Fetal Heart Rate Analysis for Automatic Detection of Perinatal Hypoxia Using Normalized Compression Distance and Machine Learning.

Accurate identification of Perinatal Hypoxia from visual inspection of Fetal Heart Rate (FHR) has been shown to have limitations. An automated signal processing method for this purpose needs to deal with time series of different lengths, recording interruptions, and poor quality signal conditions. We propose a new method, robust to those issues, for automated detection of perinatal hypoxia by analyzing the FHR during labor. Our system consists of several stages: (a) time series segmentation; (b) feature extraction from FHR signals, including raw time series, moments, and usual heart rate variability indices; (c) similarity calculation with Normalized Compression Distance, which is the key element for dealing with FHR time series; and (d) a simple classification algorithm for providing the hypoxia detection. We analyzed the proposed system using a database with 32 fetal records (15 controls). Time and frequency domain and moment features had similar performance identifying fetuses with hypoxia. The final system, using the third central moment of the FHR, yielded 92% sensitivity and 85% specificity at 3 h before delivery. Best predictions were obtained in time intervals more distant from delivery, i.e., 4-3 h and 3-2 h.

Quality estimation of the electrocardiogram using cross-correlation among leads.

BACKGROUND: Fast and accurate quality estimation of the electrocardiogram (ECG) signal is a relevant research topic that has attracted considerable interest in the scientific community, particularly due to its impact on tele-medicine monitoring systems, where the ECG is collected by untrained technicians. In recent years, a number of studies have addressed this topic, showing poor performance in discriminating between clinically acceptable and unacceptable ECG records. METHODS: This paper presents a novel, simple and accurate algorithm to estimate the quality of the 12-lead ECG by exploiting the structure of the cross-covariance matrix among different leads. Ideally, ECG signals from different leads should be highly correlated since they capture the same electrical activation process of the heart. However, in the presence of noise or artifacts the covariance among these signals will be affected. Eigenvalues of the ECG signals covariance matrix are fed into three different supervised binary classifiers. RESULTS AND CONCLUSION: The performance of these classifiers were evaluated using PhysioNet/CinC Challenge 2011 data. Our best quality classifier achieved an accuracy of 0.898 in the test set, while having a complexity well below the results of contestants who participated in the Challenge, thus making it suitable for implementation in current cellular devices.

An automated screening system for tuberculosis.

Automated screening systems are commonly used to detect some agent in a sample and take a global decision about the subject (e.g., ill/healthy) based on these detections. We propose a Bayesian methodology for taking decisions in (sequential) screening systems that considers the false alarm rate of the detector. Our approach assesses the quality of its decisions and provides lower bounds on the achievable performance of the screening system from the training data. In addition, we develop a complete screening system for sputum smears in tuberculosis diagnosis, and show, using a real-world database, the advantages of the proposed framework when compared to the commonly used count detections and threshold approach.

Extended input space support vector machine.

In some applications, the probability of error of a given classifier is too high for its practical application, but we are allowed to gather more independent test samples from the same class to reduce the probability of error of the final decision. From the point of view of hypothesis testing, the solution is given by the Neyman-Pearson lemma. However, there is no equivalent result to the Neyman-Pearson lemma when the likelihoods are unknown, and we are given a training dataset. In this brief, we explore two alternatives. First, we combine the soft (probabilistic) outputs of a given classifier to produce a consensus labeling for K test samples. In the second approach, we build a new classifier that directly computes the label for K test samples. For this second approach, we need to define an extended input space training set and incorporate the known symmetries in the classifier. This latter approach gives more accurate results, as it only requires an accurate classification boundary, while the former needs an accurate posterior probability estimate for the whole input space. We illustrate our results with well-known databases.

Nucleotide variation in central nervous system genes among male suicide attempters.

Despite marked morbidity and mortality associated with suicidal behavior, accurate identification of individuals at risk remains elusive. The goal of this study is to identify a model based on single nucleotide polymorphisms (SNPs) that discriminates between suicide attempters and non-attempters using data mining strategies. We examined functional SNPs (n = 840) of 312 brain function and development genes using data mining techniques. Two hundred seventy-seven male psychiatric patients aged 18 years or older were recruited at a University hospital psychiatric emergency room or psychiatric short stay unit. The main outcome measure was history of suicide attempts. Three SNPs of three genes (rs10944288, HTR1E; hCV8953491, GABRP; and rs707216, ACTN2) correctly classified 67% of male suicide attempters and non-attempters (0.50 sensitivity, 0.82 specificity, positive likelihood ratio = 2.80, negative likelihood ratio = 1.64). The OR for the combined three SNPs was 4.60 (95% CI: 1.31-16.10). The model's accuracy suggests that in the future similar methodologies may generate simple genetic tests with diagnostic utility in identification of suicide attempters. This strategy may uncover new pathophysiological pathways regarding the neurobiology of suicidal acts.

Variables associated with familial suicide attempts in a sample of suicide attempters.

Attempted suicide appears to be a familial behavior. This study aims to determine the variables associated with family history of attempted suicide in a large sample of suicide attempters. The sample included 539 suicide attempters 18 years or older recruited in an emergency room. The two dichotomous dependent variables were family history of suicide attempt (10%, 51/539) and of completed suicide (4%, 23/539). Independent variables were 101 clinical variables studied with two data mining techniques: Random Forest and Forward Selection. A model for family history of completed suicide could not be developed. A classificatory model for family history of attempted suicide included the use of alcohol in the intent and family history of completed suicide (sensitivity, specificity, 98.7%; and accuracy, 96.6%). This is the first study that uses a powerful new statistical methodology, data mining, in the field of familial suicidal behaviors and suggests that it may be important to study familial variables associated with alcohol use to better understand the familiality of suicide attempts.

Using data mining to explore complex clinical decisions: A study of hospitalization after a suicide attempt.

BACKGROUND: Medical education is moving toward developing guidelines using the evidence-based approach; however, controlled data are missing for answering complex treatment decisions such as those made during suicide attempts. A new set of statistical techniques called data mining (or machine learning) is being used by different industries to explore complex databases and can be used to explore large clinical databases. METHOD: The study goal was to reanalyze, using data mining techniques, a published study of which variables predicted psychiatrists' decisions to hospitalize in 509 suicide attempters over the age of 18 years who were assessed in the emergency department. Patients were recruited for the study between 1996 and 1998. Traditional multivariate statistics were compared with data mining techniques to determine variables predicting hospitalization. RESULTS: Five analyses done by psychiatric researchers using traditional statistical techniques classified 72% to 88% of patients correctly. The model developed by researchers with no psychiatric knowledge and employing data mining techniques used 5 variables (drug consumption during the attempt, relief that the attempt was not effective, lack of family support, being a housewife, and family history of suicide attempts) and classified 99% of patients correctly (99% sensitivity and 100% specificity). CONCLUSIONS: This reanalysis of a published study fundamentally tries to make the point that these new multivariate techniques, called data mining, can be used to study large clinical databases in psychiatry. Data mining techniques may be used to explore important treatment questions and outcomes in large clinical databases and to help develop guidelines for problems where controlled data are difficult to obtain. New opportunities for good clinical research may be developed by using data mining analyses.

A hybrid hopfield network-simulated annealing approach for frequency assignment in satellite communications systems.

A hybrid Hopfield network-simulated annealing algorithm (HopSA) is presented for the frequency assignment problem (FAP) in satellite communications. The goal of this NP-complete problem is minimizing the cochannel interference between satellite communication systems by rearranging the frequency assignment, for the systems can accommodate the increasing demands. The HopSA algorithm consists of a fast digital Hopfield neural network which manages the problem constraints hybridized with a simulated annealing which improves the quality of the solutions obtained. We analyze the problem and its formulation, describing and discussing the HopSA algorithm and solving a set of benchmark problems. The results obtained are compared with other existing approaches in order to show the performance of the HopSA approach.