Italian Dataset Research Articles

Calculation of the reliability of classification in discriminant partial least-squares binary classification

A classification decision must include the degree of confidence in that decision. We have modified the binary classification method Discriminant Partial Least Squares (DPLS) to provide the reliability of the classification of an unknown object. This method, called Probabilistic Discriminant Partial Least Squares ( p-DPLS), integrates DPLS, density methods and Bayes decision theory in order to take into account the uncertainty of the predictions in DPLS. The reliability of classification is also used to derive a new classification rule, so that an unknown object is classified in the class for which it has the highest reliability. This new methodology is tested with two data sets, the benchmark Iris data set and an Italian olive oil data set. The results show that the proposed method is comparable with other methodologies, with percentages of correct classification higher than 95%, with the advantage of providing a measurement of the reliability of classification that agrees with the distribution of the samples in the training set.

CHOP T/C and C/T haplotypes contribute to early‐onset type 2 diabetes in Italians

Type 2 diabetes (T2D) is characterized by impaired insulin secretion, insulin insensitivity and decreased beta-cell mass. Multiple genes contribute to T2D. The chromosome 12q13.1 region is in linkage to T2D in different populations, including our Italian dataset. CHOP is a candidate gene for the linkage, as it is located in the chromosome 12q13.1 region, and may contribute to T2D by increasing beta-cell apoptosis susceptibility and by impairing insulin sensitivity. Our goal was to identify any potential CHOP gene variants contributing to T2D in our Italian early-onset T2D families, which show linkage to the CHOP region. We directly sequenced the CHOP gene in 28 Italian probands of the linked T2D families and in 115 control subjects. We performed genotype and haplotype association tests with T2D of the identified single nucleotide polymorphisms (SNPs). We performed model-free and parametric association haplotype tests with T2D. We identified three SNPs [5'UTR-c.279T > C, 5'UTR-c.120A > G and + nt30C > T (F10F)] in CHOP. These SNPs are in complete linkage disequilibrium. The genotype association test showed an association trend with T2D of TT (F10F) and AG (-c.120A > G). The haplotype association test provided significant results for the haplotypes T/C (frequency = 0.33) and C/T (frequency = 0.01) (at 5'UTR-c.279T > C and + nt30C > T, respectively) under non-parametric analysis (P-value = 0.0000), recessive model (P-value = 0.0000) and additive model (P-value = 0.0014). Our data show that CHOP described haplotypes T/C and C/T, as an additive and as a homozygous variant, contribute significantly to T2D in our Italian early-onset group. We conclude that the CHOP T/C and C/T haplotype contributes to our T2D linkage signal on chromosome 12q13.1.

The dynamics of repeated temporary jobs

The path to a permanent job often implies a sequence of temporary contracts, sometimes including periods of unemployment. This has usually been disregarded in previous studies on the transition from temporary to permanent employment. To account for these transitions, I apply multiple-spell duration techniques to an Italian dataset. I find that the probability of moving from a temporary to a permanent job increases with the duration of the contract, but decreases with repeated temporary jobs and especially with interruptions. This suggests that it is not temporary employment per se but the intermittence associated with it that is detrimental to employment prospects.

Measuring patient safety: the Agency for Healthcare Research and Qualityís patient safety indicators

There is a lot of interest in patient safety, but there is still little useable national level information on the actual magnitude of patient safety problems that can be used by providers and policy makers to judge performance. The AHRQ Patient Safety Indicators (PSIs) are a set of measures that can be used with hospital inpatient administrative (discharge) data to provide a perspective on patient safety. They screen for problems that patients experience as a result of exposure to the healthcare system and that are likely amenable to prevention by changes at the system or provider level. There is a growing interest in the possible use of the AHRQ PSIs in international settings. The Organization for Economic Cooperation and Development (OECD) maintains an ongoing project on Health Care Quality Indicators (HCQI) and whose goal is to develop a set of quality indicators that can be used to reliably assess quality of care across countries and raise questions about differences in quality of care internationally. Work is ongoing though a partnership between AHRQ and the Italian National Observatory on Health in the Italian Regions to test the AHRQ QIs with the Italian national hospital discharge data set. Preliminary results indicate that many of the operational issues associated with differences in coding schemes and data set structure are surmountable. With additional refinements on their clinical specificity, increased stability in their definitions over time to permit long-term monitoring and country interest within organizations such as the OECD to build on the existing scientific work of these indicators, their to help answer questions about patient safety worldwide will be significantly enhanced.

Prediction performances of portable near infrared instruments for at farm forage analysis

The objective of this study was to evaluate the use of Near Infrared Spectroscopy (NIRS) to analyze maize silage with a portable instrument. The instrument was a Zeiss Corona 45 working between 960 and 1700 nm which was used in Italy, Czech Republic and Poland. Best prediction performances were obtained using the Italian data set. Prediction error were 1.0, 0.16 and 0.4 respectively for DM, CP and NDF on a as is basis. With the instrument from Poland and Czech Republic there were lower accuracy of prediction compared to the Italian dataset, probably for their limited (less than 100 samples) calibration data set. Merging all the data set improved prediction accuracy for CP but not DM. It would appear that some form of instrument standardization is needed before merging data set.

Self-Configuring Radial Basis Function Neural Networks for Chemical Pattern Recognition

Construction of radial basis function neural networks (RBFN) involves selection of radial basis function centroid, radius (width or scale), and number of radial basis function (RBF) units in the hidden layer. The K-means clustering algorithm is frequently used for selection of centroids and radii. However, with the K-means clustering algorithm, the number of RBF units is usually arbitrarily selected, which may lead to suboptimal performance of the neural network model. Besides, class membership and the related probability distribution are not considered. Linear averaging (L-A) was devised for selection of centroids and radii for the RBFs and computing the number of RBF units. The proposed method considers the class membership and localized probability density distribution of each class in the training sets. The parameters related to the network construction were investigated. The network was trained with the QuickProp algorithm (QP) or Singular Value Decomposition (SVD) algorithm and evaluated with the poly(chlorobiphenyl) (PCB) mass spectra and an Italian olive oil reference data set. The prediction accuracy of PCB data sets was better than 94%, and the prediction accuracy with Italian olive oil data sets achieved 100% with RMSEP as low as 2.4 × 10-3. The training times were usually about a second on a personal computer. The performance of neural networks constructed from the linear-averaging method was observed to be better than that with the K-means algorithm with these data sets.

A fuzzy adaptive resonance theory—supervised predictive mapping neural network applied to the classification of multivariate chemical data

A fuzzy adaptive resonance theory—supervised predictive mapping (Fuzzy ARTMAP) neural network has been studied for the classification of multivariate chemical data. Fuzzy ARTMAP achieves a synthesis of fuzzy logic and adaptive resonance theory (ART) by exploiting the close formal similarity between the computations of fuzzy subset membership and ART category choice, resonance, and learning. To examine the properties of Fuzzy ARTMAP, the well-known Italian olive oil data set was employed. Then this method was applied to a practical agricultural data set to classify different soil samples depending on the crops grown on them. For comparison, the back-propagation (BP) neural network has also been used to treat these data. The results show that the classification performance of the Fuzzy ARTMAP neural network is as good or better than the BP network in the present applications. Among other features, the Fuzzy ARTMAP needs less training time and fewer algorithmic parameters to be optimized than BP does to achieve good classification.

Kohonen neural network as a pattern recognition method based on the weight interpretation

The Kohonen self-organizing neural network is a useful tool for pattern recognition. Based on the Kohonen map obtained from the training set, predictions can be made for the unknown objects. The problem is how to determine the membership of new objects hitting empty neurons which were not activated by any training set objects. The K-nearest neighbor technique has been previously used to solve this problem based on the relative geometric position of the neurons in the two-dimensional Kohonen map (Kohonen-KNN). However, during the projection into a low-dimensional subspace for the Kohonen neural network, some information about the correct neighbor relationships between the object vectors is lost. Thus, the Kohonen-KNN method may not give the best prediction results. In this paper, an alternative method is proposed for the Kohonen neural network to be used in a supervised way based on the weight interpretation (Kohonen-WI). The membership of the samples hitting the empty neurons during the prediction process is determined to be the same as that of the nearest active neuron based on a distance measure from the trained weight vectors. The Italian olive oil data set is used to test this method. Moreover, the learning vector quantization (LVQ) method has also been used to treat the same data set. This method explicitly uses the class membership of samples in the training set for the fine adaptions of network weights. It has been found that the Kohonen-WI method gives better prediction results than Kohonen-KNN, indicating that the weight interpretation can partly compensate for the information loss about the correct neighbor relationship between the neurons in the Kohonen map. The LVQ method gives very similar and satisfactory classification results as Kohonen-WI, though their working mechanisms are different. By comparison, the Kohonen-WI method is easier to use.

An econometric test of the self-employment model: The case of Italy

In this paper the authors put forward their attempt to test a self-employment model using an Italian data set which collects information about 78 Italian provinces (out of 95) over the period of 1985–1988. The self-employment model is introduced as a useful way to explain the formation of new small firms and subsequently previous econometric studies based on this model are discussed and compared. Once the empirical definitions of the variables are clarified, the econometric specification is introduced in Section 4 and results are discussed in Section 5 and 6. The general outcome of the estimates backs to a certain extent the self-employment approach which has already been tested with good results both in the U.K. and in the U.S. As far as the income choice is concerned, it turns out to be important in explaining the birth of new small firms. With regard to the role of job-losses, they also turn out to be significantly correlated with the high rates of firm formation. On the other hand, the discussion reported in Section 5 underlines the importance of other environmental factors which were not included in the original specification of Section 4. In particular, if the numerosity of the existing small firms is taken into account, self-employment relationships lose some of their significance. p]The laborer asks what he thinks the entrepreneur will be able to pay, and in any case will not accept less than he can get from some other entrepreneur, or by turning entrepreneur himself. In the same way the entrepreneur offers to any laborer what he thinks he must in order to secure his services, and in any case not more than he thinks the laborer will actually be worth to him, keeping in mind what he can get by turning laborer himself. Knight, 1921, p. 273

Coffee Consumption and Serum Cholesterol

The relationship between coffee consumption and serum cholesterol was examined in the comparison group of a case–control study of myocardial infarction involving 642 patients from various Italian regions who were hospitalized for diseases having no relationship to cardiovascular disease risk factors. Overall mean total cholesterol was 198.9 mg/dl. Mean cholesterol values (in mg/dl) standardized for age, sex, and smoking habits were 204.0 for nonconsumers of coffee, 194.8 for drinkers of one cup per day, 196.5 for two, 202.9 for three, 205.9 for four, and 206.5 for five or more cups per day. Thus, serum cholesterol levels were higher in non-coffee drinkers than in moderate drinkers; among coffee drinkers, however, there was a direct, although moderate, relationship between the amount of coffee consumed and the total cholesterol levels. A similar though less consistent pattern was also evident across separate strata of sex, age, and smoking habits, and the association was appreciably greater among younger subjects (below age 50). Although mean cholesterol levels in this Italian dataset were lower than those in other populations from northern Europe and the United States, the relative difference between moderate and heavy drinkers was proportionally similar to that reported in other studies. These results are of special interest since most Italian coffee (i.e., mocha or espresso) is unfiltered.

Pooled analysis of 3 european case‐control studies of ovarian cancer: II. Age at menarche and at menopause

The role of age at menarche and at menopause on epithelial ovarian cancer risk was re-assessed in a combined analysis of 3 hospital-based case-control studies conducted in Italy, the United Kingdom and Greece, which produced a total of 1,140 cases and 2,724 controls. In the overall dataset, there was no evidence of an association with age at menarche: compared with women whose menarche occurred at age 15 or over, the relative risk (RR) estimates were 1.0 [95% confidence interval (CI) 0.8 to 1.2] for those with menarche at ages 12 to 14, and 1.0 (95% CI 0.8-1.2) for those with menarche below age 12. There was no consistent interaction between age at menarche and study centre or age at diagnosis. In relation to age at menopause, compared with women whose menopause occurred at age 44 or earlier, the RR was 1.4 between 45 and 49, 1.6 between 50 and 52 and 1.9 above 52. The strength of the association was apparently (but not significantly) greater in the British than in the Greek or Italian dataset. The effect of age at menopause tended to be long-lasting and, if anything, to increase across subsequent age-groups. The large dataset, and the replication of results in different studies, provide more definite and precise information than previously available on the absence of appreciable effect of age at menarche on subsequent ovarian cancer risk in developed countries. For age at menopause, there was a direct and consistent trend in risk, but the association was relatively weak, with RRs below 2 even between extreme categories.