Propuesta de un sistema para detección precoz de trastornos del lenguaje en niños de 0 a 6 años

Las Tecnologías de la Información y las Comunicaciones han propiciado avances en el contexto de la salud tanto en la gestión efectiva de información socio‐sanitaria de forma electrónica, como en la provisión de servicios de e‐salud y telemedicina. Los antecedentes de investigación publicados en esta área corroboran este hecho presentando las mejoras experimentadas en la atención de la población y en la provisión de servicios sanitarios. La atención temprana, cuyos principios científicos se fundamentan en los campos de la pediatría, neurología, psicología, psiquiatría, pedagogía, fisiatría y lingüística, entre otros, tiene como finalidad ofrecer a los niños con déficit o con riesgo de padecerlos un conjunto de acciones optimizadoras y compensadoras, que faciliten su adecuada maduración en todos los ámbitos y que les permita alcanzar el máximo nivel de desarrollo personal y de integración social. La detección de posibles alteraciones en el desarrollo infantil es un aspecto clave de la atención temprana en la medida en que puede posibilitar la puesta en marcha de diversos mecanismos de actuación disponibles en las entidades implicadas, valiosos para la calidad de vida de la persona. Cuanto antes se realice la detección, existen mayores garantías de prevenir patologías añadidas, lograr mejoras funcionales y posibilitar un ajuste más adaptativo entre el niño y su entorno. El objetivo de la investigación presentada en esta tesis doctoral es analizar, diseñar, verificar y validar un sistema de información abierto, basado en conocimiento, que facilite efectivamente a los profesionales que trabajan con la población infantil entre 0 y 6 años la detección precoz de posibles trastornos del lenguaje. Desde el punto de vista metodológico, la Ingeniería del Conocimiento ofrece un marco conceptual sólido que permite desarrollar y validar Sistemas de Ayuda a la Toma de Decisiones distribuidos y escalables, capaces de ayudar al pediatra de Atención Primaria y al educador infantil en la detección precoz de posibles trastornos del lenguaje en niños. La evaluación del sistema se ha realizado de forma incremental mediante el diseño y validación de pruebas de campo experimentales consistentes en la evaluación de niños en dos escenarios distintos: la escuela infantil y el centro de atención temprana. Los experimentos realizados en poblaciones distintas con alrededor de 344 niños durante 2 años, han permitido contrastar la buena adecuación del sistema propuesto a las necesidades de detección de los profesionales que trabajan con niños entre 0 y 6 años. La tesis resultante ha permitido caracterizar el uso del sistema en entornos reales, conocer la aceptación entre los usuarios y su impacto en la provisión de un servicio de atención temprana como el descrito para el correcto seguimiento del desarrollo del lenguaje en los niños, además de proponer un nuevo modelo de atención y evaluación cooperativa que permita incrementar el conocimiento experimental existente al respecto. ABSTRACT The Information and Communication Technology have led to advances in the context of health both in the effective management of socio‐health information electronically, and in the provision of e‐health and telemedicine. The history of research published in this area confirm this fact by presenting the improvements in the care of the population and the provision of health services. Early attention, whose scientific principles are based on the fields of pediatrics, neurology, psychology, psychiatry, pedagogy, physical medicine and linguistics, among others, aims to provide children with deficits or risk of suffering a set of enhancer actions, which facilitate adequate maturation in all areas and allow them to achieve the highest level of personal development and social integration. The detection of possible changes in child development is a key aspect of early intervention to the extent that it can enable the implementation of different mechanisms of action available to the entities involved, valuable to the quality of life of the person. The earlier the detection is made, there are more guarantees added to prevent diseases, achieving functional improvements and enable a more adaptive fit between the child and his environment. The aim of the research presented is to analyze, design, verify and validate an open information system, based on knowledge, which effectively provide professionals working with the child population between 0 and 6 years, in processes of early detection of language disorders. From the methodological point of view, Knowledge Engineering provides a solid conceptual framework to develop and validate a distributed and scalable decision support systems aim to assist pediatricians and language therapists at early identification and referral of language disorder in childhood. The system evaluation was performed incrementally with the design and validation of consistent experimental field tests in the assessment of children in two different scenarios: the nursery and early intervention center. Experiments in different populations with about 344 children over 2 years, allowed to testing the adequacy of the proposed good detection needs of professionals working with children between 0 and 6 years old system. The resulting thesis has allowed to formalizing the system at real environments and to identifying the acceptance by users as well as its impact on the provision of an early intervention service, such as the one described for the proper monitoring of language development in children. In addition, it proposes a new model of care and cooperative evaluation that lets to increase the existing experimental knowledge about it.

Discrete Multi-Criteria Methods for lands use and conservation planning on La Colacha in Arroyos Menores (Río Cuarto, Province of Córdoba, Argentina)

The study area is La Colacha sub-basins from Arroyos Menores basins, natural areas at West and South of Río Cuarto in Province of Córdoba of Argentina, fertile with loess soils and monsoon temperate climate, but with soil erosions including regressive gullies that degrade them progressively. Cultivated gently since some hundred sixty years, coordinated action planning became necessary to conserve lands while keeping good agro-production. The authors had improved data on soils and on hydrology for the study area, evaluated systems of soil uses and actions to be recommended and applied Decision Support Systems (DSS) tools for that, and were conducted to use discrete multi-criteria models (MCDM) for the more global views about soil conservation and hydraulic management actions and about main types of use of soils. For that they used weighted PROMETHEE, ELECTRE, and AHP methods with a system of criteria grouped as environmental, economic and social, and criteria from their data on effects of criteria. The alternatives resulting offer indication for planning depending somehow on sub basins and on selections of weights, but actions for conservation of soils and water management measures are recommended to conserve the basins conditions, actually sensibly degrading, mainly keeping actual uses of the lands.

Tour virtual: una forma eficiente de realizar evaluaciones tempranas en aplicaciones de paciente

Tradicionalmente, los sistemas de ayuda a la decisión (Decision Support Systems, DSS) han estado dirigidos a los profesionales médicos; sin embargo también pueden ayudar a aquellos pacientes que desean tener un papel más activo en el cuidado de su salud. Además, los pacientes quieren ser tratados en el momento en que su estado de salud lo requiera, sin importar el lugar en el que se encuentren. El sistema MobiGuide proporciona un soporte personalizado y basado en evidencia clínica tanto a profesionales médicos como a pacientes en todo momento y en todo lugar. La aplicación móvil del paciente representa el punto de acceso al servicio y, por tanto, es responsable en gran medida del éxito o fracaso del sistema. En MobiGuide, se ha incorporado a los pacientes desde el comienzo en el proceso de diseño y evaluación de la aplicación para garantizar una adecuada funcionalidad y usabilidad del sistema. En este trabajo presentamos la primera evaluación realizada por los pacientes mediante un tour virtual por la Aplicación de Paciente. Los resultados son altamente positivos y útiles para mejorar la aplicación, corregir defectos y conseguir la aplicación final esperada por los pacientes.

Algorithm for the detection of outliers based on the theory of rough sets

Outliers are objects that show abnormal behavior with respect to their context or that have unexpected values in some of their parameters. In decision-making processes, information quality is of the utmost importance. In specific applications, an outlying data element may represent an important deviation in a production process or a damaged sensor. Therefore, the ability to detect these elements could make the difference between making a correct and an incorrect decision. This task is complicated by the large sizes of typical databases. Due to their importance in search processes in large volumes of data, researchers pay special attention to the development of efficient outlier detection techniques. This article presents a computationally efficient algorithm for the detection of outliers in large volumes of information. This proposal is based on an extension of the mathematical framework upon which the basic theory of detection of outliers, founded on Rough Set Theory, has been constructed. From this starting point, current problems are analyzed; a detection method is proposed, along with a computational algorithm that allows the performance of outlier detection tasks with an almost-linear complexity. To illustrate its viability, the results of the application of the outlier-detection algorithm to the concrete example of a large database are presented.

A Computational Architecture Based on RFID Sensors for Traceability in Smart Cities

Information Technology and Communications (ICT) is presented as the main element in order to achieve more efficient and sustainable city resource management, while making sure that the needs of the citizens to improve their quality of life are satisfied. A key element will be the creation of new systems that allow the acquisition of context information, automatically and transparently, in order to provide it to decision support systems. In this paper, we present a novel distributed system for obtaining, representing and providing the flow and movement of people in densely populated geographical areas. In order to accomplish these tasks, we propose the design of a smart sensor network based on RFID communication technologies, reliability patterns and integration techniques. Contrary to other proposals, this system represents a comprehensive solution that permits the acquisition of user information in a transparent and reliable way in a non-controlled and heterogeneous environment. This knowledge will be useful in moving towards the design of smart cities in which decision support on transport strategies, business evaluation or initiatives in the tourism sector will be supported by real relevant information. As a final result, a case study will be presented which will allow the validation of the proposal.

Parametric Cost Estimating module (PACE) : test version 1.00 /

"May 1991."

Contract appraisal system (CAPPS) : version 2.20 /

"January 1991."

Participatory approach for the identification of dairy industry needs in the design of research, development and extension actions: Australian and Brazilian case studies

In both Australia and Brazil there are rapid changes occurring in the macroenvironment of the dairy industry. These changes are sometimes not noticed in the microenvironment of the farm, due to the labour-intensive nature of family farms, and the traditionally weak links between production and marketing. Trends in the external environment need to be discussed in a cooperative framework, to plan integrated actions for the dairy community as a whole and to demand actions from research, development and extension (R, D & E). This paper reviews the evolution of R, D & E in terms of paradigms and approaches, the present strategies used to identify dairy industry needs in Australia and Brazil, and presents a participatory strategy to design R, D & E actions for both countries. The strategy incorporates an integration of the opinions of key industry actors ( defined as members of the dairy and associated communities), especially farm suppliers ( input market), farmers, R, D & E people, milk processors and credit providers. The strategy also uses case studies with farm stays, purposive sampling, snowball interviewing techniques, semi-structured interviews, content analysis, focus group meetings, and feedback analysis, to refine the priorities for R, D & E actions in the region.

A cognitive genetic algorithm for power distribution system planning

Power systems are large scale nonlinear systems with high complexity. Various optimization techniques and expert systems have been used in power system planning. However, there are always some factors that cannot be quantified, modeled, or even expressed by expert systems. Moreover, such planning problems are often large scale optimization problems. Although computational algorithms that are capable of handling large dimensional problems can be used, the computational costs are still very high. To solve these problems, in this paper, investigation is made to explore the efficiency and effectiveness of combining mathematic algorithms with human intelligence. It had been discovered that humans can join the decision making progresses by cognitive feedback. Based on cognitive feedback and genetic algorithm, a new algorithm called cognitive genetic algorithm is presented. This algorithm can clarify and extract human's cognition. As an important application of this cognitive genetic algorithm, a practical decision method for power distribution system planning is proposed. By using this decision method, the optimal results that satisfy human expertise can be obtained and the limitations of human experts can be minimized in the mean time.

Knowledge management: a review of the field and of OR's contribution

This paper examines the field of knowledge management (KM) and identifies the role of operational research (OR) in key milestones and in KM's future. With the presence of the OR Society journal Knowledge Management Research and Practice and with the INFORMS journal Organization Science, OR may be assumed to have an explicit and a leading role in KM. Unfortunately, the origins and the evidence of recent research efforts do not fully support this assumption. We argue that while OR has been inside many of the milestones there is no explicit recognition of its role and while OR research on KM has considerably increased in the last 5 years, it still forms a rather modest explicit contribution to KM research. Nevertheless, the depth of OR's experience in decision-making models and decision support systems, soft systems with hard systems and in risk management suggests that OR is uniquely placed to lead future KM developments. We suggest that a limiting aspect of whether OR will be seen to have a significant profile will be the extent to which developments are recognized as being informed by OR.

Uncertainty and topographic visualisations

This thesis is a study of low-dimensional visualisation methods for data visualisation under certainty of the input data. It focuses on the two main feed-forward neural network algorithms which are NeuroScale and Generative Topographic Mapping (GTM) by trying to make both algorithms able to accommodate the uncertainty. The two models are shown not to work well under high levels of noise within the data and need to be modified. The modification of both models, NeuroScale and GTM, are verified by using synthetic data to show their ability to accommodate the noise. The thesis is interested in the controversy surrounding the non-uniqueness of predictive gene lists (PGL) of predicting prognosis outcome of breast cancer patients as available in DNA microarray experiments. Many of these studies have ignored the uncertainty issue resulting in random correlations of sparse model selection in high dimensional spaces. The visualisation techniques are used to confirm that the patients involved in such medical studies are intrinsically unclassifiable on the basis of provided PGL evidence. This additional category of ‘unclassifiable’ should be accommodated within medical decision support systems if serious errors and unnecessary adjuvant therapy are to be avoided.

Cues and knowledge structures used by mental-health professionals when making risk assessments

Background: Research into mental-health risks has tended to focus on epidemiological approaches and to consider pieces of evidence in isolation. Less is known about the particular factors and their patterns of occurrence that influence clinicians’ risk judgements in practice. Aims: To identify the cues used by clinicians to make risk judgements and to explore how these combine within clinicians’ psychological representations of suicide, self-harm, self-neglect, and harm to others. Method: Content analysis was applied to semi-structured interviews conducted with 46 practitioners from various mental-health disciplines, using mind maps to represent the hierarchical relationships of data and concepts. Results: Strong consensus between experts meant their knowledge could be integrated into a single hierarchical structure for each risk. This revealed contrasting emphases between data and concepts underpinning risks, including: reflection and forethought for suicide; motivation for self-harm; situation and context for harm to others; and current presentation for self-neglect. Conclusions: Analysis of experts’ risk-assessment knowledge identified influential cues and their relationships to risks. It can inform development of valid risk-screening decision support systems that combine actuarial evidence with clinical expertise.

A method for automatically eliciting node weights in a hierarchical knowledge-based structure for reasoning with uncertainty

Hierarchical knowledge structures are frequently used within clinical decision support systems as part of the model for generating intelligent advice. The nodes in the hierarchy inevitably have varying influence on the decisionmaking processes, which needs to be reflected by parameters. If the model has been elicited from human experts, it is not feasible to ask them to estimate the parameters because there will be so many in even moderately-sized structures. This paper describes how the parameters could be obtained from data instead, using only a small number of cases. The original method [1] is applied to a particular web-based clinical decision support system called GRiST, which uses its hierarchical knowledge to quantify the risks associated with mental-health problems. The knowledge was elicited from multidisciplinary mental-health practitioners but the tree has several thousand nodes, all requiring an estimation of their relative influence on the assessment process. The method described in the paper shows how they can be obtained from about 200 cases instead. It greatly reduces the experts’ elicitation tasks and has the potential for being generalised to similar knowledge-engineering domains where relative weightings of node siblings are part of the parameter space.

An investigation into inductive parameter learning in complex hierarchical knowledge structures representing clinical expertise

This dissertation investigates the very important and current problem of modelling human expertise. This is an apparent issue in any computer system emulating human decision making. It is prominent in Clinical Decision Support Systems (CDSS) due to the complexity of the induction process and the vast number of parameters in most cases. Other issues such as human error and missing or incomplete data present further challenges. In this thesis, the Galatean Risk Screening Tool (GRiST) is used as an example of modelling clinical expertise and parameter elicitation. The tool is a mental health clinical record management system with a top layer of decision support capabilities. It is currently being deployed by several NHS mental health trusts across the UK. The aim of the research is to investigate the problem of parameter elicitation by inducing them from real clinical data rather than from the human experts who provided the decision model. The induced parameters provide an insight into both the data relationships and how experts make decisions themselves. The outcomes help further understand human decision making and, in particular, help GRiST provide more accurate emulations of risk judgements. Although the algorithms and methods presented in this dissertation are applied to GRiST, they can be adopted for other human knowledge engineering domains.