Biomedical subjects

Christian Lovis

Publications and source records attributed to Christian Lovis.

At least 19 recordsLinked to original sources

PubMed2006

Acceptance and cognitive load in a clinical setting of a novel device allowing natural real-time data acquisition.

INTRODUCTION: This paper reports the findings of an evaluation study in the field of human-computer interaction about the use of a new data acquisition device, the digital pen. It focuses on specific aspects of the interaction between the users and the technology: the cognitive burden induced by the design of the tool in real conditions of use and its impact on user acceptance. METHODOLOGY: Human cognition is embedded in a complex sociocultural world. Therefore, we opted for ethnographically informed investigations reinforced by a satisfaction survey. The work context chosen for these investigations was the emergency room triage process. RESULTS: The technology meets a high acceptance (median 3 on a [-5,5] scale) shaded by unexpected additional cognitive burdens. These burdens originate in several technological and ergonomic flaws that have been discovered during the observations. These results have been used to improve the technology. CONCLUSION: We demonstrate the importance of this kind of field study to uncover unexpected possible sources of failure of acceptance of a new technology. Such kind of study should be held prior to the introduction of a new technology to lower the common failure rate encountered in the field of medical informatics.

Attitude to Computers↗

PubMed2006

Comprehensive management of the access to the electronic patient record: towards trans-institutional networks.

BACKGROUND: A system ensuring tight control access is used since 5 years at the University Geneva Hospitals (HUG) over a four campuses health care system with ambulatory care settings behaving like a small community care network. Access to identified clinical information is limited to care providers that have a therapeutic relationship with the patient and to those data needed for that relation. The same policy applies to administrative or scientific research accesses. This paper presents how the HUG met the challenging goal of protecting patient privacy within regulatory limits while keeping the system operational in terms of use and management. SOLUTION: The main characteristics of the system are: (a) an institution-wide policy for access rights to the computerized patient record; (b) an institutional management of the contracts of the collaborators; (c) access profiles based on application-independent, fine-grained access rights; (d) a decentralized attribution of profession-specific access profiles; (e) a complete, centralized log of all accesses to the clinical information system; and (f) a decentralized verification of the accesses. Many of these characteristics can be maintained when evolving towards a trans-institutional computerized patient record, but new constraints need to be taken into account.

Access to Information↗

PubMed2006

Using argumentation to extract key sentences from biomedical abstracts.

PROBLEM: key word assignment has been largely used in MEDLINE to provide an indicative "gist" of the content of articles and to help retrieving biomedical articles. Abstracts are also used for this purpose. However with usually more than 300 words, MEDLINE abstracts can still be regarded as long documents; therefore we design a system to select a unique key sentence. This key sentence must be indicative of the article's content and we assume that abstract's conclusions are good candidates. We design and assess the performance of an automatic key sentence selector, which classifies sentences into four argumentative moves: PURPOSE, METHODS, RESULTS and CONCLUSION METHODS: we rely on Bayesian classifiers trained on automatically acquired data. Features representation, selection and weighting are reported and classification effectiveness is evaluated on the four classes using confusion matrices. We also explore the use of simple heuristics to take the position of sentences into account. Recall, precision and F-scores are computed for the CONCLUSION class. For the CONCLUSION class, the F-score reaches 84%. Automatic argumentative classification using Bayesian learners is feasible on MEDLINE abstracts and should help user navigation in such repositories.

Abstracting and Indexing↗

PubMed2006

Implementing a new ADT based on the HL7 version 3 RIM.

The University Hospitals of Geneva (HUG) are the result of the merge of six hospitals into one single organization. While a true fusion of the management has been effectively done, it was not the case 5 years after for several databases, and in particular the ADT (admission, discharge, transfer). In order to truly realize the fusion, a new ADT service has been built using state of the art technology and standards in order to replace the existing seven services. This paper presents the results of the redesign and development of the new ADT service. The data model, based on HL7 RIM, is described and the technologies selected are presented. Finally, a status after 1 year of production is presented.

Hospital Information Systems↗

PubMed2006

Comprehensive management of the access to a component-based healthcare information system.

OBJECTIVE: to describe the key concepts and elements used to implement a comprehensive access management system to a distributed, component-based healthcare information system. METHODS: the a priori access is based on an institution-wide policy for access rights coupled to proximity process for the granting of such rights. Access rights are explicit and externalized from the information systems components. A posteriori control is based on a centralized, exhaustive journal of accesses to all components coupled to a decentralized verification process for suspicious accesses. RESULTS: the system has been operational for three years, initially used for the access to the computerized patient record components, and now extending to all the components of the hospital information system. The same architecture will be used for the development of the trans-institutional community health information network.

Access to Information↗

PubMed2005

Methodology to ease the construction of a terminology of problems.

INTRODUCTION: Problem lists summarize an aspect of the patient's medical history and provide an important way to implement entry points for clinical pathways and guideline-oriented care. However, in order to automate processes based on problem lists, the use of controlled vocabularies is required. We developed a methodology to extract a collection of standardized problem-related terms from medical documents entered in free text by physicians. METHODS: We extracted a corpus of sentences describing problems from a randomized selection of admission notes collected at the University Hospitals of Geneva. Theses sentences underwent manual and automatic normalization processes, and a statistical clustering, in order to build a set of terms. RESULTS: We obtained 17,805 sentences from 5000 admission notes. We refined them into 1546 terms, 88.6% of which could be related to a relevant problem statement. DISCUSSION: A clinically relevant problems terminology was derived from clinical admission notes in free-text using a few methodical steps with a reasonable investment of human resources. Such an approach will ease the development and the use of problem lists better suited to user needs.

Medical Records, Problem-Oriented↗

PubMed2005

Amplification of Terminologia anatomica by French language terms using Latin terms matching algorithm: a prototype for other language.

OBJECTIVE: Terminologia anatomica is the new standard in anatomical terminology. This terminology is available only in Latin and English and its worldwide adoption is subject to the addition of terms from others languages. On the other hand, Nomina anatomica, the previous standard, has been widely translated. Aim of this work was to append foreign terms to Terminologia by using similarity-matching algorithm between its Latin terms and those from Nomina. METHODS: A semi-automatic matching of Latin terms from Terminologia with those of Nomina was performed using a string-to-string distance algorithm and manual assessment. We used a French-Latin version of Nomina together with Terminologia and we suggested French terms for Terminologia. Coverage was evaluated by the number of exact and approximate matches. A target of 78% was set due to the higher number of terms in Terminologia compared to Nomina. Relevance was estimated by manually comparing the meanings of the English and French terms related to the same Latin term. The question was whether they refer to the same anatomical structure. RESULTS: Exact or approximate matches were found for 5982 terms (76.5%) of Terminologia. Our results indicated that more than 75% of the terms from Terminologia came from Nomina, most of them were left unchanged and all were used with the same meaning. CONCLUSION: This method produces relevant results, reaching our 78% target. The method is based only on Latin terms and can be used for other languages. We consider this work as a starting point for adding terms to other knowledge sources, such as the foundational model of anatomy or the Unified Medical Language System (UMLS).

Algorithms↗

PubMed2005

Evaluating user interactions with clinical information systems: a model based on human-computer interaction models.

OBJECTIVES: This article proposes a model for dimensions involved in user evaluation of clinical information systems (CIS). The model links the dimensions in traditional CIS evaluation and the dimensions from the human-computer interaction (HCI) perspective. PROPOSED METHOD: In this article, variables are defined as the properties measured in an evaluation, and dimensions are defined as the factors contributing to the values of the measured variables. The proposed model is based on a two-step methodology with: (1) a general review of information systems (IS) evaluations to highlight studied variables, existing models and frameworks, and (2) a review of HCI literature to provide the theoretical basis to key dimensions of user evaluation. RESULTS: The review of literature led to the identification of eight key variables, among which satisfaction, acceptance, and success were found to be the most referenced. DISCUSSION: Among those variables, IS acceptance is a relevant candidate to reflect user evaluation of CIS. While their goals are similar, the fields of traditional CIS evaluation, and HCI are not closely connected. Combining those two fields allows for the development of an integrated model which provides a model for summative and comprehensive user evaluation of CIS. All dimensions identified in existing studies can be linked to this model and such an integrated model could provide a new perspective to compare investigations of different CIS systems.

Attitude to Computers↗

PubMed2005

Enterprise-wide PACS: beyond radiology, an architecture to manage all medical images.

RATIONALE AND OBJECTIVES: Picture archiving and communication systems (PACS) have the vocation to manage all medical images acquired within the hospital. To address the various situations encountered in the imaging specialties, the traditional architecture used for the radiology department has to evolve. MATERIALS AND METHODS: We present our preliminarily results toward an enterprise-wide PACS intended to support all kind of image production in medicine, from biomolecular images to whole-body pictures. Our solution is based on an existing radiologic PACS system from which images are distributed through an electronic patient record to all care facilities. This platform is enriched with a flexible integration framework supporting digital image communication in medicine (DICOM) and DICOM-XML formats. In addition, a generic workflow engine highly customizable is used to drive work processes. RESULTS: Echocardiology; hematology; ear, nose, and throat; and dermatology, including wounds, follow-up is the first implemented extensions outside of radiology. CONCLUSION: We also propose a global strategy for further developments based on three possible architectures for an enterprise-wide PACS.

Cardiology↗

PubMed2005

The digital pen and paper technology: implementation and use in an existing clinical information system.

OBJECTIVE: Evaluation of the technical feasibility of tight integration of the digital pen and paper technology in an existing computerized patient record.Technology: The digital pen is a normal pen able to record all actions of the user and to analyze a micro pattern printed on the paper. The digital paper is a normal paper printed with an almost invisible micro pattern of small dots encoding information such as position and identifiers. We report our experience in the implementation and the use of this technology in an existing large clinical information system for acquiring clinical information. DISCUSSION: It is possible to print uniquely identified forms using the digital paper technology. These forms can be pre-filled with clinical readable information about the patient. When care providers complete these forms using the digital pen, it is possible to acquire the data in a structured computerized patient record. The technology is easy to integrate in a component-based architecture based on Web Services. CONCLUSION: The digital pen and paper is a cost-effective technology that can be integrated in an existing clinical information system and allows fast and easy bedside clinical information acquisition without the need for an expensive infrastructure based on traditional portable devices or wireless devices.

Humans↗

PubMed2005

Lung CT Analysis and Retrieval as a Diagnostic Aid.

Image retrieval is currently a very active research field due to the large amount of visual data being produced in most modern hospitals. Most often, the goal is to aid the diagnostic process. Unfortunately, only very few medical image retrieval systems are currently used in clinical routine. One of the application domains for image retrieval is the analysis and retrieval of lung CTs. A first user study in the United States shows that these systems allow improving the diagnostic quality.This article describes the approach to an aid for lung CT diagnostics. The analysis incorporates several steps and the goal is to automate the process as much as possible for easy integration into diagnostics. Thus, several automatic steps are proposed from a selection of the most characteristic slices, to an automatic segmentation of the lung tissue and a classification on the segmented area into diagnostic classes. Feedback to the MD will be given in the form of marked regions in the images that appear to be different from the norm of healthy tissue. We are currently working on a small set of training images with marked and annotated regions but a larger set of images for the evaluation of our algorithm is in work. For this reason, the article does currently not contain much quantitative evaluation.For several tasks we use existing open source software such as Weka and itk. This allows an easy reproduction of the search results.

Algorithms↗

PubMed2005

Implementing a New ADT Based on the HL-7 Version 3 RIM.

The University Hospitals of Geneva (HUG) are the result of the merge of six hospitals into one single organization. While a true fusion of the management has been effectively done, it was not the case five years after for several databases, and in particular the ADT (Admission, Discharge, Transfer). In order to truly realize the fusion, a new ADT service has been built using state of the art technology and standards in order to replace the existing seven services. This paper presents the results of the redesign and development of the new ADT service. The data model, based on HL-7 RIM, is described and the technologies selected are presented. Finally, a status after a few months of production is presented.

Hospitals↗

PubMed2005

Desiderata for representing anatomical knowledge.

The general problem of knowledge representation for gross anatomy supporting both computers and human is rarely globally solved. Partial solutions are flourishing, but the actual and potential users are left with a lack of satisfaction and uncomfortable feeling of incompleteness. Moreover, these solutions are not ready for a sound evolution and are at risk to disappear at any moment by default of adequate maintenance. In addition, the problem is complicated by the fact that any solutions should be relevant for Natural Language Processing applications in a multilingual environment.This paper tackles with this problem and defines the basic steps for a proper knowledge representation scheme. Taking the subdomain of gross anatomy, it shows how each step has been solved and what performances and benefits are expected by such a solution. A discussion is done on the way to interface from a common source for both computers and humans.

Anatomy↗

PubMed2005

Towards a multilingual version of terminologia anatomica.

OBJECTIVE: Terminologia Anatomica (TA) is the new standard in anatomical terminology. This terminology is available only in Latin and English and its worldwide adoption is subdued to the addition of terms from others languages. On the other hand Nomina Anatomica (NA), the previous standard, has been widely translated. Aim of this work was to append foreign terms to TA by using similarity matching algorithm between its Latin terms and those from NA. METHODS: A semi-automatic matching of Latin terms from TA with those of NA was performed using a string-to-string distance algorithm and manual assessment. We used a French - Latin version of NA together with TA and we suggested French terms for TA. Coverage was evaluated by the number of exact and approximate matches. A target of 80% was set due to the superior number of terms in TA compared to NA. Relevance was estimated by manually comparing the meanings of the English and French terms related to the same Latin term. The question was whether they refer to the same anatomical structure. RESULTS: Exact or approximate matches were found for 5,982 terms (76.5%) of TA. Our results outlined that more than 75% of the terms from TA came from NA, most of them were left unchanged and all were used with the same meaning. CONCLUSION: This method produces relevant results, reaching our 80% target. The method is based only on Latin terms and can be used for other languages and for others terminologies including Latin terms.

Algorithms↗

PubMed2004

Coping with the variability of medical terms.

OBJECTIVES: To cope with medical terms, which present a high variability of expression through a single natural language, in the sense that any term may be reformulated in hundred of different ways. METHODS: A typology of term variants is presented as a systematic approach in order to favour the implementation of an exhaustive solution. Then, an algorithm able to handle all variants is designed. RESULTS: Using MetaMap, single terms are analyzed with a success rate varying between 68 and 88 %; the algorithm presented in this paper improves this situation. CONCLUSIONS: This experience shows that a semantic driven method, based on a thesaurus, provides a satisfactory solution to the problem of variability of a single term. The presented typology is representative of most variants in a language.

Algorithms↗

PubMed2004

User acceptance of clinical information systems: a methodological approach to identify the key dimensions allowing a reliable evaluation framework.

The introduction of Computerized Information Systems (CIS) in clinical settings encountered difficulties. These difficulties highlight the lack of understanding of factors and mechanisms influencing user acceptance. The existing tools and research obtained contradictory results that point out the existence of neglected aspects, such as impacts of CIS, in computer science developments in complex settings. This paper proposes to identify key dimensions which make up user acceptance in clinical settings through the union of three methods. They define five main dimensions which require a concrete evaluation to validate the underlying proposed framework and to complete the description of the acceptance phenomenon. Identifying key dimensions opens the gate to comparative evaluation of many CIS and adds new indicators to evaluate the highlighted dimensions. A long-term aim is the development of longitudinal studies and to state priorities and guidelines for new CIS designs.

Attitude to Computers↗

PubMed2003

Preparation and use of preconstructed orders, order sets, and order menus in a computerized provider order entry system.

OBJECTIVE: To describe the configuration and use of the computerized provider order entry (CPOE) system used for inpatient and outpatient care at the authors' facility. DESIGN: Description of order configuration entities, use patterns, and configuration changes in a production CPOE system. MEASUREMENTS: The authors extracted and analyzed the content of order configuration entities (order dialogs, preconfigured [quick] orders, order sets, and order menus) and determined the number of orders entered in their production order entry system over the previous three years. The authors measured use of these order configuration entities over a six-month period. They repeated the extract two years later to measure changes in these entities. RESULTS: CPOE system configuration, conducted before and after first production use, consisted of preparing 667 order dialogs, 5,982 preconfigured (quick) orders, and 513 order sets organized in 703 order menus for particular contexts, such as admission for a particular diagnosis. Fifty percent of the order dialogs, 57% of the quick orders, and 13% of the order sets were used within a six-month period. Over the subsequent two years, the volume of order configuration entities increased by 26%. CONCLUSIONS: These order configuration steps were time-consuming, but the authors believe they were important to increase the ordering speed and acceptability of the order entry software. Lessons learned in the process of configuring the CPOE ordering system are given. Better understanding of ordering patterns may make order configuration more efficient because many of the order configuration entities that were created were not used by clinicians.

Hospital Information Systems↗

PubMed2003

XML as standard for communicating in a document-based electronic patient record: a 3 years experiment.

During the past few years, the eXtensible Markup Language (XML) has progressively become a gold standard for accessing, representing and exchanging information, especially in the health care environment. This paper presents an implementation of the use of XML for the electronic patient record (EPR) and discusses more specifically its growing use in two areas of the EPR: first, as a format for the exchange of structured messages, and second, as a comprehensible way of representing patient documents. These statements rely on a 3 years experiment conducted at the Geneva University Hospital as part of its document-centered EPR.

Delivery of Health Care↗