J. Fayn

Institut National des Sciences Appliquées de Lyon, Lyons, Rhône-Alpes, France

Are you J. Fayn?

Claim your profile

Publications (61)47.53 Total impact

  • J. Fayn, N. Vuillerme
    [show abstract] [hide abstract]
    ABSTRACT: In this paper, we briefly describe the eHealth theme of GdR STIC-Santé we created in January 2011, then we summarize the main contributions to the promotion, development, organization and diffusion of research, innovation, education and training initiatives in the field of eHealth we provided in 2011–2012, and we finally draw some perspectives for future works for the coming years.
    IRBM. 02/2013; 34(1):18–20.
  • E. Nageba, P. Rubel, J. Fayn
    [show abstract] [hide abstract]
    ABSTRACT: The objective of this research work is to empower healthcare information systems to deliver high quality information anytime and anywhere and to present distributed and heterogeneous resources access solutions which perfectly meet user requirements in different contexts. To reach this objective, we propose in this paper a new framework, called ONtology Oriented Framework for Pervasive Applications and Services (ONOF-PAS), and mainly based on: 1) interrelated ontological models representing the main entities in pervasive computing, such as Organization, Actor, Task, Service, Process, Object, Resources, etc.; 2) rule-based reasoning to infer the available and capable resources required by each task. The main functionality of the ONOF-PAS framework is to capture and to process the acquired knowledge about the user's context, the tasks they perform, the availability and capabilities of the required resources, and the organizations that own or manage these resources. Our framework allows healthcare information systems to infer the needed resources by linking each user-task with the required, available and capable resources taking into account the clinical conditions of the patients. The ONOF-PAS framework has been successfully applied in the telemedicine domain in order to provide practical and efficient resources access solutions that better meet the contexts and the expectations of the eHealth actors.
    IRBM. 02/2013; 34(1):79–85.
  • [show abstract] [hide abstract]
    ABSTRACT: Given the soaring costs associated with the treatment of ever more prevalent chronic disease, it is widely agreed that a revolution is required in health care provision. It is often thought that the necessary technology already exists for the home-based monitoring of such patients and that it is other factors which are holding back the more widespread clinical uptake of these new tools. The authors suggest that the necessary sensor-related technologies are often not as advanced as may first appear; certainly they are generally not adequate for the robust, long-term monitoring of patients under real-life conditions. An additional problem is the evident efforts to apply a given sensor and related technology platform to any and all monitoring scenarios without sufficient consideration of patient needs and the clinical requirements. The authors review the key sensing platforms and suggest the applications for which they are best suited.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2011; 2011:3648-51.
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: In this paper we propose a new design of a wearable sensor-system produced in three different sizes for recording anywhere and at anytime three pseudo-orthogonal ECG leads I, II and V2 according to the Mason-Likar system. It looks like a bib and aims to provide any individual with a sensor-system suitably adapted to his/her morphology. Our research goal is to establish for each citizen the most appropriate sensor-system size, which produces ECG signals with a diagnostic content that is closest to that of a standard ECG. In order to evaluate the possible automation of this selection process, we performed a series of experiments on eight healthy volunteers and we present the results of 280 ECG comparisons in terms of correlation, RMS values, as well as changes in diagnosis probability and of selected ECG measurements.
    Computing in Cardiology, 2010; 10/2010
  • Asta Krupaviciute, Jocelyne Fayn
    [show abstract] [hide abstract]
    ABSTRACT: Automating sophisticated, personalized expert activities, which are based on the application of professional knowledge to process an individual case, remains a great challenge. It is all the more relevant in some complex domains such as preventive medicine or e-learning where reliable and self-adaptive solutions are expected by users. In this paper we analyze differences between typical procedure-based business processes automation and expert activities automation. We propose to integrate context related knowledge into the business process modeling via the development of an intelligent process management agent. The latter is designed to dynamically orchestrate the set of services that will build up the process reproducing an expert activity, adapted to the concrete client’s context. KeywordsExpert activity-Dynamic business process-Ontology-based approach-Web services orchestration-Data and Model driven SOA
    08/2010: pages 497-500;
  • H. Jumaa, P. Rubel, J. Fayn
    [show abstract] [hide abstract]
    ABSTRACT: Providing a transparent and automatic communication between health information systems for the purpose of exchanging patients' data among healthcare professionals is deemed as one of the most challenging problems in eHealth. Indeed, data storage in health information systems is mainly performed in relational databases, whereas eXtensible Markup Language (XML) is seen as the de facto standard for exchanging data among health organizations. Automating data interchange between relational databases and XML documents remains however a challenge. In this paper, we propose a general mediation framework to facilitate the storage of the new incoming data in XML format into the relational databases of the legacy health information systems and vice versa. The proposed mediation architecture is based on the XML technology and its related languages and derivatives (XML Schema, eXtensible Stylesheet Language Transformations (XSLT)...), which provide powerful tools for sharing, converting and exchanging information. The adopted methodology consists in converting the database model into an XML schema and in performing an automatic, reliable and efficient mapping between the schemas representing the exchanged source and target data by means of the XSLT language. Our approach has the capacity to preserve the integrity constraints of the relational schema, which allows to check the XML infosets for anomalies or incoherencies before updating the relational database from the XML document. It also captures the hierarchy of the tables in the target database, which guarantees that the automatically generated Structured Query Language (SQL) queries will be correctly performed. Moreover, our mediator includes a rule base allowing a coherent and secure mapping between the exchanged data sources for ensuring the database integrity.
    e-Health Networking Applications and Services (Healthcom), 2010 12th IEEE International Conference on; 08/2010
  • Asta Krupaviciute, Jocelyne Fayn
    [show abstract] [hide abstract]
    ABSTRACT: As knowledge is usually heterogeneous, voluminous, poorly structured and steadily evolving, its automated use in practice is extremely difficult. These limitations remain the main blocking element for creating advanced, adaptive business processes providing intelligent assistance. In this paper we propose to extend the typical business process development view, mainly focusing on services composition, with a business intelligence view which aims to support the design of complex, automatically reconfigurable services. To fulfil this objective, we designed an approach that consists in setting up an intelligent environment based on a context-aware concepts ontology of business processes and on related context handling rules for services orchestration. It's a generic method that enables to capture and to granulate the knowledge into a set of models that support dynamic business processes management. We demonstrate the relevance of this approach for the design of automatic and personalised decision support services orchestration based on a core ontology.
    Second International Conference on Computational Intelligence, Communication Systems and Networks, CICSyN 2010, Liverpool, UK, 28-30 July, 2010; 01/2010
  • Source
    Wearable Monitoring Systems. 01/2010;
  • [show abstract] [hide abstract]
    ABSTRACT: New medical devices and services enabling citizenpsilas 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 citizenpsilas and the devices profiles, the citizenpsilas 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.
    14th IEEE International Conference on Engineering of Complex Computer Systems, ICECCS 2009, Potsdam, Germany, 2-4 June 2009; 01/2009
  • Source
    H. Jumaa, J. Fayn, P. Rubel
    [show abstract] [hide abstract]
    ABSTRACT: The aim of this paper is to present a generic mediator for automating the storage and retrieval of an SCP-ECG message into and from a relational database. The architecture of the mediator is based on the XML technology and its related languages and derivatives (XML Schema, XSLT...), which provide powerful tools for sharing, converting and exchanging information. The adopted methodology consists in the design and in the interconnection of meta-models of the source and target data representations using the XML language. The SCP-ECG format is easily represented in XML, whereas the database meta-model must be appropriately created according to a tree structure by reverse engineering. Then, our method includes a rule base allowing a coherent and secure mapping between the source and the target data for ensuring the database integrity.
    Computers in Cardiology, 2008; 10/2008
  • H. Atoui, J Fayn, P Rubel
    [show abstract] [hide abstract]
    ABSTRACT: Synthesis of the 12-lead ECG has been investigated in the last decade as a method to improve patient monitoring in situations where the acquisition of the 12-lead ECG is cumbersome and time consuming.This paper presents and assesses a novel approach for deriving 12-lead ECGs from a pseudo orthogonal 3-lead subset via generic and patient-specific non-linear reconstruction methods based on the use of artificial neural networks (ANN)committees. We train and test the ANN on a set of serial ECGs from 120 cardiac in patients from the intensive care unit of the Cardiology Hospital of Lyon. We then assess the similarity between the synthesized ECGs and the original ECGs on the quantitative level in comparison with generic and patient specific multiple regression based methods. The ANN achieved accurate reconstruction of the 125-lead ECGs of the study population using both generic and patient specific ANN transforms,showing significant improvements over generic (p-value $\leq$ 0.05)and patient specific multiple linear regression based models. Consequently, our neural network based approach has proven to be sufficiently accurate to be deployed in home care as well as in ambulatory situations to synthesize a standard 12-lead ECG from a reduced lead set ECG recording.
    IEEE transactions on information technology in biomedicine: a publication of the IEEE Engineering in Medicine and Biology Society 07/2008; · 1.69 Impact Factor
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: Thanks to the development of homecare facilities, elderly prefer to stay at home, and the age at which they are admitted in retirement homes is steadily increasing. As a result, a very large number of these persons are going to live in such dedicated centers because they have several health problems and need a daily assistance. But, a great number of these institutions for the elderly do not necessarily include medical services with a permanent on-site physician. These citizens/patients may be located in isolated geographic areas and sometimes need a GP intervention within less than two hours. In this context, we have designed a telemedical solution, called Tele-Nurse, based on a medical trolley equipped with several sensors (ECG, blood pressure, weight scale, SaO2, glucometer, videoconference) connected to a laptop which allows to collect and transmit the data to the GP via a J2EE server and a MySQL database. In this paper, we describe the global architecture which has been implemented and the various models that have been designed to support the user requirements, the use-case scenarios and the functions of the core system.
    Computers in Cardiology, 2006; 10/2006
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: There is a growing demand for developing personalized and non-hospital based care systems to improve the management of cardiac care. The EPI- MEDICS project has designed a personal ECG monitor (PEM) capable of recording a simplified 4-electrode, professional quality 3-lead ECG, detecting arrhythmias and ischemia by means of committees of Artificial Neural Networks (ANN), and alerting the relevant health care professionals. Our objective is to improve the patient risk stratification and to reduce the number of false positive and false negative alarms by taking into account the demographic and clinical data featured by the user's electronic health record (EHR) stored in the PEM device. To design and assess such a new type of system, we adopted a decision making solution based on Bayesian networks (BN) that we trained to predict the risk of a cardiovascular event (infarction, stroke, or cardiovascular death) based on a set of demographic and clinical data (age, BMI, etc.) as provided by the INDANA database, from which we randomly extracted a training set of 15013 subjects and a testing set of 5004 subjects. The BN is then compared to an ANN committee (N=50) and a logistic regression (LR) model in terms of sensitivity, specificity, and area under the ROC curve (AUC). AUC = 0.80 for the BN, 0.75 for the ANN committee and 0.74 for the LR model. The Bayesian network approach achieved a high overall accuracy over both the neural network and logistic regression models on the testing set, and therefore can be useful in pHealth systems such as the PEM.
    Computers in Cardiology, 2006; 10/2006
  • Source
    D. Telisson, J. Fayn, P. Rubel
    [show abstract] [hide abstract]
    ABSTRACT: The aim of this paper is to present an open and generic medical tele-expertise architecture which may be implemented intra and inter hospitals in any medical or call centre and at home. This architecture is based on TCP/IP Internet technology and on the XML metalanguage for data representation, storage and communication. It is composed of a main application installed on a web server for the intelligent management of the messages exchange and of distributed client applications for sending and receiving the tele-expertise requests via HTTPS. A message contains the communicating parties, the electronic health record (EHR) and any attached files like SCP-ECGs or DICOM images. In order to guarantee the reception of the message in due time, the expert should be able to receive anywhere different kinds of notifications by means of different types of devices that depend on the available technologies (Pager, SMS, PDA, etc.). This new infrastructure is being experimented within the Lyon area in a setting that includes an emergency department, regional and general hospitals, the Cardiology Hospital of Lyon and patients homes.
    Computers in Cardiology, 2004; 10/2004
  • Source
    H. Atoui, J. Fayn, P. Rubel
    [show abstract] [hide abstract]
    ABSTRACT: In recent years, there has been a growing interest in developing accurate methods for the synthesis of the 12-lead ECG from a minimal lead-set to improve patient monitoring in situations where the acquisition of the 12-lead ECG is difficult or impractical. This paper presents a method that aims to derive the standard 12-lead ECG from a pseudoorthogonal 3-lead subset via a nonlinear patient specific reconstruction method that is based on the use of artificial neural networks (ANN). We train and test the ANN over a 300 adult patients study population. We then assess the performance of the ANN based ECG synthesis method in comparison with the multiple regression based method and test for statistical differences between the two methods using the paired Student's t-test. The ANNs achieved high overall accuracies for all the testing sets. Moreover, the difference in accuracies between both methods is statistically significant (p<0.001). The encouraging results reported here suggest that the artificial neural networks represent a rather interesting and very promising approach to improve the synthesis of the 12-lead ECG.
    Computers in Cardiology, 2004; 10/2004
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: The congenital Long QT Syndrome (LQTS) is an inherited disorder of ventricular repolarization that predisposes affected individuals to sudden death. The analysis of conventional ECG may be misleading, and we need non invasive markers to identify more accurately patients with these conditions. In the LQT2 syndrome, the fast-delayed rectifier current Ikr is altered and leads to a prolonged Action Potential Duration (APD) in mid- myocardial areas that in turn translates to a prolonged QT interval and a widened T-wave. The aim of this work was to find new ECG parameters which can be used to identify LQT2 carriers in a large population. The study population was composed of 67 normal healthy subjects and 11 known carriers of a HERG mutation (four different mutations and four families). For each subject a 12-lead digital ECG was recorded and analyzed by using the spatiotemporal CAVIAR method. With only one single CAVIAR measurement we could correctly classify 93.6% of the cases. This measurement, called ODIR, represents the difference in orientation between the T wave and the beginning of QRS. Its values are significantly higher in the LQT2 patients (m±SD=58.5° ±14.5°) than in the normal population (m±SD=21.6°±14.6°) with a p- value
    01/2004;
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: An operational e-health infrastructure including pervasive services and remote distributed applications servers in the cardiology domain is presented. Based on the implementation of previously reported software components building blocks, developed in particular within the frame of European projects, the architecture promotes and facilitates the use of advanced methods of quantitative electrocardiology. The expected outcome is the improvement of the early detection of cardiac diseases, of the patients follow-up and the enhancement of the citizens quality of life.
    Computers in Cardiology, 2003; 10/2003
  • [show abstract] [hide abstract]
    ABSTRACT: In western countries, heart disease is the main cause of premature death. Most of victims do not survive long enough to benefit from in-hospital treatments. To reduce the time before treatment, the only useful diagnostic tool to assess the presence of a cardiac event in the pre-hospital care situations is the electrocardiogram (ECG). Event and transtelephonic ECG recorders are being used to improve decision-making but require setting up new infrastructures. The pervasive solution proposed by the European EPI-MEDICS project is a wearable, intelligent Personal ECG Monitor for the early detection of cardiac events. It records pseudo-orthogonal 3-lead ECGs from an easy-to-wear 4-electrode sub-system embedding professional recording and processing capabilities, includes part of the patient electronic health record (EHR), embeds a web server and powerful soft computing decision-making techniques, generates different alarm levels and forwards alarm messages to the relevant care providers by means of new generation wireless communication. It is cost saving, involving care providers only if necessary, without requiring to set-up specific infrastructures. Healthcare becomes personalized, wearable and ubiquitous.
    Information Technology Applications in Biomedicine, 2003. 4th International IEEE EMBS Special Topic Conference on; 05/2003
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: In western countries, heart disease is the main cause of premature death. Most of cardiac deaths occur out of hospital. Symptoms are often interpreted incorrectly. Victims do not survive long enough to benefit from in-hospital treatments. To reduce the time before treatment, the only useful diagnostic tool to assess the presence of a cardiac event is the electrocardiogram (ECG). Event and transtelephonic ECG recorders are used to improve decision-making but require setting up new infrastructures. The Pervasive solution proposed by the European EPI-MEDICS project is an intelligent Personal ECG Monitor for the early detection of cardiac events. It includes decision-making techniques, generates different alarm levels and forwards alarm messages to the relevant care providers by means of new generation wireless communication. It is cost saving, involving care provider only if necessary without specific infrastructure. Healthcare becomes personalized, wearable, ubiquitous.
    Computers in Cardiology, 2002; 10/2002
  • [show abstract] [hide abstract]
    ABSTRACT: Because of a continuously growing elderly population, the number of heart attacks is steadily increasing. Most victims do not survive long enough to receive medical help. The only useful early decision-making support tool is the electrocardiogram (ECG). The solution proposed by the European EPI-MEDICS (Enhanced, Personal, Intelligent and Mobile system for Early Detection and Interpretation of Cardiological Syndromes) project consists in developing a very affordable, easy-to-use but powerful, embedded personal ECG monitor (PEM) for the early detection and prevention of cardiac events. The PEM device records, stores and synthesises standard 12-lead ECGs, generates different levels of alarms and forwards the alarm messages with the recorded signals to the relevant healthcare providers by means of new-generation wireless communication techniques. In this paper, we briefly describe the different use cases of the PEM and propose a global telemedical architecture for the follow-up of ambulatory patients. The paper also reports about the ins and outs of the project and the results which have been reached so far
    Computers in Cardiology 2001; 02/2001

Publication Stats

311 Citations
130 Downloads
47.53 Total Impact Points

Institutions

  • 1992–2011
    • Institut National des Sciences Appliquées de Lyon
      Lyons, Rhône-Alpes, France
  • 2008–2010
    • University of Lyon
      Lyons, Rhône-Alpes, France
  • 2002–2006
    • Unité Inserm U1077
      Caen, Lower Normandy, France
  • 2001
    • INSA
      Альтамира, Tamaulipas, Mexico
  • 1988–2000
    • French Institute of Health and Medical Research
      Lutetia Parisorum, Île-de-France, France
  • 1997
    • CHU de Lyon - Hôpital Cardio-vasculaire et Pneumologique Louis Pradel
      Lyons, Rhône-Alpes, France
    • Hôpital Universitaire Necker
      Lutetia Parisorum, Île-de-France, France
  • 1995
    • Lund University
      • Department of Clinical Physiology
      Lund, Skane, Sweden