the method of Avignon. We have confirmed that each indirect method needs a different set of parameters when it is applied to a specific population in order to obtain an accurate value of insulin sensitivity.

Anthropometric measurements for assessing insulin sensitivity on patients with metabolic syndrome, sedentaries and marathoners.

The diagnosis of low insulin sensitivity is commonly done through the HOMA-IR index, in which fasting insulin and glucose blood levels are evaluated. Insulin and blood glucose levels are used for insulin sensitivity assessment by surrogate methods (HOMA-IR, Matsuda, etc), but anthropometric measurements like body weight, height and waist circumference are not considered, even if these variables also are related to low insulin sensitivity and metabolic syndrome. In this study we evaluate the impact of anthropometric measurements on the HOMA-IR, Matsuda and Caumo indexes to estimate insulin sensitivity. Specifically, we compare insulin sensitivity indexes with and without the anthropometric measurements in their equations on three different groups: patients with metabolic syndrome, sedentaries and marathoners. Results show relationships between anthropometric variables and insulin sensitivity indexes. On the other hand, subjects are mapped differently for insulin sensitivity assessment when anthropometric variables are taken into account. In addition, subjects diagnosed with normal insulin sensitivity could be considered as having low insulin sensitivity when anthropometric variables are considered.

Extracting Stationary Segments from Non-Stationary Synthetic and Cardiac Signals

Physiological signals are commonly the result of complex interactions between systems and organs, these interactions lead to signals that exhibit a non-stationary behaviour. For cardiac signals, non-stationary heart rate variability (HRV) may produce misinterpretations. A previous work proposed to divide a non-stationary signal into stationary segments by looking for changes in the signal’s properties related to changes in the mean of the signal. In this paper, we extract stationary segments from non-stationary synthetic and cardiac signals. For synthetic signals with different signal-to-noise ratio levels, we detect the beginning and end of the stationary segments and the result is compared to the known values of the occurrence of these events. For cardiac signals, RR interval (cardiac cycle length) time series, obtained from electrocardiographic records during stress tests for two populations (diabetic patients with cardiovascular autonomic neuropathy and control subjects), were divided into stationary segments. Results on synthetic signals reveal that the non-stationary sequence is divided into more stationary segments than needed. Additionally, due to HRV reduction and exercise intolerance reported on diabetic cardiovascular autonomic neuropathy patients, non-stationary RR interval sequences from these subjects can be divided into longer stationary segments compared to the control group.

Unsupervised subjects classification using insulin and glucose data for insulin resistance assessment

In this paper, the K-means clustering algorithm is employed to perform an unsupervised classification of subjects based on unidimensional observations (HOMA-IR and the Matsuda indexes separately) and multidimensional observations (insulin and glucose samples obtained from the oral glucose tolerance test). The goal is to explore if the clusters obtained could be used to predict or diagnose insulin resistance or are related to the profiles of the population under study: metabolic syndrome, marathoners and sedentaries. Using two and three clusters, three classification experiments were carried out: i) using the HOMA-IR index as unidimensional observations, ii) using the Matsuda index as unidimensional observations, and iii) using five insulin and five glucose samples as multidimensional observations. The results show that using the HOMA-IR index the clusters are related to insulin resistance but when multidimensional observations are used in the classification process the clusters could be used to predict the insulin resistance or other related diseases.

Data fusion for QRS complex detection in multi-lead electrocardiogram recordings

Heart diseases are the main cause of death worldwide. The first step in the diagnose of these diseases is the analysis of the electrocardiographic (ECG) signal. In turn, the ECG analysis begins with the detection of the QRS complex, which is the one with the most energy in the cardiac cycle. Numerous methods have been proposed in the bibliography for QRS complex detection, but few authors have analyzed the possibility of taking advantage of the information redundancy present in multiple ECG leads (simultaneously acquired) to produce accurate QRS detection. In our previous work we presented such an approach, proposing various data fusion techniques to combine the detections made by an algorithm on multiple ECG leads. In this paper we present further studies that show the advantages of this multi-lead detection approach, analyzing how many leads are necessary in order to observe an improvement in the detection performance. A well known QRS detection algorithm was used to test the fusion techniques on the St. Petersburg Institute of Cardiological Technics database. Results show improvement in the detection performance with as little as three leads, but the reliability of these results becomes interesting only after using seven or more leads. Results were evaluated using the detection error rate (DER). The multi-lead detection approach allows an improvement from DER = 3:04% to DER = 1:88%. Further works are to be made in order to improve the detection performance by implementing further fusion steps.