Application of machine learning to predict obstructive sleep apnea syndrome severity.

INTRODUCTION: Obstructive sleep apnea syndrome has become an important public health concern. Polysomnography is traditionally considered an established and effective diagnostic tool providing information on the severity of obstructive sleep apnea syndrome and the degree of sleep fragmentation. However, the numerous steps in the polysomnography test to diagnose obstructive sleep apnea syndrome are costly and time consuming. This study aimed to test the efficacy and clinical applicability of different machine learning methods based on demographic information and questionnaire data to predict obstructive sleep apnea syndrome severity. MATERIALS AND METHODS: We collected data about demographic characteristics, spirometry values, gas exchange (PaO2, PaCO2) and symptoms (Epworth Sleepiness Scale, snoring, etc.) of 313 patients with previous diagnosis of obstructive sleep apnea syndrome. After principal component analysis, we selected 19 variables which were used for further preprocessing and to eventually train seven types of classification models and five types of regression models to evaluate the prediction ability of obstructive sleep apnea syndrome severity, represented either by class or by apnea-hypopnea index. All models are trained with an increasing number of features and the results are validated through stratified 10-fold cross validation. RESULTS: Comparative results show the superiority of support vector machine and random forest models for classification, while support vector machine and linear regression are better suited to predict apnea-hypopnea index. Also, a limited number of features are enough to achieve the maximum predictive accuracy. The best average classification accuracy on test sets is 44.7 percent, with the same average sensitivity (recall). In only 5.7 percent of cases, a severe obstructive sleep apnea syndrome (class 4) is misclassified as mild (class 2). Regression results show a minimum achieved root mean squared error of 22.17. CONCLUSION: The problem of predicting apnea-hypopnea index or severity classes for obstructive sleep apnea syndrome is very difficult when using only data collected prior to polysomnography test. The results achieved with the available data suggest the use of machine learning methods as tools for providing patients with a priority level for polysomnography test, but they still cannot be used for automated diagnosis.

GrCount: Counting method for uncertain data.

We report a method for counting uncertain data, i.e. observations that cannot be precisely associated to referents. We model data uncertainty through Possibility Theory and we develop the counting method so as to take into account the possibility distributions attached to data. The result is a fuzzy interval on the domain of natural numbers, which can be obtained by two variants of the method: exact counting provides the true fuzzy interval in quadratic time complexity, while approximate counting carries out an estimate of the fuzzy interval in linear time. We give a step-by-step description of the method so that it can be replicated in any programming environment. We also provide a Python implementation and a use case in Bioinformatics. The method usage is the following: •The uncertain data are represented in form of matrix, one row for each observation. Each row is a possibility distribution;•The method variant must be selected. In the case of the approximate variant, the number of α-values of the resulting fuzzy interval must be provided;•For each referent, a fuzzy interval is determined and carried out by the method.

Identification and evaluation of cognitive deficits in schizophrenia using "Machine learning".

BACKGROUND: Schizophrenia can be interpreted as a pathology involving the neocortex whose cognitive dysfunctions represent a central and persistent characteristic of the disease, as well as one of the more important symptoms in relation to the impairment of psychosocial functioning and the resulting disabilities. Given the implication of cognitive functions in everyday life, they can better predict the degree of schizophrenia. The study proposes to use Machine Learning techniques to identify the specific cognitive deficits of schizophrenia that mostly characterize the disorder, as well as to develop a predictive system that can diagnose the presence of schizophrenia based on neurocognitive tests. BACKGROUND: The study employs a dataset of neurocognitive assessments carried out on 201 people (86 schizophrenic patients and 115 healthy patients) recruited by the Neuroscience Group of the University of Bari "A. Moro". A data analysis process has been carried out, with the aim of selecting the most relevant features as well as to prepare data for training a number of "off-the-shelf" machine learning methods (Decision Tree, Random Forest, Logistic Regression, k-Nearest Neighbor, Neural Network, Support Vector Machine), which have been evaluated in terms of classification accuracy according to stratified 20-fold cross-validation. RESULTS: Among all variables, 14 were selected as the most influential for the classification problem. The variables with greater influence are related to working memory, executive functions, attention, verbal fluency, memory. The best algorithms turned out to be Support Vector Machine (SVM) and Neural Network, showing an accuracy of 87.8% and 84.8% on a test set. CONCLUSIONS: Machine Learning provides "cheap" and non-invasive methods that potentially enable early intervention with specific rehabilitation interventions. The results suggest the need to integrate a thorough neuropsychological evaluation into the more general diagnostic evaluation of patients with schizophrenia disorder.

A fuzzy method for RNA-Seq differential expression analysis in presence of multireads.

BACKGROUND: When the reads obtained from high-throughput RNA sequencing are mapped against a reference database, a significant proportion of them - known as multireads - can map to more than one reference sequence. These multireads originate from gene duplications, repetitive regions or overlapping genes. Removing the multireads from the mapping results, in RNA-Seq analyses, causes an underestimation of the read counts, while estimating the real read count can lead to false positives during the detection of differentially expressed sequences. RESULTS: We present an innovative approach to deal with multireads and evaluate differential expression events, entirely based on fuzzy set theory. Since multireads cause uncertainty in the estimation of read counts during gene expression computation, they can also influence the reliability of differential expression analysis results, by producing false positives. Our method manages the uncertainty in gene expression estimation by defining the fuzzy read counts and evaluates the possibility of a gene to be differentially expressed with three fuzzy concepts: over-expression, same-expression and under-expression. The output of the method is a list of differentially expressed genes enriched with information about the uncertainty of the results due to the multiread presence. We have tested the method on RNA-Seq data designed for case-control studies and we have compared the obtained results with other existing tools for read count estimation and differential expression analysis. CONCLUSIONS: The management of multireads with the use of fuzzy sets allows to obtain a list of differential expression events which takes in account the uncertainty in the results caused by the presence of multireads. Such additional information can be used by the biologists when they have to select the most relevant differential expression events to validate with laboratory assays. Our method can be used to compute reliable differential expression events and to highlight possible false positives in the lists of differentially expressed genes computed with other tools.

An empirical risk functional to improve learning in a neuro-fuzzy classifier.

The paper proposes a new Empirical Risk Functional as cost function for training neuro-fuzzy classifiers. This cost function, called Approximate Differentiable Empirical Risk Functional (ADERF), provides a differentiable approximation of the misclassification rate so that the Empirical Risk Minimization Principle formulated in Vapnik's Statistical Learning Theory can be applied. Also, based on the proposed ADERF, a learning algorithm is formulated. Experimental results on a number of benchmark classification tasks are provided and comparison to alternative approaches given.