Search

Proceeding paper [Abstract] Information extracted from electronic health records (EHRs) is used for predictive tasks and clinical pattern recognition. Machine learning techniques also allow the extraction of knowledge from EHR. This study is a continuation of previous work in which EHRs were exploited to make predictions about patients with respiratory diseases. In this study, we will try to predict the recurrence of patients with respiratory diseases using four different machine learning algorithms. Centro de Investigación de Galicia CITIC and Campus Innova (agreement I+D+ 2019-20) is funded by Consellería de Educación, Universidade e Formación Profesional from Xunta de Galicia and European Union (European Regional Development Fund - FEDER Galicia 2014-2020 Program) by grant ED431G 2019/01 and Universidade da Coruña. Partially supported by the Spanish Ministry of Science (Challenges of Society 2019) PID2019-104323RB-C33 Xunta de Galicia; ED431G 2019/01

[Abstract] This study evaluated the antioxidative effects of magnolol based on the mouse model induced by Enterotoxigenic Escherichia coli (E. coli, ETEC). All experimental mice were equally treated with ETEC suspensions (3.45×109 CFU/ml) after oral administration of magnolol for 7 days at the dose of 0, 100, 300 and 500 mg/kg Body Weight (BW), respectively. The oxidative metabolites and antioxidases for each sample (organism of mouse) were determined: Malondialdehyde (MDA), Nitric Oxide (NO), Glutathione (GSH), Myeloperoxidase (MPO), Catalase (CAT), Superoxide Dismutase (SOD), and Glutathione Peroxidase (GPx). In addition, we also determined the corresponding mRNA expressions of CAT, SOD and GPx as well as the Total Antioxidant Capacity (T-AOC). The experiment was completed with a theoretical study that predicts a series of 79 ChEMBL activities of magnolol with 47 proteins in 18 organisms using a Quantitative Structure- Activity Relationship (QSAR) classifier based on the Moving Averages (MAs) of Rcpi descriptors in three types of experimental conditions (biological activity with specific units, protein target and organisms). Six Machine Learning methods from Weka software were tested and the best QSAR classification model was provided by Random Forest with True Positive Rate (TPR) of 0.701 and Area under Receiver Operating Characteristic (AUROC) of 0.790 (test subset, 10-fold crossvalidation). The model is predicting if the new ChEMBL activities are greater or lower than the average values for the magnolol targets in different organisms. National Natural Science Foundation of China; 30972166 Hunan Provincial Education Department; 08A031 Hunan Provincial Innovation Foundation for Postgraduate; CX2011B304 Hunan Provincial Innovation Foundation for Postgraduate; CX2014B300 Xunta de Galicia; R2014/039 Xunta de Galicia; GRC2014/049 Ministerio de Economía y Competitividad; UNLC08-1E-002 Ministerio de Economía y Competitividad; UNLC13-13-3503

The physical rehabilitation community has been demonstrating serious interest for therapeutic serious games (theragames). The paper presents a framework for theragames enriched by a natural user interface (NUI) and materialized by Kinect. A set of 3D virtual reality (VR) scenarios motivate patients to perform upper limb rehabilitation and provide armmotion metrics in an unobtrusive way. The measurements are verified using a set of wearable inertial measurement units (IMU) attached to the upper limbs. The framework is planned to be included as part of a remote physiotherapy service that may improve the physical rehabilitation process. Experimental results and appropriate data processing is included in the paper.

The International Classification of Functioning, Disability and Health (ICF) (WHO, 2001) provides the term disability as a part of the multi-aspects of the interaction between the individual and social environmental context in which it operates. Therefore a disabled person is a person who has impairment, activity limitation or participation restriction. A person in this situation can present difficulties in occupational performance. It is necessary to develop a set of resources, technological or otherwise, to offset these difficulties, decrease the distance between exclusion and participation and contribute to the integration of people with functional diversity in society. These resources are called support products or technology support, but do not eliminate the deficits, they can eliminate the limitation of the performance of persons with disabilities.

Introduction: It was observed that technology developers expressed a clear interest to design programs that meet the needs of individuals with Autism Spectrum Disorder (ASD). Several authors indicate that any software designed for people with ASD has to include special requirements in the design. Methodology: This research study describes a software for children with ASD named Module ASD and describes the interactive process of design that it was followed. This research focuses on a software development and the design process, based on scientific evidence study, consultation and tests done by specialists, children with ASD and their families. The techniques used to formalize the collection of information from different groups of participants were: observation, interview, group discussions and field book. Results: The ASD Module is the result of the study and it is a free technological application that is made up of a set of virtual keyboards (or adapted interfaces), digital schedules and activities, especially designed and tested by and for children with ASD. The application is included in the In-TIC PC software. The software is available for the Windows operating system and was implemented with the Visual Studio development tool, .NET environment, C# programming language and Windows Form technology. Other materials used for content development were the Interactive Books Multimedia (LIM according to the Spanish acronym) software and the ARASAAC pictograms. Discussion and conclusions: The results show that the digital content can be oriented to promote independence in several daily activities (ADL, education, leisure and social participation). This technology design provides useful information for researchers, developers, social and healthcare professionals and families, with the aim of offering alternatives for children with ASD and facilitating the understanding of daily life. SciForum

In 1999, the 1451.1 standard, which defines a common object model and interface specification to develop open multivendor distributed measurement and control systems, was published. However, despite the well-known advantages of the model, there have been a few initiatives to implement a commercial version of the standard. In this paper, we describe the implementation of a network capable application processor (NCAP) in a well-known and well-proven infrastructure, i.e., the microsoft .NET framework. The use of a commercial framework increases productivity because it handles low-level programming details and provides good development tools, which allows us to produce a reusable and robust code. In addition, a solution to enhance the 1451.1 Standard is presented by proposing a new format for interNCAP communication based on eXtended Markup Language (XML) Web Services. This approach promotes interoperability because any device with a compatible Web Service middleware can locate and communicate with our prototype.

Epigenetics is the study of heritable changes in gene expression resulting from modifications in chromatin structure, without involving changes in the genetic information stored in DNA. In addition to their critical role in regulating cell differentiation and development, epigenetic modifications have also been linked to human diseases, most notably cancer. Epigenetic analyses often require the integration of disparate and heterogeneous data, often combining molecular biology and bioinformatic approaches. The fast development of high-throughput sequencing technologies has boosted epigenetic data production dramatically, posing challenges for information management that require innovative and efficient computational approaches. In this chapter, we review the data types most commonly used in epigenetic studies and the computational approaches for their integrative analysis, especially in the field of medicine. Additionally, online data resources and worldwide standardization consortia have established the purpose of optimizing the efficiency of epigenetics, with special emphasis given to the collective efforts in organizing and connecting molecular and clinical information.

Qualitatively enhanced access to data collections requires a more meaningful interface which endows the users with personal agents that are easily adaptable to the users' individual retrieval preferences. Tracking individual needs of users leads to personal digital assistance that appears in the system's interaction mode as the user's personal software agent. The main objective of personal assistance as envisaged here is enabling the system to give the users recommendations that are derived from best practive in information search processes. Best practice reflects the knowledge about how users perform successful retrieval activities and attempt to define the best ways of searching large document collections. Best practices are developed on an individual as well as on a community base. The model presented here was developed for the information system IRAIA, a portal for economic information from huge data collections of Economic Research Institutes (ERI) and National Statistical Institutions (NSI). The personal agent draws on IRAIA's model of context-oriented retrieval and observe, record and analye the users' search and navigation by applying concepts of the respective taxonomies.

[Abstract] 1H-MRS variability increases due to normal aging and also as a result of atrophy in grey and white matter caused by neurodegeneration. In this work, an automatic process was developed to integrate data from spectra and high-resolution anatomical images to quantify metabolites, taking into account tissue partial volumes within the voxel of interest avoiding additional spectra acquisitions required for partial volume correction. To evaluate this method, we use a cohort of 135 subjects (47 male and 88 female, aged between 57 and 99 years) classified into 4 groups: 38 healthy participants, 20 amnesic mild cognitive impairment patients, 22 multi-domain mild cognitive impairment patients, and 55 Alzheimer's disease patients. Our findings suggest that knowing the voxel composition of white and grey matter and cerebrospinal fluid is necessary to avoid partial volume variations in a single-voxel study and to decrease part of the variability found in metabolites quantification, particularly in those studies involving elder patients and neurodegenerative diseases. The proposed method facilitates the use of 1H-MRS techniques in statistical studies in Alzheimer's disease, because it provides more accurate quantitative measurements, reduces the inter-subject variability, and improves statistical results when performing group comparisons.

In biomedical informatics, ontologies are considered a key technology for annotating, retrieving and sharing the huge volume of publicly available data. Due to the increasing amount, complexity and variety of existing biomedical ontologies, choosing the ones to be used in a semantic annotation problem or to design a specific application is a difficult task. As a consequence, the design of approaches and tools addressed to facilitate the selection of biomedical ontologies is becoming a priority. In this paper we present BiOSS, a novel system for the selection of biomedical ontologies. BiOSS evaluates the adequacy of an ontology to a given domain according to three different criteria: (1) the extent to which the ontology covers the domain; (2) the semantic richness of the ontology in the domain; (3) the popularity of the ontology in the biomedical community. BiOSS has been applied to 5 representative problems of ontology selection. It also has been compared to existing methods and tools. Results are promising and show the usefulness of BiOSS to solve real-world ontology selection problems. BiOSS is openly available both as a web tool and a web service. Instituto de Salud Carlos III; FIS-PI10/02180 Galicia. Consellería de Cultura, Educación e Ordenación Universitaria; CN2012/217 Galicia. Consellería de Cultura, Educación e Ordenación Universitaria; CN2011/034 Galicia. Consellería de Cultura, Educación e Ordenación Universitaria; CN2012/211 Programa Iberoamericano de Ciencia y Tecnología para el Desarrollo; ref. 209RT0366

[Abstract] Physicians in the Intensive Care Unit (ICU) are specially trained to deal constantly with very large and complex quantities of clinical data and make quick decisions as they face complications. However, the amount of information generated and the way the data are presented may overload the cognitive skills of even experienced professionals and lead to inaccurate or erroneous actions that put patients’ lives at risk. In this paper, we present the design, development, and validation of iOSC3, an ontology-based system for intelligent supervision and treatment of critical patients with acute cardiac disorders. The system analyzes the patient’s condition and provides a recommendation about the treatment that should be administered to achieve the fastest possible recovery. If the recommendation is accepted by the doctor, the system automatically modifies the quantity of drugs that are being delivered to the patient. The knowledge base is constituted by an OWL ontology and a set of SWRL rules that represent the expert’s knowledge. iOSC3 has been developed in collaboration with experts from the Cardiac Intensive Care Unit (CICU) of the Meixoeiro Hospital, one of the most significant hospitals in the northwest region of Spain. Instituto de Salud Carlos III; FIS-PI10/02180 Programa Iberoamericano de Ciencia y Tecnología para el Desarrollo; 209RT0366 Galicia. Consellería de Cultura, Educación e Ordenación Universitaria; CN2012/217 Xunta. Consellería de Cultura, Educación e Ordenación Universitaria; CN2011/034 Galicia. Consellería de Cultura, Educación e Ordenación Universitaria; CN2012/211

Selected paper of the 16th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems, 2012 September 10-12, San Sebastian, Spain [Abstract] When a patient enters an intensive care unit (ICU), either after surgery or due to a serious clinical condition, his vital signs are continually changing, forcing the medical experts to make rapid and complex decisions, which frequently imply modifications on the dosage of drugs being administered. Life of patients at critical units depends largely on the wisdom of such decisions. However, the human factor is sometimes a source of mistakes that lead to incorrect or inaccurate actions. This work presents an expert system based on a domain ontology that acquires the vital parameters from the patient monitor, analyzes them and provides the expert with a recommendation regarding the treatment that should be administered. If the expert agrees, the system modifies the drug infusion rates being supplied at the infusion pumps in order to improve the patient's physiological status. The system is being developed at the IMEDIR Center (A Coruña, Spain) and it is being tested at the cardiac intensive care unit (CICU) of the Meixoeiro Hospital (Vigo, Spain), which is a specific type of ICU exclusively aimed to treat patients who have underwent heart surgery or that are affected by a serious coronary disorder. Instituto de Salud Carlos III; FIS-PI10/02180 Programa Iberoamericano de Ciencia y Tecnología para el Desarrollo; ref. 209RT0366 Galicia. Consellería de Cultura, Educación e Ordenación Universitaria; CN2012/217 Galicia. Consellería de Cultura, Educación e Ordenación Universitaria; CN2011/034 Galcia. Consellería de Cultura, Educación e Ordenación Universitaria; CN2012/211

[Abstract] Ontology matching consists of finding the semantic relations between different ontologies and is widely recognized as an essential process to achieve an adequate interoperability between people, systems or organizations that use different, overlapping ontologies to represent the same knowledge. There are several techniques to measure the semantic similarity of elements from separate ontologies, which must be adequately combined in order to obtain precise and complete results. Nevertheless, combining multiple similarity measures into a single metric is a complex problem, which has been traditionally solved using weights determined manually by an expert, or through general methods that do not provide optimal results. In this paper, a genetic algorithms based approach to aggregate different similarity metrics into a single function is presented. Starting from an initial population of individuals, each one representing a combination of similarity measures, our approach allows to find the combination that provides the optimal matching quality. Instituto de Salud Carlos III; FISPI10/02180 Programa Iberoamericano de Ciencia y Tecnología para el Desarrollo; 209RT0366 Xunta de Galicia; CN2012/217 Xunta de Galicia; CN2011/034 Xunta de Galicia; CN2012/211

In this chapter, we state an evolution of the Recurrent ANN (RANN) to enforce the persistence of activations within the neurons to create activation contexts that generate correct outputs through time. In this new focus we want to file more information in the neuron’s connections. To do this, the connection’s representation goes from the unique values up to a function that generates the neuron’s output. The training process to this type of ANN has to calculate the gradient that identifies the function. To train this RANN we developed a GA based system that finds the best gradient set to solve each problem.

In this paper we present work-in-progress - a technology platform for Social Collaboration in the context of Personalized Information Extraction. In particular, we consider elements of user-centered software engineering as it converges on the development of folksonomies. Results from our work-in-progress demonstrate to what extent non-IT users can apply natural language when managing their IT-based processes addressing information integration. We concentrate on the language model that supports the development of process-related folksonomies in the context of retrieving and merging textual information from different sources concerning legal documents. Findings in our work-in-progress underpin the conjecture that the computational nature of natural language overcomes the inherent problem of ambiguity when applied in a collaboration context that the users are aware of.

[Abstract] The purpose of the study was to determine the use of computers and assistive devices amongst children with cerebral palsy (CP) and establish the satisfaction level of both users and educational staff. The study was carried out with 30 children with cerebral palsy. A questionnaire was designed to characterize the use of new technologies and assistive devices. Some of the questions were reserved for the teachers. Even though 29 users show some type of communication difficulty, only 4 users dispose of a computer-aided communication device, with the static symbolic board being the most widely used device (4). More than half of the participants (17) regularly use a computer, 16 of them requiring some type of assistive device. The perception of the teachers with regard to the use of Information and Communications Technologies (ICTs) in the classrooms is positive in 5 out of 6 cases. ICTs only provide assistance if their application is accompanied by the involvement of professionals and the child's social environment. The low use of Augmentative and Alternative Communication techniques along with the absence of communication codes reveal the need to establish training protocols. The inclusion of social, physical, and personal factors is considered essential in order to evaluate the needs for assistive technology.

This paper presents a recommender system for contextual targeted advertisement in Video-on-demand scenarios. The proposal arises from a real case of a Japanese company planning to add advertisement to its On-Demand IPTV services. The advertisements consist of icon or text-based links that may be shown before, during or after the playing of the film the customer has selected to watch. The goal of the company is to maximize the number of times customers follow the links to advertised sites because its revenues depends on this. Since only a small portion of the advertising links can be included in a movie, these must be selected carefully. This work proposes a recommender system for selecting the most appropriate advertisement for a certain customer based on the success the advertisement has had in the past among other customers having similar preferences. The paper describes the proposed method, shows the implementation work done so far and describes the remaining work in order to test it in the real scenario.

In recent years, ontologies have become an essential tool to structure and reuse the exponential growth of information in the Web. As the number of publicly available ontologies increases, researchers face the problem of finding the ontology (or ontologies) which provides the best coverage for a particular context. In this paper, we propose an approach to automatically recommend the best ontology for an initial set of terms. The approach is based on measuring the adequacy of the ontology according to three different criteria: (1) How well the ontology covers the given terms, (2) the semantic richness of the ontology and, importantly, (3) the popularity of the ontology in the Web 2.0. In order to evaluate this approach, we implemented a prototype to recommend ontologies in the biomedical domain. Results show the importance of using collaborative knowledge in the field of ontology recommendation.

A technique is described in this chapter that makes it possible to extract the knowledge held by previously trained artificial neural networks. This makes it possible for them to be used in a number of areas (such as medicine) where it is necessary to know how they work, as well as having a network that functions. This chapter explains how to carry out this process to extract knowledge, defined as rules. Special emphasis is placed on extracting knowledge from recurrent neural networks, in particular when applied in predicting time series.

This paper dedicates a particular attention to pulse-width modulation (PWM) analog-to-digital ( A/D) conversion techniques underlining their importance in smart sensing systems. Nowadays, smart sensing systems and advanced signal processing techniques can improve measuring system's performance and flexibility relaxing hardware specifications and associated cost. The integration of sensing units, conditioning circuitry and A/D conversion is becoming trivial in a large number of instrumentation and measurement applications. In a large number of systems, linearization is generally required because most sensors have an intrinsic nonlinear characteristic or the presence of influence variables makes their characteristic nonlinear over its measuring range. Fortunately, digitalization and linearization can be performed in a single step nearby the transducer in smart sensing systems. A possible solution to achieve this goal is based on a PWM scheme for nonlinear A/D conversion. The proposed A/D conversion method is easily implemented in low-cost microcontrollers that generally include comparator inputs and PWM outputs. The input voltage range can be divided in several intervals and the nonlinearity profile of the A/D in each interval can be dynamically adapted if results from calibration or auto-calibration are available even when hysteresis effects are present. The paper includes some simulation results obtained with MATLAB and an experimental result of a strain gage system linearization is also presented in the final part of the paper.

The field of Medical Informatics is currently experiencing increasing demands for new models of the Picture Archiving and Communication Systems (PACS) and Digital Imaging and Communications in Medicine (DICOM) protocols. Despite of the considerable advantages of current systems, implementation in hospitals is remarkably slow, due primarily to difficulties in integration and relatively high costs. Even though the success of DICOM standards has greatly contributed to the development of PACS, many hospitals remain unable to support it or to make full use of its potential because various imaging modalities in use at these sites generate images that cannot be stored in the PACS and cannot be managed in a centralized manner without DICOM standardization modules. Furthermore, the imaging modalities being used in such smaller centers are expensive and unlikely to be replaced, making DICOM compliance untenable. With this in mind, this paper describes the design, development, and implementation of a management system for medical diagnostic imaging, based on the DICOM standard and adapted to the needs of a small hospital. The system is currently being implemented in the San Rafael Hospital at A Coruna in Spain, and integrated with the existing hospital information system (HIS). We have studied the networking infrastructure of the hospital and its available image generation devices, and have subsequently carried out a series of measurements including transmission times, image file size, compression ratios, and many others that allow us to analyze the behavior of the system. Results obtained from these investigations demonstrate both the flexibility of using such a "small-hospital" DICOM-based framework as well as the relative cost-effectiveness of the system. In this regard, the approach, described herein, might serve as a model for other small, and possibly mid-sized, medical centers.

Component-based approaches to elaborate software must deal with the fact that in practical settings, components information may be incomplete, imprecise and uncertain, and requirements may be likewise. Architects wanting to evaluate candidate architectures regarding requirements satisfaction need to use whatever information be available about components, however imperfect. Imperfect information can be dealt with using specialized analytical formalisms, such as fuzzy values for imprecision and rough sets for incompleteness; but if used, evaluations need to compare and rank using non-scalar, non-symbolic values. This article presents an approach to systematically describe components’ imperfect information, and to evaluate and rank whole component assemblies, by using credibility values-based “support scores” that aggregate imperfect information about requirements, mechanisms and components. The approach builds on the Azimut framework, which offers progressive refinement of architectural entities via architectural policies, architectural mechanisms, components, and component assemblies. An example of the proposed approach and “what-if” analysis are illustrated.

Universally available services, which communicate in a standardized way, can provide a new generation of middleware. Harnessing the advantages of this promising middleware technology, however, means to be capable to understand and to handle its design language which emerges from standards like SOAP, WSDL, BPEL, etc. These languages are necessary for finding, composing and orchestrating web services. If at all, only IT experts are familiar with these languages.The key actors, the domain experts of business processes, however, are not IT experts, and thus do not become the main designers. WS-Talk is a research project that encourages the co-existence of Natural Language and Web service technology. It reinforces the role of domain experts in designing business processes without having to resort to their IT colleagues. In our approach business process experts write storybooks in their own language. Their instructions are matched with semantics that represent application logic that, in turn, supports the automatic composition of software components. The WS-Talk products currently support organizations in managing their own and individual information, i.e. to set up their own enterprise search engine.

This article presents the architecture and implementation of an information system for medical data and images. Thanks to a modular and flexible design, it can be implanted in hospital environments with various kinds of communication infrastructures (going from very low bandwidth lines (RTC of 56 Kb) to high capacity lines (ATM of 155 Mb)). Both its design and combination of small functional modules with a well defined entry/exit interface allows us to implement the functionalities required by the users. A database stores not only the information but also the specialist's reports and notes concerning patients and diagnoses. We have incorporated tools that are not found in conventional systems (image segmentation, advanced visualization, etc.) but which allow us to incorporate new data to the decision-making process. The user accesses the system with all its information and functionalities via a user-friendly web interface.

Presents the structure of an information system for medical data and images. Thanks to a modular and flexible design, it can be implanted in hospital environments with various kinds of communication infrastructures to high capacity lines. Both its design and combination of small functional modules with a well defined entry/exit interface allows us to implement the functionalities required by the users. A database stores not only the information but also the specialist's reports and notes concerning patients and diagnoses. We have incorporated tools that are not found in conventional systems (image segmentation, advanced visualization, etc.) to assist the physicians in analysis of images and which allow us to incorporate new data into the decision-making process. The user accesses the system with all its information and functionalities via a user-friendly Web interface.

Advances in telemedicine technology have led to intelligent monitoring systems that are capable of helping medical experts in their decision-making process. These systems imply the introduction of a bed-side computer that supervises the patient and collects, stores and visualizes all the information provided by the medical devices in an accessible way. This paper describes the telemedicine system that is currently being developed by our research team for the intelligent telemonitoring of patients at an intensive care unit (ICU). Concretely, the paper focuses on our 3D visualization module, which shows a virtual model of the patient and allows the clinical staff to visualize the patient's evolution in a rapid and clear manner.

The implementation of an Information System of medical images with safe Internet access and with an interface which allows visualization, analysis, processing and advanced visualization, will enable the radiologist to access those clinical cases he wishes to consult, both within the hospital Intranet and also from an extranet. Freeware software has been used for its implementation and the analysis, processing and advanced visualization module is easily integrated in the existing equipment of the organization. This system also allows for the production of multi-centre epidemiological studies. An analysis of radiological data from patients with head and neck cancer were carried out in order to validate the system. This system has automatic link devices with the medical modality equipment for a safe and restricted acquisition, storing, and access. This allows its integration within the existing RIS at the medical centres.

This article describes a system for the acquisition, storage and secure remote access to information generated by a hospital's devices for image diagnosis. The system allows the experts of a medical centre to recover and manage information. Our solution also makes it possible to obtain more elaborate results, thanks to the implemented functionalities of image analysis (edge detectors, clustering algorithms, etc.) and the storage of historical diagnosis results that give a certain experience to the application.

Component-based software elaboration becomes unwieldy for some practical situations with large numbers of components for which information is imperfect (incomplete, imprecise and/or uncertain). This article addresses the problem of identifying “interesting” component sets for some given non-functional requirements (NFRs), using imperfect information about large number of components. Rather than providing completely specified solutions, this approach allows architects to identify and compare whole assemblies, and focus eventual information- improvement efforts only on those components that are part of candidate assemblies. The proposed technique builds on the Azimut layered architectural abstractions, adapting an algorithmic approach used to mine association rules, and taking three parameters: a minimal “support score” that candidate assemblies must meet, and two credibility-value thresholds about the catalog themselves. An example illustrates the approach.

The evolution in information and telecommunication technologies has allowed the development of systems that use the Internet infrastructure and Web technology to remotely access a hospital's picture archiving and communication system (PACS). However, one of the main problems in the construction of this type of system is the development of mechanisms that guarantee the security of the medical data that are being consulted. Most countries have specific norms for the protection of such medical data. This work describes security mechanisms that are developed in an access system to PACS DICOM with Web technology and comply with the Spanish legislation concerning the protection of medical data. The proposed security mechanisms are flexible, they leave room for the definition of security policies adjusted to the needs of each particular organization and they can be adapted to comply with new or foreign norms.

Among the last new developments in the field of teleradiology, a new system of telediagnostic which allows the remote transmission of digital images via Internet is prevailing. These communications have to be made through mechanisms that guarantee the confidentiality and the integrity of the clinical data, as well as the authenticity of the transmitter. This system is, in many cases, the only way to diagnose the patient pathology in emergency rooms with no radiologist on call. Access to the medical data from any computer is possible through the implantation of a picture archiving and communication system (PACS) with direct acquisition from DICOM equipment and Web technology. So, the radiologist with a computer connected to the WWW (from inside or outside the hospital) has access to the clinical histories and images. Free distribution software (Apache-PHP-MySQL) and PC platforms in WinNT environment has been used. All the medical imaging equipment of a medium size hospital has been connected to be system, integrating them with the medical history data. Restricted access based on privileges were design to to make reports or only to consult data.