Search

The cardiovascular prevention represents a hot topic in particular when referred to children or adolescents. Indeed it is demonstrated that atherosclerosis starts early in childhood in the presence of cardiovascular risks factors such as dyslipidemia. It arises precociously when inherited lipoprotein disorders occur as in familial hypercholesterolemia, but not only, or in the presence of a cluster of metabolic changes leading to metabolic syndrome. In these conditions it is mandatory to apply all measures aimed to improve the lipid profile as recommended by international guidelines. Lifestyle is recognized the main basic approach while hypolipidemic drugs should be limited to very high risk children since 8–10 years of age. To comply with the expected LDL-Cholesterol (LDL-C) goal some limitations occur at times then nutraceuticals have been considered in children, as demonstrated beneficial in reducing LDL-C in most of adults. The experience in children is so far very poor since limited randomized controlled trials have been performed including a limited number of subjects. Studies mainly concern Fibre and Phytosterols/stanols and the majority improved lipid profile resulting safe and well tolerated. In this review we synthetize these results including other nutraceuticals as Red Yeast Rice, Omega-3/−6 PUFAs, Probiotic, Soy derivative and Nut.

The translation of precision medicine in clinical practice will depend mostly on the possibility to make statistical inference at the individual level, exactly positioning a new case in the taxonomy space (diagnosis) or in the time space (prognosis). As a matter of the fact, clinical epidemiology and medical statistics have not been suited to answer specific questions at the individual level. They focus on groups of individuals and not on single individuals. Classical statistics by definition needs samples to work, and samples by definition are always greater than one. This explains why for traditional statistics the single individual is a sort of moving and vague target to intercept. The objective of this chapter is to show the feasibility of the use of potent machine learning system developed at the Semeion Institute in approaching the problem of single individual statistics in a consistent and sound way. Three case studies relevant to different unsupervised machine learning systems are reviewed: (a) the use of self-organizing maps (SOMs) to determine the confidence interval of a quality of life scale total score in seven new individual subjects having a group of 1000 individuals as reference data set; (b) the use of the evolutionary algorithm “pick and squash tracking” (PST) to cluster and discriminate patients affected by Barrett disease from those affected by simple gastroesophageal reflux disease, (c) the use of the auto-contractive map (Auto-CM) system, a fourth-generation artificial neural network, to map individual patients with and without acute myocardial infarction (AMI) on the basis of genetic, clinical traits, and classical risk factors. A further case study is described relying on the use of supervised machine learning systems, based on the concept of Fermi mathematics. The three unsupervised methods proved to be reliable and easily applicable to real-world examples in terms of readability, accuracy, and reproducibility. The confidence interval related to the seven new cases in the first case study allowed the clinician to identify easily the outlier. The accuracy of the map projection with PST algorithm in the second case study allowed an immediate visual evidence of the degree of membership of each individual subject to the two diagnostic classes. In the third case study, the overall accuracy of clustering obtained by the Auto-CM system resulted is found to be 93%.The conceptual advantages obtainable are explained. The fourth method shows that it is possible by using several independent classification models on the same individual to establish a degree of confidence of the prediction and therefore to overcome the dogma that it is not possible to make a statistical inference when a sample is composed by just one subject.

Huge amounts of antibiotics are currently being used in both human and veterinary medicine. Moreover, most are recalcitrant to biodegradation and can persist in the environment. In fact these compounds have been increasingly found as micro-contaminants in natural ecosystems and cause particular concern because of the development of multi-resistant bacteria, posing serious risks for human and animal health. In particular, the antibiotics used in livestock farms can persist in manure, causing environmental contamination if used as a biofertilizer. However, farm manure can also be a feed for biogas reactors and the digested effluent (digestate) used as fertilizer or soil improver. The fact that the latter can still contain antibiotic residues and possibly antibiotic resistance genes still remains to be clarified.

Background and objective Atrial fibrillation (AF) is the most common cardiac arrhythmia in clinical practice, having been recognized as a true cardiovascular epidemic. In this paper, a new methodology for Computer Aided Diagnosis of AF based on a special kind of artificial adaptive systems has been developed. Methods Following the extraction of data from the PhysioNet repository, a new dataset composed of the R/R distances of 73 patients was created. To avoid redundancy, the training set was created by randomly selecting 50% of the subjects from the entire sample, thus making a choice by patient and not by record. The remaining 50% of subjects were randomly split by records in testing and prediction sets. The original ECG data has been transformed according to the following four orders of abstraction: a) sequence of R/R intervals; b) composition of ECG data into a moving window; c) training of different machine learning systems to abstract the function governing the AF; d) fuzzy transformation of Machine learning estimations. In this paper, in parallel with the classic method of windowing, we propose a variant based on a system of progressive moving averages. Results The best performing machine learning, Supervised Contractive Map (SVCm), reached an overall mean accuracy of 95%. SVCm is a new deep neural network based on a different principle than the usual descending gradient. The minimization of the error occurs by means of decomposition into contracted sine functions. Conclusions In this research, atrial fibrillation is considered from a completely different point of view than classical methods. It is seen as the stable process, i.e. the function, that manages the irregularity of the irregularities of the R/R intervals. The idea, therefore, is to abstract from mere physiology to investigate fibrillation as a mathematical object that handles irregularities. The attained results seem to open new perspectives for the use of potent artificial adaptive systems for the automatic detection of atrial fibrillation, with accuracy rates extremely promising for real world applications.

Background Familial hypercholesterolemia (FH) is a genetic disorder caused by mutations in genes involved in low-density lipoprotein (LDL) uptake (LDLR, APOB and PCSK9). Genetic diagnosis is particularly useful in asymptomatic children allowing for the detection of definite FH patients. Furthermore, defining their genetic status may be of considerable importance as the compound heterozygous status is much more severe than the heterozygous one. Our study aims at depicting the genetic background of an Italian pediatric population with FH focusing on the correlation between lipid profile and genetic status. Methods Out of 196 patients with clinically suspected FH (LDL-cholesterol [LDL-C] levels above 3.37 mmol/L, cholesterol level above 6.46 mmol/L in a first-degree relative or the presence of premature cardiovascular acute disease in a first/second-degree relative), we screened 164 index cases for mutations in the LDLR, APOB and PCSK9 genes. Results Patients with mutations (129/164) showed increased levels of LDL-C, 95th percentile-adjusted LDL-C and LDL/high-density lipoprotein (HDL) ratio and decreased levels of HDL-C, adjusted HDL-C. The association of the LDL/HDL ratio with the presence of mutations was assessed independently of age, (body mass index) BMI, parental hypercholesterolemia, premature coronary artery disease (CAD), triglycerides by multivariate logistic regression (odds ratio [OR]=1.701 [1.103–2.621], p=0.016). The LDL/HDL ratio gradually increased from patients without mutations to patients with missense mutations, null mutations and compound heterozygotes. Conclusions In conclusion, the LDL/HDL ratio proved to be a better parameter than LDL-C for discriminating patients with from patients without mutations across different genetic statuses.

In this paper, we introduce an innovative approach to the fusion between datasets in terms of attributes and observations, even when they are not related at all. With our technique, starting from datasets representing independent worlds, it is possible to analyze a single global dataset, and transferring each dataset onto the others is always possible. This procedure allows a deeper perspective in the study of a problem, by offering the chance of looking into it from other, independent points of view. Even unrelated datasets create a metaphoric representation of the problem, useful in terms of speed of convergence and predictive results, preserving the fundamental relationships in the data. In order to extract such knowledge, we propose a new learning rule named double backpropagation, by which an auto-encoder concurrently codifies all the different worlds. We test our methodology on different datasets and different issues, to underline the power and flexibility of the Theory of Impossible Worlds.

Children affected by primary hyperlipidemia have a high risk of developing cardiovascular diseases (CVDs) during adulthood. Several studies have reported a positive association between the intake of polyunsaturated fatty acids (PUFAs) and improvements in lipid markers and CVD risk. Dietary supplements may represent a potential strategy in the management of hyperlipidemia. In this context, the effectiveness of hempseed oil (HSO) rich in PUFAs (particularly linoleic acid (LA) and α-linolenic acid (ALA)) in the modulation of hyperlipidemia has been poorly investigated. The present pilot study aimed to explore the impact of HSO supplementation on the serum lipid profile and fatty acid (FA) composition of red blood cells (RBCs) in children and adolescents with primary hyperlipidemia. A randomized, 8 week long, parallel dietary intervention study was performed. Thirty-six hyperlipidemic probands (6-16 years) on diet therapy were randomized into two groups: the HSO group, receiving 3 g of HSO providing 1.4 g of LA and 0.7 g/day of ALA, and the control group. Both groups received specific dietary guidelines. Before and after the intervention, blood samples were collected and the serum lipid profile, FA composition of RBCs and omega-3-index were analyzed. Eight weeks of supplementation with HSO significantly (p .01) reduced the RBC content of total saturated and monounsaturated FAs (-5.02 ± 7.94% and - 2.12 ± 2.23%, respectively), increased the levels of total n-3 and n-6 PUFAs (+1.57 ± 1.96% and + 5.39 ± 7.18%, respectively) and the omega-3 index (+1.18 ± 1.42%), but failed to affect the serum lipid profile compared to the control group. In conclusion, our findings seem to support the contribution of HSO supplementation in improving the RBC phospholipid composition and omega-3 index, while no effect was observed regarding modulation of the lipid profile. Further controlled studies are necessary to achieve a complete understanding of the effects of HSO in the modulation of hyperlipidemia and CVD risk in this and other target groups.

Artificial Adaptive Systems include Artificial Neural Networks (ANNs or simply neural networks as they are commonly known). The philosophy of neural networks is to extract from data the underlying model that relates this data as an input/output (domain/range) pair. This is quite different from the way most mathematical modeling processes operate. Most mathematical modeling processes normally impose on the given data a model from which the input to output relationship is obtained. For example, a linear model that is a “best fit” in some sense, that relates the input to the output is such a model. What is imposed on the data by artificial neural networks is an a priori architecture rather than an a priori model. From the architecture, a model is extracted. It is clear, from any process that seeks to relate input to output (domain to range), requires a representation of the relationships among data. The advantage of imposing an architecture rather than a data model, is that it allows for the model to adapt. Fundamentally, a neural network is represented by its architecture. Thus, we look at the architecture first followed by a brief introduction of the two types of approaches for implementing the architecture—supervised and unsupervised neural networks. Recall that Auto-CM, which we discuss in Chap. 3, is an unsupervised ANN while K-CM, discussed in Chap. 6, is a supervised version of Auto-CM. However, in this chapter, we show that, in fact, supervised and unsupervised neural networks can be viewed within one framework in the case of the linear perceptron. The chapter ends with a brief look at some theoretical considerations.

We have looked at how to visualize the relationships among the elements of a dataset in Chap. 4. This chapter is devoted to the use of Auto-CM in the transformation of datasets for the purpose of extracting further relationships among data elements. The first transformation we call the FS-Transform, which looks beyond an all or nothing, binary relationship that is typical of most ANNs. The extraction of these perhaps more subtle relationships can be thought of as gradual relationships, zero denoting no relationship is present and one denoting a full/complete relationship that is absolutely present. It is thus, akin to a fuzzy set. The second transformation is one, which “morph” the delineation between records and variables within records that we call Hyper-Composition.

We look at how to use Auto-CM in the context of datasets that are changing in time. We modify our approach while keeping the original philosophy of Auto-CM.

According to an OCSE study, corruption in healthcare costs about €56 billion yearly, corresponding to €160 million daily (European Commission, Accompanying document on the draft Commission Decision on Establishing an EU Anti-corruption Reporting Mechanism (“EU Anti-Corruption Report”), 2011). In Italy the situation is even more alarming. A recent study (WHO, The World Health Report: Health Systems Financing: The Path to Universal Coverage, 2010) has estimated that waste, inefficiency and corruption cost our National Health Service about €20 billion a year, corresponding to about 20 % of the total health expense. By nature, corruption is a hidden, complex and difficult to quantify reality. The measurement of this phenomenon may only be approximate and risks not to include important elements such as social costs of corruption that cannot be quantified. For this reason, there is no mathematical formula able to supply a country’s level of corruption. However, in the course of time, some research demonstrated that people’s perception of corruption gives a rather reliable estimate of the nature and extent of some corruption phenomena in a given context. In this perspective, the objective of this study is to understand how the phenomenon of corruption is perceived across several world countries; in other words, is there a common view concerning corruption? Secondly, we aim at identifying any management “models” of this phenomenon, that may be applied to different social and economic contexts. These objectives are considered through the application and the comparison of results of two different methods of data mining, such as the principal component analysis and the auto-contractive map, based on the analysis of a dataset.

The paper is a preliminary research report and presents a method for generating new records using an evolutionary algorithm (close to but different from a genetic algorithm). This method, called Pseudo-Inverse Function (in short P-I Function), was designed and implemented at Semeion Research Centre (Rome). P-I Function is a method to generate new (virtual) data from a small set of observed data. P-I Function can be of aid when budget constraints limit the number of interviewees, or in case of a population that shows some sociologically interesting trait, but whose small size can seriously affect the reliability of estimates, or in case of secondary analysis on small samples.

The Artificial Adaptive Systems (AAS) are theories with which generative algebras are able to create artificial models simulating natural phenomenon. Artificial Neural Networks (ANNs) are the more diffused and best-known learning system models in the AAS. This article describes an overview of ANNs, noting its advantages and limitations for analyzing dynamic, complex, non-linear, multidimensional processes. An example of a specific ANN application to alcohol consumption in Spain, as part of the EU AMPHORA-3 project, during 1961–2006 is presented. Study's limitations are noted and future needed research using ANN methodologies are suggested.

Artificial neural networks can be currently considered as one of the most important emerging tools in multivariate analysis due to their ability to deal with non-liner complex systems.In this work, a recently proposed neural network, called K-Contractive Map (K-CM), is presented and its performance in classification is evaluated towards other well-known classification methods. K-CM exploits the non-linear variable relationships provided by the Auto-CM neural network to obtain a fuzzy profiling of the samples and then applies the k-NN classifier to evaluate the class membership of samples. The algorithm Training with Input Selection and Testing (TWIST) is applied prior to K-CM to perform training/test data splitting for model parameter optimization and validation. This novel classification strategy was evaluated on ten different datasets and the obtained results were generally satisfactory. © 2014 Elsevier B.V.

HighlightsNew version of I_FAST for blind classification of electroencephalogram tracing.Application to mild cognitive impairment, early Alzheimer's disease and controls.Avoidance of pre-processing and filtering procedure of EEG data.Accuracies in distinguishing between two classes around 98%. ObjectiveThis paper proposes a new, complex algorithm for the blind classification of the original electroencephalogram (EEG) tracing of each subject, without any preliminary pre-processing. The medical need in this field is to reach an early differential diagnosis between subjects affected by mild cognitive impairment (MCI), early Alzheimer's disease (AD) and the healthy elderly (CTR) using only the recording and the analysis of few minutes of their EEG. Methods and materialThis study analyzed the EEGs of 272 subjects, recorded at Rome's Neurology Unit of the Policlinico Campus Bio-Medico. The EEG recordings were performed using 19 electrodes, in a 0.3-70Hz bandpass, positioned according to the International 10-20 System. Many powerful learning machines and algorithms have been proposed during the last 20 years to effectively resolve this complex problem, resulting in different and interesting outcomes. Among these algorithms, a new artificial adaptive system, named implicit function as squashing time (I-FAST), is able to diagnose, with high accuracy, a few minutes of the subject's EEG track; whether it manifests an AD, MCI or CTR condition. An updating of this system, carried out by adding a new algorithm, named multi scale ranked organizing maps (MS-ROM), to the I-FAST system, is presented, in order to classify with greater accuracy the unprocessed EEG's of AD, MCI and control subjects. ResultsThe proposed system has been measured on three independent pattern recognition tasks from unprocessed EEG tracks of a sample of AD subjects, MCI subjects and CTR: (a) AD compared with CTR; (b) AD compared with MCI; (c) CTR compared with MCI. While the values of accuracy of the previous system in distinguishing between AD and MCI were around 92%, the new proposed system reaches values between 94% and 98%. Similarly, the overall accuracy with best artificial neural networks (ANNs) is 98.25% for the distinguishing between CTR and MCI. ConclusionsThis new version of I-FAST makes different steps forward: (a) avoidance of pre-processing phase and filtering procedure of EEG data, being the algorithm able to directly process an unprocessed EEG; (b) noise elimination, through the use of a training variant with input selection and testing system, based on naive Bayes classifier; (c) a more robust classification phase, showing the stability of results on nine well known learning machine algorithms; (d) extraction of spatial invariants of an EEG signal using, in addition to the unsupervised ANN, the principal component analysis and the multi scale entropy, together with the MS-ROM; a more accurate performance in this specific task.

The self-organizing map artificial neural network takes high-dimensional data and produces a diagram (map) that displays it in one or two dimensions. In short, humans can visualize interactions when displayed in one, two, or three dimensions, but not four or more dimensions. Data composed of only one variable can “see” a point on an x-axis diagram; data composed of two variables can be displayed on an x–y axis diagram; data composed of three variables can be displayed on an x–y–z axis diagram, and the visualization stops here. We simply cannot visualize diagrams in four or more dimensions, and that is where the self-organizing map comes into play. It has the ability of analyzing data in an unsupervised way (without any preconceived indication of the number of patters present in the data) and placing the resulting analysis in a one- or two-dimensional diagram. While some information might be lost in the translation is more than made up with the insights that one can glean from the resulting diagram.

The aim of this study is to evaluate the capability of improved artificial adaptive systems and additional novel training methods in order to distinguish between benign and malignant lung nodules in Multi Detector Computed Tomography. A total of 90 nodules belonging to 88 patients are analyzed. A set of adjacent slices representing the lesion selected from the CT Image analysis by the experts are collected and stored in a database. Features extracted by an assembly of adaptive algorithms working in sequence [Active Connection Fusion (ACF): a new set of ANNs for image fusion; J-Net Active Connections Matrix (J-Net): a new ANN for dynamic image segmentation; Population (Pop): a new and fast multidimensional scaling algorithm] are divided into several groups using random or experimental methods to train and test different Artificial Neural Networks. Best results are obtained with Adaptive Learning Quantization (AVQ) and Meta-Consensus, two new supervised ANNs, experts in rapid classification and not sensitive to over fitting. After optimization of the distribution of cases among the training and testing sets the following results are achieved: sensitivity (recognition of malignant nodules) ranging from 93.33% to 100%; specificity (recognition of benign nodules) stable on 95.56% and overall accuracy ranging from 94.44% to 97.78%. These results represent the highest predictive values ever recorded in lung CAD literature. Benchmarking analysis, with advanced mathematical algorithms using simpler approaches, show that complex processing systems, composed of different steps and sub processing systems, are clearly superior and probably needed to reach excellent predictive performances in lung nodule characterization.

Constraint Satisfaction Networks were used by Semeion, a Research Center of Science of Communication, in order to analyze drug-addict patient data files, provided by the Jerusalem Methadone Treatment Center. The short and partial analysis carried out in this article is presented to show how this high technology can be a support for treatment staff in order to improve the quality and the timeliness of the necessary intervention with patients. One of the problems for which the networks could offer support is, for example, the individuation or “matching” of the most suitable therapy for the patient during the treatment planning phase. In this field the networks need to analyze data files of patients in therapy at different centers, with the results collected after many years of observation. What follows, obviously, only has demonstrative values.