The relationship between body image and physical activity in African American women

High rates of overweight and obesity in African American women have been attributed, in part, to poor health habits, such as physical inactivity, and cultural influences on body image perceptions. The purpose of this study was to determine the relationship among body mass index (BMI=kg/m2), body image perception (perceived and desired) and physical activity, both self-reported and objectively measured. Anthropometric measures of BMI and Pulvers' culturally relevant body image, physical activity and demographic data were collected from 249 African American women in Houston. Women ( M = 44.8 yrs, SD = 9.5) were educated (53% college graduates) and were overweight (M = 35.0 kg/m2, SD = 9.2). Less than half of women perceived their weight correctly regardless of their actual weight (p < 0.001). Nearly three-fourths (73.9%) of women who were normal weight desired to be obese, and only 39.4% of women desired to be normal weight, regardless of actual or perceived weight. Women in all weight classes (normal, overweight and obese) varied in objective measures of physical activity (F(2,112) = 4.424, p = .014). Regression analyses showed objectively measured physical activity was significantly associated with BMI ( Beta = -2.45, p < .01) and self-reported walking was significantly associated with perceived BMI (Beta = -.156, p = .017). Results suggest African American women who are smaller want to be larger and African American women who are larger want to be smaller, revealing dichotomous distortion in body images. Low rates of physical activity may be a factor. Research is needed to increase physical activity levels in African American women, leading to improved satisfaction with normal weight as desirable for health and beauty. Supported by NCI (NIH) 1R01CA109403. ^

The association of internet use and depression among spinal cord injury population

The purpose of this study was to exam the relationship between internet use and depression among a population of individuals who have sustained spinal cord injury. This was cross-sectional survey design conducted among spinal cord injury (SCI) patients in the Model Spinal Cord Injury System. We included a total of 1,011 SCI-patients who were interviewed face-to-face or by telephone interview over approximately a three year time period (2004–2006). All data were collected through a telephone survey which included the Patient Health Questionnaire-9 (PHQ-9) to assess depression. We examined various scales of this survey, included a reduced 3-item scale (items 1, 2 and 6) to avoid the presence of somatic symptoms among SCI patients from influencing classification of depression. The frequency of internet usage was grouped as daily/weekly/monthly/non user. Covariates examined as possible confounders included demographic characteristics, occupational status, educational level, injury type, daily function of living, pain level, self-perceived health status and satisfaction with life. We observed a negative association between the frequency of internet use and the level of depression. Daily use of internet was associated with lower PHQ-9 score and depression; however this association did not reach statistical significance after for the mentioned covariates. In conclusion, the factors related to lower depression in SCI patients who use the internet are complicated. Daily internet usage was associated with lower levels of depression. The accuracy of 3-item scale needs further validation and investigation. Further study of internet usage pattern in SCI patient is recommended. ^

Doctor-patient communication in the medical interaction: Context, implications, and practice

Effective communication; whether from an interpersonal, mass media, or global perspective, is a critical component in public health. It is an essential conduit in increasing public awareness of available health resources, potential health hazards and related disease prevention strategies, and in delivering better health care. Within this context, available literature asserts doctor-patient communication as central to healthcare delivery. It has been shown to affect patient health outcomes, satisfaction with care, adherence to treatment recommendations, and even understanding of medical information. While research supports the essential imperative of interventions aimed at teaching doctors and patients the communication skills necessary for a successful and meaningful medical interaction, most interventions to date, focus on teaching these communication skills to doctors and seem to rely, largely, on mass media for providing patients with the information needed to increase communication efficacy. This study sought to fill a significant gap in the doctor-patient communication literature by reviewing the context of the doctor-patient exchange in the medical interaction, the implications of this exchange in resulting care of the patient, and the potential improvements to practice through interventions aimed at improving the communication exchange. Closing with an evaluation of a patient-centered communication intervention, the “How to Talk to Your Doctor” (HTTTYD) program that combines previously identified optimal strategies for improving communication between doctors and patients, this study examined the patients’ perspective of their potential as better communicators in the medical interaction. ^ Specific Aims, Hypotheses or Questions (Aim I) To examine the context of health communication within a public health framework and its relation to health care delivery. (Aim II) To review doctor-patient communication as a central focus within health care delivery and the resulting implications to patient care. (Aim III) To assess the utility of interventions to improve doctor-patient communication. Specifically, to evaluate the effectiveness of a patient-centered community education intervention, the “How to Talk to Your Doctor” (HTTTYD) program, aimed at improving patient communication efficacy.^

Improving the Quality of Life of spousal caregivers of stroke survivors: A cost effectiveness analysis

Back ground and Purpose. There is a growing consensus among health care researchers that Quality of Life (QoL) is an important outcome and, within the field of family caregiving, cost effectiveness research is needed to determine which programs have the greatest benefit for family members. This study uses a multidimensional approach to measure the cost effectiveness of a multicomponent intervention designed to improve the quality of life of spousal caregivers of stroke survivors. Methods. The CAReS study (Committed to Assisting with Recovery after Stroke) was a 5-year prospective, longitudinal intervention study for 159 stroke survivors and their spousal caregivers upon discharge of the stroke survivor from inpatient rehabilitation to their home. CAReS cost data were analyzed to determine the incremental cost of the intervention per caregiver. The mean values of the quality-of-life predictor variables of the intervention group of caregivers were compared to the mean values of usual care groups found in the literature. Significant differences were then divided into the cost of the intervention per caregiver to calculate the incremental cost effectiveness ratio for each predictor variable. Results. The cost of the intervention per caregiver was approximately $2,500. Statistically significant differences were found between the mean scores for the Perceived Stress and Satisfaction with Life scales. Statistically significant differences were not found between the mean scores for the Self Reported Health Status, Mutuality, and Preparedness scales. Conclusions. This study provides a prototype cost effectiveness analysis on which researchers can build. Using a multidimensional approach to measure QoL, as used in this analysis, incorporates both the subjective and objective components of QoL. Some of the QoL predictor variable scores were significantly different between the intervention and comparison groups, indicating a significant impact of the intervention. The estimated cost of the impact was also examined. In future studies, a scale that takes into account both the dimensions and the weighting each person places on the dimensions of QoL should be used to provide a single QoL score per participant. With participant level cost and outcome data, uncertainty around each cost-effectiveness ratio can be calculated using the bias-corrected percentile bootstrapping method and plotted to calculate the cost-effectiveness acceptability curves.^

Relating one's social support network to one's mid term grade

Much has been written about the relation of social support to health outcomes. Support networks were found to be predictive of health status. Not so clear was the manner in which social support helped the individual to avoid health complications. Whereas some aspects of the support network were protective, others were burdensome. Duties to one's network could serve as a stressor and duties outside one's network might stress the support system itself. Exposure to one's network was associated with certain health risks while disruption in one's social support network was associated with other health risks.^ Many factors contributed to the impact of a social support network upon the individual member: the characteristics of the individual, the individual's role or position within the network, qualities of the network and duties or indebtedness of the individual to the network. This investigation considered the possibility that performance could serve as a stressor in a fashion similar to an exposure to a health hazard.^ Because the literature includes many examples of studies in which the subjects were college students, academic progress is a performance common to most subjects. A profile of the support networks of successful students was contrasted with those of less successful students in this correlational study.^ What was uncovered in this investigation was a very complex web of interrelated constructs. Most aspects of the social support network did not significantly predict academic performance. Only a limited number of characteristics were associated with academic success: the frequency of support, student age, the existence of a 'mentor' within one' s network, and the extent to which one received a predominant source of support. Other factors had a tendency to be negatively correlated with midterm grade, suggesting those factors may impede academic performance.^ Medical status did not predict grades, but was correlated with many aspects of the network. Disruptions in particular parts of one's network were correlated with particular health categories. In fact, disruption in social support was more predictive of academic outcomes than medical complications. Whereas the individual's values were related to the contributing factors, only the individual's satisfaction with certain aspects of the support network were predictive of higher midterm grades in a psychology class. Dissatisfaction was associated with lower grades, suggesting a disruptive effect within the network. Associations among the features of support networks which predicted academic progress were considered. ^

Program evaluation for a summer science internship: Short and long term benefits as reported by interns

Undergraduate research programs have been used as a tool to attract and retain student interest in science careers. This study evaluates the short and long-term benefits of a Summer Science Internship (SSI) at the University of Texas Health Science Center at Houston– School of Public Health – in Brownsville, Texas, by analyzing survey data from alumni. Questions assessing short-term program impact were aimed at three main topics, student: satisfaction with program, self-efficacy for science after completing the program, and perceived benefits. Long-term program impact was assessed by looking at student school attendance and college majors along with perceived links between SSI and future college plans. Students reported high program satisfaction, a significant increase in science self-efficacy and high perceived benefits. At the time data were collected for the study, one-hundred percent of alumni were enrolled in school (high school or college). The majority of students indicated they were interested in completing a science major/career, heavily influenced by their participation in the program.^

Family Preservation: The Parents’ Perceptions

This research documents the perspective of 100 parents who had an open case with the Department of Children and Family Service’s (DCFS) regarding their family’s well-being, reasons for referral and satisfaction with services. Two DCFS services, Family Preservation (FP) and routine Family Maintenance (FM) were examined using standardized instruments. Parents’ responses regarding reasons for involvement with the system differed from DCFS administrative data. FP parents had more children, were more likely to be monolingual Spanish speakers, and perceived greater improvement in discipline and emotional care of children and housing than FM parents. FP parents reported being satisfied with services. Implications include supporting community based culturally competent FP programs.

Evaluating the Harris County TexHealth 3-Share Plan: An exploratory study

An important health issue in the United States today is the large number of people who have problems accessing needed health care because they lack health insurance coverage. Providing health insurance coverage for the working uninsured is a particularly significant challenge in Texas, which has the highest percentage of uninsured in the nation. In response to the low rate of employer-sponsored coverage in the Houston area and the growing numbers of uninsured, the Harris County Health Care Alliance (HCHA) developed and implemented the Harris County 3-Share Plan. A 3-Share Plan is not insurance, but provides health coverage in the form of a benefits package to employers who subscribe to the program and offer it to their employees. ^ A cross sectional study design was conducted to describe 3-Share employer and employee participants and evaluate their outcomes after its first year of operation. Between September and December 2011, 85% of employers enrolled in the 3-Share Plan completed a survey about the affordability of the 3-Share Plan, their satisfaction with the Plan, and the Plan's impact on employee recruitment, retention, productivity, and absenteeism. Forty-five percent of employees enrolled in the 3-Share Plan responded to a survey asking about the affordability of the 3-Share plan, accessibility of health care, availability of providers on the plan, health plan availability, utilization of primary care providers and the ER, and satisfaction with the plan. ^ A summary of the findings shows employers and employees say that they joined the plan because of the low-cost, and once they had participated in the Plan, the majority of employers and employees found that it is affordable for them. The majority of employees say they are getting access easily and without delay, but for those who aren't able to get access, or are delayed, the main cause is related to non-financial barriers to care. Ultimately, employees are satisfied with the 3-Share, and they plan to continue with health coverage under the 3-Share Plan. The 3-Share Plan will keep people in a system of care, and promote health, which will benefit the individuals, the businesses and the community of Harris County.^

Evaluating the Harris County TexHealth 3-Share plan: An exploratory study

An important health issue in the United States today is the large number of people who have problems accessing needed health care because they lack health insurance coverage. Providing health insurance coverage for the working uninsured is a particularly significant challenge in Texas, which has the highest percentage of uninsured in the nation. In response to the low rate of employer-sponsored coverage in the Houston area and the growing numbers of uninsured, the Harris County Health Care Alliance (HCHA) developed and implemented the Harris County 3-Share Plan. A 3-Share Plan is not insurance, but provides health coverage in the form of a benefits package to employers who subscribe to the program and offer it to their employees. ^ A cross sectional study design was conducted to describe 3-Share employer and employee participants and evaluate their outcomes after its first year of operation. Between September and December 2011, 85% of employers enrolled in the 3-Share Plan completed a survey about the affordability of the 3-Share Plan, their satisfaction with the Plan, and the Plan's impact on employee recruitment, retention, and productivity. Forty-five percent of employees enrolled in the 3-Share Plan responded to a survey asking about the affordability of the 3-Share plan, accessibility of providers on the plan, satisfaction, and utilization of primary care providers and the ER. ^ A summary of the findings shows employers and employees say that they joined the plan because of the low-cost, and once they had participated in the Plan, the majority of employers and employees found that it is affordable for them. The majority of employees say they are getting access easily and without delay, but for those who aren't able to get access, or are delayed, the main cause is related to non-financial barriers to care. Ultimately, employees are satisfied with the 3-Share, and they plan to continue with health coverage under the 3-Share Plan. The 3-Share Plan will keep people in a system of care, and promote health, which will benefit the individuals, the businesses and the community of Harris County.^

The impact of school year work on adolescent *development

In recent decades, work has become an increasingly common feature of adolescent life in the United States. Once assumed to be an inherently positive experience for youth, school year work has recently been associated with several adverse effects, especially as the number of hours of weekly work increases. The purpose of this dissertation was to describe the impact of school year work on adolescent development in a sample of high school students from rural South Texas, an area where economically-disadvantaged and Hispanic students are heavily represented.^ The first study described the prevalence and work circumstances of 3,565 10$\rm\sp{th}$ and 12$\rm\sp{th}$ grade students who responded to anonymous surveys conducted in regular classrooms. The overall prevalence of current work was 53%. Prevalence differed by grade, college-noncollege-bound status, and parent education. Fifty percent of employed students worked to support consumer spending.^ The second study examined the effects of four levels of work intensity on the academic, behavioral, social, mental and physical health of students. The following negative effects of intense work were reported: (1) decreased engagement in school, satisfaction with leisure time, and hours of weeknight and weekend sleep, and (2) increased health risk behaviors and psychological stress. The negative effects of intense work differed by gender, grade, ethnicity, but not by parent education.^ The third study described the prevalence of injury in the study population. A dose response effect was observed where increasing hours of weekly work were significantly related to work-related injury. The likelihood of being injured while employed in restaurant, farm/ranch, and construction work was greater than the probability of being injured while working in factory/office/skilled, yard, or retail work when compared to babysitting. Cuts, shocks/burns and sprains were the most common injuries in working teens.^ Students, parents, educators, health professionals and policymakers should continue to monitor the number of weekly hours that students work during the school year. ^

The association between academic achievement and health status among eighth -grade Hispanic students in Houston

This cross-sectional study examines the association between health and academic achievement among Hispanic eighth-grade students in the Houston Independent School District. As part of the district's 3 year Safe Schools/Healthy Students Initiative to enhance comprehensive educational programs, a brief anonymous questionnaire was administered in the classroom to 359 students in two schools during a one-month period in the early part of the 2001 school year. ^ The primary study questions are: Among this sample of Hispanic adolescents, is there a significant association between academic achievement and health status? and in this same population, is there a significant association between health risk behavior and health status? The specific aims of this research are: (1) to describe the association between academic achievement and health status; (2) to describe the association between health risk behaviors and health status; and (3) to describe the relative contribution of health risk behaviors and academic achievement to adolescent health status among this sample of Hispanic adolescents. ^ The survey instrument was a 32-item questionnaire that incorporated: several academic achievement questions measuring usual grades, school-related performance, attendance, student and perceived parental satisfaction with academic achievement, and educational aspirations; two health and quality of life scales measuring adolescent self-reported health; and specific measures of health risk behavior, e.g., frequency of tobacco cigarette smoking, alcohol and other drug use, aggression, and suicidal ideation and behavior that were incorporated from the national Youth Risk Behavior Survey. Questions pertaining to sexual behavior and pregnancy were omitted to comply with school district guidelines. ^ Analysis revealed that strong associations between academic achievement and health status and between health risk behaviors and health status were observed after controlling for the covariates. Eight factors were found to be significantly associated with poor health status: usual grades (low), academic performance (low), academic achievement beliefs (low), classroom and homework performance satisfaction (low), ever drinking alcohol (6 or more times), suicidality (ever thought about, planned for, or sought medical help after attempting suicide), gender (female), and age (15 years and older). (Abstract shortened by UMI.) ^

Hacia una aproximación multidimensional e innovadora de los pilares de la orientación vocacional

Se estudian cuestiones relativas a la elección de una carrera universitaria por alumnos que finalizan la educación secundaria. La hipótesis es que una complementación de enfoques que recupere dimensiones presentes en la teoría y en los instrumentos derivados, algunos de vieja data, permite anticipar una elección profesional satisfactoria. El objetivo general es analizar la viabilidad de conjugar principios y recursos de diferente origen psicológico-epistemológico, en una perspectiva holística y con proyección al plano aplicado. Para alcanzarlo se abordan cuali y cuantitativamente: intereses vocacionales y personalidad, globalmente considerados (variables independientes) en su relación con la elección de una carrera y se estima la capacidad de anticipar “una buena elección", medida por permanencia en la carrera, satisfacción y convicción de que se la volvería a elegir (variables dependientes). La fuente son registros documentales de procesos de Orientación y una entrevista de seguimiento habiendo transcurrido entre dos y seis años desde la elección. Es un estudio descriptivo, comparativo y en algunas instancias analiza correspondencias. Los resultados corroboran que la complementación de perspectivas e instrumentos sustenta una decisión vocacional que se caracteriza por la satisfacción con la elección, la permanencia en la carrera y la convicción de que se la volvería a elegir. Como corolario se resignifica la conceptualización de Orientación Vocacional sobre bases etimológicas y empíricas, en tanto proceso que realiza “quien se orienta" en cierta dirección.

A New Multidisciplinary Home Care Telemedicine System to Monitor Stable Chronic Human Immunodeficiency Virus-Infected Patients: A Randomized Study

BACKGROUND: Antiretroviral therapy has changed the natural history of human immunodeficiency virus (HIV) infection in developed countries, where it has become a chronic disease. This clinical scenario requires a new approach to simplify follow-up appointments and facilitate access to healthcare professionals. METHODOLOGY: We developed a new internet-based home care model covering the entire management of chronic HIV-infected patients. This was called Virtual Hospital. We report the results of a prospective randomised study performed over two years, comparing standard care received by HIV-infected patients with Virtual Hospital care. HIV-infected patients with access to a computer and broadband were randomised to be monitored either through Virtual Hospital (Arm I) or through standard care at the day hospital (Arm II). After one year of follow up, patients switched their care to the other arm. Virtual Hospital offered four main services: Virtual Consultations, Telepharmacy, Virtual Library and Virtual Community. A technical and clinical evaluation of Virtual Hospital was carried out. FINDINGS: Of the 83 randomised patients, 42 were monitored during the first year through Virtual Hospital (Arm I) and 41 through standard care (Arm II). Baseline characteristics of patients were similar in the two arms. The level of technical satisfaction with the virtual system was high: 85% of patients considered that Virtual Hospital improved their access to clinical data and they felt comfortable with the videoconference system. Neither clinical parameters [level of CD4+ T lymphocytes, proportion of patients with an undetectable level of viral load (p = 0.21) and compliance levels >90% (p = 0.58)] nor the evaluation of quality of life or psychological questionnaires changed significantly between the two types of care. CONCLUSIONS: Virtual Hospital is a feasible and safe tool for the multidisciplinary home care of chronic HIV patients. Telemedicine should be considered as an appropriate support service for the management of chronic HIV infection. TRIAL REGISTRATION: Clinical-Trials.gov: NCT01117675.

Integrated learning of computer applications for production engineering

A high productivity rate in Engineering is related to an efficient management of the flow of the large quantities of information and associated decision making activities that are consubstantial to the Engineering processes both in design and production contexts. Dealing with such problems from an integrated point of view and mimicking real scenarios is not given much attention in Engineering degrees. In the context of Engineering Education, there are a number of courses designed for developing specific competencies, as required by the academic curricula, but not that many in which integration competencies are the main target. In this paper, a course devoted to that aim is discussed. The course is taught in a Marine Engineering degree but the philosophy could be used in any Engineering field. All the lessons are given in a computer room in which every student can use each all the treated software applications. The first part of the course is dedicated to Project Management: the students acquire skills in defining, using Ms-PROJECT, the work breakdown structure (WBS), and the organization breakdown structure (OBS) in Engineering projects, through a series of examples of increasing complexity, ending up with the case of vessel construction. The second part of the course is dedicated to the use of a database manager, Ms-ACCESS, for managing production related information. A series of increasing complexity examples is treated ending up with the management of the pipe database of a real vessel. This database consists of a few thousand of pipes, for which a production timing frame is defined, which connects this part of the course with the first one. Finally, the third part of the course is devoted to the work with FORAN, an Engineering Production package of widespread use in the shipbuilding industry. With this package, the frames and plates where all the outfitting will be carried out are defined through cooperative work by the studens, working simultaneously in the same 3D model. In the paper, specific details about the learning process are given. Surveys have been posed to the students in order to get feed-back from their experience as well as to assess their satisfaction with the learning process. Results from these surveys are discussed in the paper

Semi-supervised subspace clustering and applications to neuroscience

Machine learning techniques are used for extracting valuable knowledge from data. Nowa¬days, these techniques are becoming even more important due to the evolution in data ac¬quisition and storage, which is leading to data with different characteristics that must be exploited. Therefore, advances in data collection must be accompanied with advances in machine learning techniques to solve new challenges that might arise, on both academic and real applications. There are several machine learning techniques depending on both data characteristics and purpose. Unsupervised classification or clustering is one of the most known techniques when data lack of supervision (unlabeled data) and the aim is to discover data groups (clusters) according to their similarity. On the other hand, supervised classification needs data with supervision (labeled data) and its aim is to make predictions about labels of new data. The presence of data labels is a very important characteristic that guides not only the learning task but also other related tasks such as validation. When only some of the available data are labeled whereas the others remain unlabeled (partially labeled data), neither clustering nor supervised classification can be used. This scenario, which is becoming common nowadays because of labeling process ignorance or cost, is tackled with semi-supervised learning techniques. This thesis focuses on the branch of semi-supervised learning closest to clustering, i.e., to discover clusters using available labels as support to guide and improve the clustering process. Another important data characteristic, different from the presence of data labels, is the relevance or not of data features. Data are characterized by features, but it is possible that not all of them are relevant, or equally relevant, for the learning process. A recent clustering tendency, related to data relevance and called subspace clustering, claims that different clusters might be described by different feature subsets. This differs from traditional solutions to data relevance problem, where a single feature subset (usually the complete set of original features) is found and used to perform the clustering process. The proximity of this work to clustering leads to the first goal of this thesis. As commented above, clustering validation is a difficult task due to the absence of data labels. Although there are many indices that can be used to assess the quality of clustering solutions, these validations depend on clustering algorithms and data characteristics. Hence, in the first goal three known clustering algorithms are used to cluster data with outliers and noise, to critically study how some of the most known validation indices behave. The main goal of this work is however to combine semi-supervised clustering with subspace clustering to obtain clustering solutions that can be correctly validated by using either known indices or expert opinions. Two different algorithms are proposed from different points of view to discover clusters characterized by different subspaces. For the first algorithm, available data labels are used for searching for subspaces firstly, before searching for clusters. This algorithm assigns each instance to only one cluster (hard clustering) and is based on mapping known labels to subspaces using supervised classification techniques. Subspaces are then used to find clusters using traditional clustering techniques. The second algorithm uses available data labels to search for subspaces and clusters at the same time in an iterative process. This algorithm assigns each instance to each cluster based on a membership probability (soft clustering) and is based on integrating known labels and the search for subspaces into a model-based clustering approach. The different proposals are tested using different real and synthetic databases, and comparisons to other methods are also included when appropriate. Finally, as an example of real and current application, different machine learning tech¬niques, including one of the proposals of this work (the most sophisticated one) are applied to a task of one of the most challenging biological problems nowadays, the human brain model¬ing. Specifically, expert neuroscientists do not agree with a neuron classification for the brain cortex, which makes impossible not only any modeling attempt but also the day-to-day work without a common way to name neurons. Therefore, machine learning techniques may help to get an accepted solution to this problem, which can be an important milestone for future research in neuroscience. Resumen Las técnicas de aprendizaje automático se usan para extraer información valiosa de datos. Hoy en día, la importancia de estas técnicas está siendo incluso mayor, debido a que la evolución en la adquisición y almacenamiento de datos está llevando a datos con diferentes características que deben ser explotadas. Por lo tanto, los avances en la recolección de datos deben ir ligados a avances en las técnicas de aprendizaje automático para resolver nuevos retos que pueden aparecer, tanto en aplicaciones académicas como reales. Existen varias técnicas de aprendizaje automático dependiendo de las características de los datos y del propósito. La clasificación no supervisada o clustering es una de las técnicas más conocidas cuando los datos carecen de supervisión (datos sin etiqueta), siendo el objetivo descubrir nuevos grupos (agrupaciones) dependiendo de la similitud de los datos. Por otra parte, la clasificación supervisada necesita datos con supervisión (datos etiquetados) y su objetivo es realizar predicciones sobre las etiquetas de nuevos datos. La presencia de las etiquetas es una característica muy importante que guía no solo el aprendizaje sino también otras tareas relacionadas como la validación. Cuando solo algunos de los datos disponibles están etiquetados, mientras que el resto permanece sin etiqueta (datos parcialmente etiquetados), ni el clustering ni la clasificación supervisada se pueden utilizar. Este escenario, que está llegando a ser común hoy en día debido a la ignorancia o el coste del proceso de etiquetado, es abordado utilizando técnicas de aprendizaje semi-supervisadas. Esta tesis trata la rama del aprendizaje semi-supervisado más cercana al clustering, es decir, descubrir agrupaciones utilizando las etiquetas disponibles como apoyo para guiar y mejorar el proceso de clustering. Otra característica importante de los datos, distinta de la presencia de etiquetas, es la relevancia o no de los atributos de los datos. Los datos se caracterizan por atributos, pero es posible que no todos ellos sean relevantes, o igualmente relevantes, para el proceso de aprendizaje. Una tendencia reciente en clustering, relacionada con la relevancia de los datos y llamada clustering en subespacios, afirma que agrupaciones diferentes pueden estar descritas por subconjuntos de atributos diferentes. Esto difiere de las soluciones tradicionales para el problema de la relevancia de los datos, en las que se busca un único subconjunto de atributos (normalmente el conjunto original de atributos) y se utiliza para realizar el proceso de clustering. La cercanía de este trabajo con el clustering lleva al primer objetivo de la tesis. Como se ha comentado previamente, la validación en clustering es una tarea difícil debido a la ausencia de etiquetas. Aunque existen muchos índices que pueden usarse para evaluar la calidad de las soluciones de clustering, estas validaciones dependen de los algoritmos de clustering utilizados y de las características de los datos. Por lo tanto, en el primer objetivo tres conocidos algoritmos se usan para agrupar datos con valores atípicos y ruido para estudiar de forma crítica cómo se comportan algunos de los índices de validación más conocidos. El objetivo principal de este trabajo sin embargo es combinar clustering semi-supervisado con clustering en subespacios para obtener soluciones de clustering que puedan ser validadas de forma correcta utilizando índices conocidos u opiniones expertas. Se proponen dos algoritmos desde dos puntos de vista diferentes para descubrir agrupaciones caracterizadas por diferentes subespacios. Para el primer algoritmo, las etiquetas disponibles se usan para bus¬car en primer lugar los subespacios antes de buscar las agrupaciones. Este algoritmo asigna cada instancia a un único cluster (hard clustering) y se basa en mapear las etiquetas cono-cidas a subespacios utilizando técnicas de clasificación supervisada. El segundo algoritmo utiliza las etiquetas disponibles para buscar de forma simultánea los subespacios y las agru¬paciones en un proceso iterativo. Este algoritmo asigna cada instancia a cada cluster con una probabilidad de pertenencia (soft clustering) y se basa en integrar las etiquetas conocidas y la búsqueda en subespacios dentro de clustering basado en modelos. Las propuestas son probadas utilizando diferentes bases de datos reales y sintéticas, incluyendo comparaciones con otros métodos cuando resulten apropiadas. Finalmente, a modo de ejemplo de una aplicación real y actual, se aplican diferentes técnicas de aprendizaje automático, incluyendo una de las propuestas de este trabajo (la más sofisticada) a una tarea de uno de los problemas biológicos más desafiantes hoy en día, el modelado del cerebro humano. Específicamente, expertos neurocientíficos no se ponen de acuerdo en una clasificación de neuronas para la corteza cerebral, lo que imposibilita no sólo cualquier intento de modelado sino también el trabajo del día a día al no tener una forma estándar de llamar a las neuronas. Por lo tanto, las técnicas de aprendizaje automático pueden ayudar a conseguir una solución aceptada para este problema, lo cual puede ser un importante hito para investigaciones futuras en neurociencia.