Ontology-Based and Architecture-Based Method for the Development of Interoperable Care Systems for Type 2 Diabetes Mellitus.

Processes like the care of type 2 diabetes mellitus patients require support by information systems considering the heterogeneity of the actors from different domains involved, enabling harmonization and integration of their specific methodologies and knowledge representation approaches towards interdisciplinary cooperation. Currently, the development of systems starts from the simplified information world, ignoring the aforementioned heterogeneity and specificity of real-world processes. This paper aims to demonstrate the feasibility of developing an adaptive, interoperable and intelligent system that supports the major aspects of type 2 diabetes mellitus care based on the Generic Component Model as formal methodology for modelling universal systems. The result is a deployable solution based on a formal representation of the diabetes care system, its objectives, and the intended business process. The implemented system enables reasoning over the data, inferring medical diagnosis. The effectiveness of the inference was evaluated, obtaining an F-measure of 0.89. The methods presented in this paper helps to build high quality models based on computation-independent aspects, which enable the construction of knowledge-based adaptive, intelligent and interoperable eHealth systems.

Autonomous Systems and Artificial Intelligence in Healthcare Transformation to 5P Medicine - Ethical Challenges.

The paper introduces a structured approach to transforming healthcare towards personalized, preventive, predictive, participative precision (P5) medicine and the related organizational, methodological and technological requirements. Thereby, the deployment of autonomous systems and artificial intelligence is inevitably. The paper discusses opportunities and challenges of those technologies from a humanistic and ethical perspective. It shortly introduces the essential concepts and principles, and critically discusses some relevant projects. Finally, it offers ways for correctly representing, specifying, implementing and deploying autonomous and intelligent systems under an ethical perspective.

A generic architecture for an adaptive, interoperable and intelligent type 2 diabetes mellitus care system.

Chronic diseases such as Type 2 Diabetes Mellitus (T2DM) constitute a big burden to the global health economy. T2DM Care Management requires a multi-disciplinary and multi-organizational approach. Because of different languages and terminologies, education, experiences, skills, etc., such an approach establishes a special interoperability challenge. The solution is a flexible, scalable, business-controlled, adaptive, knowledge-based, intelligent system following a systems-oriented, architecture-centric, ontology-based and policy-driven approach. The architecture of real systems is described, using the basics and principles of the Generic Component Model (GCM). For representing the functional aspects of a system the Business Process Modeling Notation (BPMN) is used. The system architecture obtained is presented using a GCM graphical notation, class diagrams and BPMN diagrams. The architecture-centric approach considers the compositional nature of the real world system and its functionalities, guarantees coherence, and provides right inferences. The level of generality provided in this paper facilitates use case specific adaptations of the system. By that way, intelligent, adaptive and interoperable T2DM care systems can be derived from the presented model as presented in another publication.

Specializing architectures for the type 2 diabetes mellitus care use cases with a focus on process management.

The development of software supporting inter-disciplinary systems like the type 2 diabetes mellitus care requires the deployment of methodologies designed for this type of interoperability. The GCM framework allows the architectural description of such systems and the development of software solutions based on it. A first step of the GCM methodology is the definition of a generic architecture, followed by its specialization for specific use cases. This paper describes the specialization of the generic architecture of a system, supporting Type 2 diabetes mellitus glycemic control, for a pharmacotherapy use case. It focuses on the behavioral aspect of the system, i.e. the policy domain and the definition of the rules governing the system. The design of this architecture reflects the inter-disciplinary feature of the methodology. Finally, the resulting architecture allows building adaptive, intelligent and complete systems.

Towards automated biomedical ontology harmonization.

The use of biomedical ontologies is increasing, especially in the context of health systems interoperability. Ontologies are key pieces to understand the semantics of information exchanged. However, given the diversity of biomedical ontologies, it is essential to develop tools that support harmonization processes amongst them. Several algorithms and tools are proposed by computer scientist for partially supporting ontology harmonization. However, these tools face several problems, especially in the biomedical domain where ontologies are large and complex. In the harmonization process, matching is a basic task. This paper explains the different ontology harmonization processes, analyzes existing matching tools, and proposes a prototype of an ontology harmonization service. The results demonstrate that there are many open issues in the field of biomedical ontology harmonization, such as: overcoming structural discrepancies between ontologies; the lack of semantic algorithms to automate the process; the low matching efficiency of existing algorithms; and the use of domain and top level ontologies in the matching process.

Architectural analysis of clinical ontologies for pHealth interoperability.

Comprehensive interoperability between eHealth/pHealth systems requires properly represented shared knowledge. Formal ontologies allow specifying the semantics of health knowledge representation in a well-defined and unambiguous manner. The objective of this paper is to formally analyze - from a system-theoretical architectural perspective - existing clinical ontologies. The paper defines important ontology requirements for semantically interoperable pHealth/eHealth systems. Then, based on those requirements, 17 criteria are defined and used for analyzing 129 clinical ontologies. Statistical results confirm that most ontologies do not meet the defined criteria. OBO foundry defines a good approach to meet all defined criteria, but it does not cover yet the clinical domain as a whole. SNOMED CT was found the more comprehensive one, despite several restrictions.

Cólera en Apartadó, Antioquia: aspectos clínicos y epidemiológicos / Cholera in Apartado, Colombia: clinical and epidemiological aspects

Este trabajo fue realizado en el Hospital Regional de Apartadó, Antioquia, motivado por la falta de experiencia con cólera en la región y por la similitud clínica y epidemiológica que esta enfermedad presenta con otras enteritis agudas, endémicas en la zona. Los objetivos fueron: analizar algunas variables epidemiológicas y clínicas, verificar la eficacia del tratamiento y comparar el comportamiento del cólera con el de la Enfermedad Diarreica Aguda (EDA) sin cólera. Se revisaron las historias clínicas y epidemiológicas de 181 pacientes atendidos entre agosto 11 y octubre 11 de 1991. Se configuró un estudio retrospectivo con las siguientes variables: coprocultivo para Vibrio cholerae, edad, sexo, ocupación, procedencia, estado de hidratación al consultar, duración de la estadía hospitalaria, equilibrio hídrico, asociación epidemiológica y condiciones sanitarias. Se confirmó cólera por coprocultivo en 87 casos (48 por ciento). Al comparar el cólera con la EDA sin cólera, sólo se encontró diferencia significativa en cuanto al grupo de edad afectado (p=0.042) ya la duración de la hospitalización (p=0.016). El tratamiento recomendado por la OMS fue eficaz según el criterio clínico. No hubo complicaciones ni reingresos; ningún paciente falleció

One hundred and eighty one patients with acute diarrhea disease (ADD) were analyzed from the clinical and epidemiological points of view; 87 of them (48.1%) had confirmed cholera while the remaining 94 (51.9%) were classified as non-cholera ADD; the only significant differences between these two groups were observed in age and days of hospital stay: cholera predominated In patients older than 5 years (p=O.O42) and the frequency of a hospital stay longer than 2 days was higher in cholera patients (p=O.O16). WHO recommended treatment was effective according to clinical criteria; neither complications nor deaths were found