A multistart tabu search-based method for feature selection in medical applications.

In the design of classification models, irrelevant or noisy features are often generated. In some cases, there may even be negative interactions among features. These weaknesses can degrade the performance of the models. Feature selection is a task that searches for a small subset of relevant features from the original set that generate the most efficient models possible. In addition to improving the efficiency of the models, feature selection confers other advantages, such as greater ease in the generation of the necessary data as well as clearer and more interpretable models. In the case of medical applications, feature selection may help to distinguish which characteristics, habits, and factors have the greatest impact on the onset of diseases. However, feature selection is a complex task due to the large number of possible solutions. In the last few years, methods based on different metaheuristic strategies, mainly evolutionary algorithms, have been proposed. The motivation of this work is to develop a method that outperforms previous methods, with the benefits that this implies especially in the medical field. More precisely, the present study proposes a simple method based on tabu search and multistart techniques. The proposed method was analyzed and compared to other methods by testing their performance on several medical databases. Specifically, eight databases belong to the well-known repository of the University of California in Irvine and one of our own design were used. In these computational tests, the proposed method outperformed other recent methods as gauged by various metrics and classifiers. The analyses were accompanied by statistical tests, the results of which showed that the superiority of our method is significant and therefore strengthened these conclusions. In short, the contribution of this work is the development of a method that, on the one hand, is based on different strategies than those used in recent methods, and on the other hand, improves the performance of these methods.

Assessment of an intervention to reduce the impact of stigma on people with HIV, enabling them to cope with it / Evaluación de una intervención dirigida a reducir el impacto del estigma en las personas con VIH capacitándolas para afrontarlo

The goal of this study was to assess an intervention program to reduce the impact of stigma on people with HIV and to enable them to cope with it. A quasi-experimental design, with non-equivalent control group and pre- and posttest was used. Participants were 221 people with HIV, of whom 164 received the intervention and 56 made up the nonequivalent control groups. The dependent variables were perception of stigma-enacted and internalized-, self-esteem, perception of selfefficacy, strategies used to cope with stigma-primary control, secondary control, and avoidance-and quality of life. Analysis of variance (MANOVAS and ANOVAS) was conducted to determine pretest differences and differential scores in both groups, and analysis of covariance (MANCOVAS and ANCOVAS) was performed to assess the efficacy of the program. The results showed reduction of perceived stigma and avoidance strategies and an increase in perceived self-efficacy to cope with stigma, disposition to use approach strategies, self-esteem, and quality of life. These results indicate that it is possible to train people with HIV to cope with stigma

Este estudio tuvo como objetivo evaluar un programa de intervención dirigido a disminuir el impacto del estigma en las personas con VIH y a capacitarlas para afrontarlo. Se utilizó un diseño cuasiexperimental, con grupo control no equivalente, y prueba previa y posterior. Participaron 221 personas con VIH, 164 recibieron la intervención y 56 formaron parte de los grupos de control no equivalente. Las variables dependientes fueron la percepción de estigma -declarado e internalizado-, la autoestima, la percepción de autoeficacia, las estrategias de afrontamiento del estigma -control primario, secundario y de evitación- y, la calidad de vida. Se realizaron análisis de las varianzas (MANOVAS y ANOVAS) para comprobar las diferencias en el pre-test y en las puntuaciones diferenciales en ambos grupos, y análisis de la covarianza (MANCOVAS y ANCOVAS) para evaluar la eficacia del programa. Los resultados mostraron una reducción del estigma percibido y de las estrategias de evitación y, un incremento en la autoeficacia percibida para afrontar el estigma, en la disposición al uso de estrategias de aproximación y en la autoestima y la calidad de vida. Estos resultados indican que es posible capacitar a las personas con VIH para afrontar el estigma

Adaptation of the HIV Stigma Scale in Spaniards with HIV.

The primary goal of this study was to adapt Berger, Ferrans, & Lahley (2001) HIV Stigma Scale in Spain, using Bunn, Solomon, Miller, & Forehand (2007) version. A second goal assessed whether the four-factor structure of the adapted scale could be explained by two higher-order dimensions, perceived external stigma and internalized stigma. A first qualitative study (N = 40 people with HIV, aged 28-59) was used to adapt the items and test content validity. A second quantitative study analyzed construct and criterion validity. In this study participants were 557 people with HIV, aged 18-76. The adapted HIV Stigma Scale for use in Spain (HSSS) showed a good internal consistency (α = .88) and good construct validity. Confirmatory Factor Analyses yielded a first-order, four-factor structure and a higher-order, bidimensional structure with the two expected factors (RMSEA = .051, 90% CI [.046, .056]; RMR = .073; GFI = .96; AGFI = .96; CFI = .98). Negative relations were found between stigma and quality of life (r = -.39; p < .01), self-efficacy to cope with stigma (r = -.50; p < .01) and the degree of HIV status disclosure (r = -.35; p < .01). Moreover, the people who had suffered AIDS-related opportunistic infections had a higher score in the Perceived External Stigma dimension than those who had not suffered them, t (493) = 3.02, p = .003, d = 0.26.

Protective and risk factors associated with voice strain among teachers in Castile and Leon, Spain: recommendations for voice training.

OBJECTIVES: The aim of this research was to know the protective and risk factors associated with voice strain in teachers. METHOD AND STUDY DESIGN: A total of 675 teachers from Castille and León, Spain took part in the research within an age range between 23 and 66 years (from nursery school to university). A cross-sectional, descriptive, and analytic design was applied to data from a self-administered questionnaire. RESULTS: The research showed that 16.4% had suffered some voice disorder and a remarkable percentage had never received any kind of voice training. The bivariate and multivariate analyses show that the size of the classroom, being a primary school teacher, teaching physical education, the noise caused by the students in the classroom, the struggle to keep the order within the class, raising the voice, and bad sleep are risk factors in the voice disorders. Each learning stage features a different risk factor, namely in nursery school, the noise caused by the pupils; in primary education, raising the voice; and in secondary education, the struggle to keep the order within the class. All these risk factors are linked with each other. CONCLUSIONS: The preventive measures must provide adequate answers to the voice requirements for every subject and stage, and these preventive measures must be based on the educational psychology principles to help the teachers deal with the problems originated by the lack of authority or the noise made by the students, using the proper voice techniques.

Adaptation of the HIV Stigma Scale in Spaniards with HIV

The primary goal of this study was to adapt Berger, Ferrans, & Lahley (2001) HIV Stigma Scale in Spain, using Bunn, Solomon, Miller, & Forehand (2007) version. A second goal assessed whether the four-factor structure of the adapted scale could be explained by two higher-order dimensions, perceived external stigma and internalized stigma. A first qualitative study (N = 40 people with HIV, aged 28-59) was used to adapt the items and test content validity. A second quantitative study analyzed construct and criterion validity. In this study participants were 557 people with HIV, aged 18-76. The adapted HIV Stigma Scale for use in Spain (HSSS) showed a good internal consistency (α = .88) and good construct validity. Confirmatory Factor Analyses yielded a first-order, four-factor structure and a higher-order, bidimensional structure with the two expected factors (RMSEA = .051, 90% CI [.046, .056]; RMR = .073; GFI = .96; AGFI = .96; CFI = .98). Negative relations were found between stigma and quality of life (r = -.39; p < .01), self-efficacy to cope with stigma (r = -.50; p < .01) and the degree of HIV status disclosure (r = -.35; p < .01). Moreover, the people who had suffered AIDS-related opportunistic infections had a higher score in the Perceived External Stigma dimension than those who had not suffered them, t (493) = 3.02, p = .003, d = 0.26 (AU)

No disponible

Determinants of psychological distress among migrants from Ecuador and Romania in a Spanish city.

BACKGROUND: Migration may have consequences on the mental health of those who enter a new cultural environment. In Spain, migration has increased tenfold in 20 years. It is important to study how these migrants are interacting within this new context and which variables hinder their personal and social development. AIMS: To analyze acculturation differences in Spain between first-generation immigrants from two different countries; to analyze the self-reported mental health of these participants; and to evaluate which variables best predict mental health disorders. METHOD: One hundred and thirty five (135) respondents from Romania and Ecuador responded to a questionnaire analyzing mental health by means of the GHQ-12, coupled with other personal, social and psychosocial acculturation variables. RESULTS: Both cultural groups differed significantly regarding the impact of personal and social variables on their well-being. Nevertheless, mental health distress was not explained by their cultural differences but by gender, gross income and perceived discrimination. Social support offered by those still living at home acted as a buffer. CONCLUSION: It is important to analyze female migration patterns in order to reduce mental health problems, stress the importance of economic income, and examine how social support offered by those living in one's home culture is an effective buffer against mental distress.

Prevencion del sida en jóvenes estudiantes / Aids prevention in young students

Se presentan los resultados de un Programa de prevención del sida llevado a cabo con jóvenes de una escuela media pública, de 4o. y 5o. años, en la ciudad de Buenos Aires. La evaluación del Programa tomó en cuenta los cambios registrados entre el momento previo a su implementación y el posterior a él, en las siguientes variables: información sobre anticoncepción, sida y ETS; percepción de riesgo de embarazo y de sida; creencias positivas y negativas referidas a la anticoncepción y al preservativo como profiláctico del sida; actitudes hacia la anticoncepción y hacia el preservativo; percepción de control en las relaciones sexuales; intención de conducta preventiva y representaciones sociales "conservadoras" y "liberales" en relación con el sida. La magnitud de los cambios encontrados fue baja, excepto en lo referido a las representaciones sociales acerca del sida, por lo que se sugiere profundizar en modelos que tomen más en cuenta las variables de la subcultura juvenil que pueden obstaculizar la adopción de conductas preventivas. (AU)

Prevencion del sida en jóvenes estudiantes / Aids prevention in young students

Se presentan los resultados de un Programa de prevención del sida llevado a cabo con jóvenes de una escuela media pública, de 4o. y 5o. años, en la ciudad de Buenos Aires. La evaluación del Programa tomó en cuenta los cambios registrados entre el momento previo a su implementación y el posterior a él, en las siguientes variables: información sobre anticoncepción, sida y ETS; percepción de riesgo de embarazo y de sida; creencias positivas y negativas referidas a la anticoncepción y al preservativo como profiláctico del sida; actitudes hacia la anticoncepción y hacia el preservativo; percepción de control en las relaciones sexuales; intención de conducta preventiva y representaciones sociales "conservadoras" y "liberales" en relación con el sida. La magnitud de los cambios encontrados fue baja, excepto en lo referido a las representaciones sociales acerca del sida, por lo que se sugiere profundizar en modelos que tomen más en cuenta las variables de la subcultura juvenil que pueden obstaculizar la adopción de conductas preventivas.