Christine Verdier

Information System Architecture for Wearable Cardiac Sensors Personalization

New medical devices and services enabling citizen’s health care anywhere and anytime are expected in the near future. However, to become a reality these devices must be supported by personalized services which satisfy user needs. In this paper we propose a general approach to manage the complexity of ambiguously related information for providing enhanced, user-specific services in the self-care domain. The global architecture is driven by a compositional model between a domain-specific and a context-awareness model, which aggregates the citizen’s and the devices profiles, the citizen’s healthcare characteristics and available signal processing methods. The final objective is to support automatic composition of services helping any citizen to select an optimal and personalized sensor system and to improve decision-making.

Semantic Indexing for Intelligent Browsing of Distributed Data

We present in this paper a semantic indexing technics based on description logics. Data to be indexed are semantically organized as a Topic Map. The index is constructed according to data organization, user profile, and data distribution (association rules). This way leads to obtain a more efficient index and represents more semantics. The index is well adapted to jointly query and navigate in the topic map. DL allows to represent semantics and performs powerful reasoning. The index structure is based on subsumption relationships (for intra-concept indexing) and roles (for inter-concepts indexing).

On the Capabilities of BPMN for Workflow Activity Patterns Representation

This paper provides a complete version of the Workflow Activity Patterns (WAP) in the Business Process Modeling Notation (BPMN) as well as an extended evaluation of the capabilities of BPMN and their strengths and weaknesses when being utilizing for representing WAPs. When implementing the activity patterns in existing Business Process Modeling tools, it is fundamental to represent them in BPMN. This representation may facilitate the adoption of the WAPs by BPMN tools as well as the use of the WAPs in process design.

Public health alert system for health networks: application to cardiology

The authors propose a system that allows healthcare professionals like physicians and nurses to define medical alerts from patient and environmental data by using fuzzy linguistic variables. Such variables are associated to three importance levels (very important, important or less important) indicating their relative importance in the context and can be developed separately from alerts. Each time a predefined alert is activated by the system, it has two quality indicators which are used for filtering: an 0 to 1 applicability level stating how much the patient is concerned and a trust level indicating its reliability and calculated according to the amount of information that is available at the moment. Finally, lack of information, very common in medical records, is treated transparently thanks to the new concept of modifier, which allows to express the influence variables have on each other by means of a weighted oriented graph

Quality Indices in Medical Alert Systems

Numerous alert systems exist in healthcare domains but most of them produce too much false alerts, bad usage or disinterest. The need of better alert systems leads to develop context-aware alert systems. The alert system Tempas is a help-decision tool based on personalized alerts. It is adaptable to business environment, population targeted, expert user needs, and customized in real-time for immediate needs by end users. The adaptability is defined during the alert creation process. The customization is defined during the alert management process. It is based on the population targeted, activation conditions, and the alert behavior. It is supported by two quality indices: the applicability index expresses how much a patient (or a population) is concerned by the alert and the confidence index expresses how much the user can trust the alert. Both indices are used during the alert creation process (minimal thresholds for the population) and during the management process (minimal personalized threshold). The paper presents a summarized view of Tempas and focuses on the quality indices.

Defining Quality-Measurable Medical Alerts From Incomplete Data Through Fuzzy Linguistic Variables and Modifiers

Alert systems are frequent in the medical field, where they are typically connected to monitoring devices that are able to detect abnormal values. Our system is different in its goals and tools. First of all, it processes data extracted from electronic medical records, which are widely used nowadays, and meteorological databases. Variables that are not continually measured by devices (like the age of patients) can then be taken into account. Next, the alerts it handles are not predefined, but created by users through domain-independent fuzzy linguistic variables whose relationships (the height of an individual is conditioned by its age) are modeled by a weighted oriented graph. Finally, the alerts it triggers are associated with two indicators used for filtering and assessing their relevance to the patients, and their reliability according to the amount of information available. Then, if there is a missing variable in a record, the detection algorithm treats it transparently by automatically decreasing the reliability of the alert. The main qualities of this system are the simplicity-linguistic variables are intuitive-and the ability to measure the informational quality of alerts (applicability and reliability).

Domed: Semantic data integration and navigation in Web-based medical records.

Medical data are stored on multiple health information systems which are heterogeneous and non-communicating. These medical information systems are often built with Web-based pages. The medical record of a patient is therefore dispatched between all these removed systems. It is then difficult to get a complete and consistent long-life medical record due to semantic and structural heterogeneities. Our aim is to propose a user interface in which the patients medical records rebuilt by the end-user himself in a simple interface where concepts are chosen in a list and linked automatically together. Therefore, the user can navigate in this space of concepts to obtain information he needs, as easily as in a web site.

Personalized temporal medical alert system

The continuous increasing needs in telemedicine and healthcare, accentuate the need of well-adapted medical alert systems. Such alert systems may be used by a variety of patients and medical actors, and should allow monitoring a wide range of medical variables. This paper proposes Tempas, a personalized temporal alert system. It facilitates customized alert configuration by using linguistic trends. The trend detection algorithm is based on data normalization, time series segmentation, and segment classification. It improves state of the art by treating irregular and regular time series in an appropriate way, thanks to the introduction of an observation variable valid time. Alert detection is enriched with quality and applicability measures. They allow a personalized tuning of the system to help reducing false negatives and false positives alerts.

Exploiting profile modeling for web-based information systems

With the considerable amount of data and the diversity of the users needs, the personalization of information becomes a real challenge in web-based information systems. This paper presents a personalized access technique, based on a profile modeling. This technique requires two steps: 1) building users profile and 2) using profile content for filtering information. The first step consists in modeling a global profile which can be used for different and independent requirements of personalization. The profile modeling takes into account the users context when defining users profiles. We describe a global profile in three levels: meta-description level, description level for a specific domain, instances (data). The second step consists in selecting the profiles rules which correspond to the user and his current context and to filter information accordingly.

Conception d'une structure globale du dossier médical pour les réseaux de soins

Cet article a pour objectif de proposer une structure globale du dossier medical qui sera utilisee comme referentiel lors de la conception des nouveaux systemes d’informations medicales pour les reseaux de soins. Cette structure est construite hierarchiquement en trois niveaux. Elle est alimentee par des elements les plus utilises dans le milieu medical en s’appuyant sur une ontologie medicale telle que UMLS. Cette structure est etendue en utilisant les metadonnees des bases de donnees relationnelles heterogenes. Ensuite ces schemas sont analyses pour traduire les liens semantiques en structures locales. A partir de ces structures, les concepts seront integres dans la structure globale du dossier medical en utilisant la methode de matching. Ainsi la structure globale du dossier medical est constituee pour palier le probleme d’heterogeneite des bases de donnees medicales et pour offrir aux concepteurs une structure unique servant de lien entre les bases de donnees locales et les SI des reseaux de soins.