Biomedical subjects

C Lovis

Publications and source records attributed to C Lovis.

At least 19 recordsLinked to original sources

PubMed2000

Power of expression in the electronic patient record: structured data or narrative text?

This paper presents the authors' experience with the development and use of a document-centered electronic patient record (EPR) in a large teaching hospital. The development of the document-centered EPR began with the formulation of a set of critical hypotheses to facilitate both the continuation of the best medical practice and the implementation and use of the EPR. An alternate and more conventional approach - the data-centered EPR - is compared with the document-centered EPR. Various benefits and pitfalls are discussed. Finally, the choice was to offer both solutions in a tightly linked system. The need for an EPR which combines the document and data centered approaches is a reflection of the more general discussion of what the medical record will be in the future. All too often, the need for structured data conflicts with the need for free texts and the power of expression. It is not easy to evaluate the consequences of this initial decision. However, changing the foundations of the EPR after its implementation is difficult and expensive. Therefore, the selection of the correct orientation in a given hospital requires a broad-based discussion.

Hospitals, Teaching↗

PubMed2000

Extending the VA CPRS electronic patient record order entry system using natural language processing techniques.

An automated practitioner order entry system was recently implemented at the VA Puget Sound Health Care System. Since the introduction of this system, we have experienced various problems, among them an increase in time required for practitioners to enter orders. In order to improve usability and acceptance of the order entry, an alternate pathway was built within CPRS that allows direct natural language based order entry. Implementation of the extension in CPRS has been made possible because of the three layers CPRS architecture and its strong object oriented models. This paper discusses the advantages and needs for a natural language based order entry system and its implementation within an existing order entry system.

Humans↗

PubMed2000

Semantic handling of medical compound words through sound analysis and generation processes.

Compound words are frequently encountered in the medical domain. Their conciseness complies with the telegraphic style usually adopted by clinicians in daily practice. This amplifies the need for clarifying their semantic interpretation and representation through respectively the analysis and generation processes. While highlighting the peculiarities of medical compound words, this paper shows how model-driven linguistic tools accurately deal with the compositionality of medical language. These statements are illustrated by means of examples, stemming from the handling of surgical procedures as part of the GALEN-IN-USE project.

Linguistics↗

PubMed1999

The power and limits of a rule-based morpho-semantic parser.

The venue of Electronic Patient Record (EPR) implies an increasing amount of medical texts readily available for processing, as soon as convenient tools are made available. The chief application is text analysis, from which one can drive other disciplines like indexing for retrieval, knowledge representation, translation and inferencing for medical intelligent systems. Prerequisites for a convenient analyzer of medical texts are: building the lexicon, developing semantic representation of the domain, having a large corpus of texts available for statistical analysis, and finally mastering robust and powerful parsing techniques in order to satisfy the constraints of the medical domain. This article aims at presenting an easy-to-use parser ready to be adapted in different settings. It describes its power together with its practical limitations as experienced by the authors.

Humans↗

PubMed1999

Document versus data centred approach to the EPR.

This paper presents the document centred Electronic Patient Record (EPR) as currently in production in a large university hospital and subject to multiple additional developments in the coming years. A number of basic hypothesis have been developed in order to reach the best medical practice and the success of this application. In addition, the alternative approach of data centred EPR is compared, and different benefits and pitfalls are highlighted. It is not easy to evaluate the consequences of such an initial trend, but changing one's mind after having a system in daily production is anyway costly and difficult. Therefore, the selection of the right orientation in a given hospital necessitates a scientific debate.

Data Collection↗

PubMed1998

Do physicians modify their prehospital management of patients in response to a public campaign on chest pain?

The goals of this study were to analyze the impact of a public campaign on chest pain on physicians involved in the prehospital care of patients with this symptom, in terms of physician delay, rates of immediate hospitalization, and of transportation by ambulance. Prehospital delays and decisions for all 866 patients with chest pain managed by the community and generalist physicians or by emergency physicians, who presented to the emergency department of a teaching hospital during the 12 months of the campaign, were compared with those of all 749 patients with similar presentations during the 12 months before it. When community and generalist physicians were involved, median (110 minutes) physician delay did not decrease during the campaign, whereas it decreased from 65 to 56 minutes (p <0.003) when emergency physicians were involved. Rates of immediate hospitalization (73%) and of transportation by ambulance (47%) of patients managed by community and generalist physicians were unaffected by the campaign, whereas they increased from 96% and 89%, respectively, to 98% (p = 0.09) and 94% (p <0.02) when emergency physicians were involved. Similar observations were made in patients with confirmed acute myocardial infarction and unstable angina and remained highly significant after adjustment for differences in clinical characteristics. Thus, community and generalist physicians did not significantly modify their prehospital management of patients with chest pain despite a public campaign. To be successful, guidelines on the matter have to be developed with the active participation of these physicians.

Aged↗

PubMed1998

Internet integrated in the daily medical practice within an electronic patient record.

Healthcare enters the information age and professionals are finding an ever-growing role for computers in the daily practice of medicine. However, a number of problematic issues are associated with electronic publications, especially through Internet. Whilst access to any information has been improved, access to specific information has become more and more difficult [1], due to the lack of a general meta-knowledge allowing to structure Internet resources. Physicians have to learn and adapt themselves to computers and Internet, but Internet has to meet the specific requirements of Healthcare. Important issues must therefore be addressed to allow a real and daily use of Internet in the medical practice. The paper discusses most of these issues and proposes a solution developed at the University Hospital of Geneva that integrates an Electronic Patient Record with Internet, without compromises on security or on performances and that runs on standard PCs'.

Computer Security↗

PubMed1998

Predictors of inappropriate hospital days in a department of internal medicine.

BACKGROUND: This study aimed to identify predictors of inappropriate hospital days in a department of internal medicine, as a basis for quality improvement interventions. METHODS: The appropriateness of 5665 hospital days contributed by 500 patients admitted to the Department of Internal Medicine, Geneva University Hospitals, Switzerland, was assessed by means of the Appropriateness Evaluation Protocol. Predictor variables included patient's age and sex, manner of admission and discharge, and characteristics of hospital days (weekend, holiday, sequence). RESULTS: Overall, 15% of hospital admissions and 28% of hospital days were rated as inappropriate. In multivariate models, inappropriate hospital days were more frequent among patients whose admission was inappropriate (odds ratio [OR] = 5.3, 95% CI: 3.1-8.4) and among older patients (80-95 years: OR = 3.6, 95% CI: 1.7-7.0, versus <50 years). The likelihood of inappropriateness also increased with each subsequent hospital day, culminating on the day of discharge, regardless of the total length of stay. CONCLUSIONS: This study identified both the admission and the discharge processes as important sources of inappropriate hospital use in a department of internal medicine. The oldest patients were also at high risk of remaining in the hospital inappropriately. Surprisingly, long hospital stays did not generate a higher proportion of inappropriate days than short hospital stays. This information proved useful in developing interventions to improve the hospitalization process.

Adolescent↗

PubMed1998

Integrated computerized patient records: the DIOGENE 2 distributed architecture paradigm with special emphasis on its middleware design.

DIOGENE 2 is a full-scale distributed/open hospital information system that by June 1995 had already achieved its migration from a former mainframe system. Thanks to that architecture there is an obvious need for a common "glue" devoted to tightening up scattered applications into a middleware-based network of interoperability. After this the design of open/distributed Electronic Patient Records (EPRs) became feasible. A brief historical sketch of DIOGENE is presented from its initial to its present phase. A working prototype of these distributed EPRs is discussed showing current achievements during its first stage of production in the clinics of the University Hospitals of Geneva. On-going expansion to other public hospitals, as well as to general practioners (GPs) in the Geneva area, are partly described.

Computer Communication Networks↗

PubMed1998

Full text multilingual automatic morphosemantems for stand-alone or Internet based applications.

The authors present an automatic tool able to provide real-time morphosemantic decomposition of natural language sentences in French, German and English. This tool demonstrates the feasibility of Natural Language Processing on standard PC computers and the technology involved has been successfully implemented in daily used applications in several European hospitals. It considerably alleviates the burden of coding with various international classification and enhances the quality of the final results. This tool, delivered on PC platforms, is highly convivial and provides a versatile interface to any existing applications based on the Microsoft Windows standards. Moreover, all high levels functions have been encapsulated in Object Oriented Components and can therefore be reused using the Common Object Model standards to develop stand-alone or Internet applications.

Classification↗

PubMed1998

Automatic extraction of linguistic knowledge from an international classification.

Automatic extraction of knowledge from large corpus of texts is an essential step toward linguistic knowledge acquisition in the medical domain. The current situation shows a lack of computer-readable large medical lexicons, with a partial exception for the English language. Moreover, multilingual lexicons with versatility for multiple languages applications are far from reach as long as only manual extraction is considered. Computer-assisted linguistic knowledge acquisition is a must. A multilingual lexicon differs from a monolingual one by the necessity to bridge the words in different languages. A kind of interlingua has to be built under the form of concepts to which the specific entries are attached. In the present approach, the authors have developed an intelligent rule-based tool in order to focus on a multilingual source of medical knowledge, like the International Classification of Disease (ICD) which contains a vocabulary of some 20,000 words, translated in numerous languages.

Disease↗

PubMed1998

Happy birthday DIOGENE: a hospital information system born 20 years ago.

Since its birth in 1978, DIOGENE, the Hospital Information System of Geneva University Hospital has been constantly evolving, with a major change in 1995, when migrating from a centralized to an open distributed architecture. Since a few years, the hospital had to face health policy revolution with both economical constraints and opening of the healthcare network. The Hospital Information System DIOGENE plays a significant role by integrating four axes of knowledge medico-economical context for better understanding and influencing resources consumption the whole set of patient reports and documents (reports, encoded summaries, clinical findings, images, lab data, etc.) patient-dependent knowledge, in a vision integrating time and space external knowledge bases such as Medline (patient-independent knowledge) integration of these patient-dependent and -independent knowledges in a Case-Based Reasoning format, providing on the physician desktop all relevant information for helping him to take the most appropriate adequate decision.

Hospital Costs↗

PubMed1998

Alternative ways for knowledge collection, indexing and robust language retrieval.

Definitions are provided of the key entities in knowledge representation for Natural Language Processing (NLP). Starting from the words, which are the natural components of any sentence, both the role of expressions and the decomposition of words into their parts are emphasized. This leads to the notion of concepts, which are either primitive or composite depending on the model where they are created. The problem of finding the most adequate degree of granularity for a concept is studied. From this reflection on basic Natural Language Processing components, four categories of linguistic knowledge are recognized, that are considered to be the building blocks of a Medical Linguistic Knowledge Base (MLKB). Following on the tracks of a recent experience in building a natural language-based patient encoding browser, a robust method for conceptual indexing and query of medical texts is presented with particular attention to the scheme of knowledge representation.

Abstracting and Indexing↗

PubMed1998

Versatility of a multilingual and bi-directional approach for medical language processing.

At the dawn of the 21st century, we are experiencing an exponential growth of online information that is mostly textual, and that benefits from new electronic media, such as the World Wide Web (WWW), to be broadly diffused across borders. However, there is a gap to bridge between holding information and accessing in a relevant way the deep underlying knowledge. Multilingual natural language processing (NLP), once tuned, is certainly the best solution to cope with this era of textual information. This paper focuses on the lesson learned through the joint development of an analyzer and a generator of medical language, within a multilingual context. Concrete examples, derived from the efforts under way in the European GALEN-IN-USE project, illustrate the use of these linguistic tools for the handling of surgical procedures.

Multilingualism↗

PubMed1998

Morpho-semantic parsing of medical expressions.

The task of editing, indexing, storing, and retrieving medical expressions within medical records remains the main objective for the years to come. Therefore, the need for a parser with semantic capabilities able to robustly extract an essential part of the knowledge embedded in the medical record is paramount. The minimal requirements before considering clinical trials are that such a system has to be in position to handle any source of medical information and to conveniently grasp the main key concepts with low silence, good recognition of modalities and acceptable noise. This paper shows that the potential of morpho-semantic parsing is high to meet these conditions. This technique is an important complement to the traditional lexical approach and to expression-oriented systems like controlled vocabularies.

Language↗

PubMed1997

Risk factors for a medically inappropriate admission to a Department of Internal Medicine.

OBJECTIVE: To identify patient- and admission-related risk factors for a medically inappropriate admission to a department of internal medicine. METHODS: Cross-sectional study of a systematic sample of 500 admissions to the department of internal medicine of an urban teaching hospital. The appropriateness of each admission and reasons for inappropriate admissions were assessed using the Appropriateness Evaluation Protocol. Risk factors included the time (day of week and holidays) and manner (through emergency department or direct admission) of admission, patient age and sex, health status of patient and spouse, living arrangements, formal home care services, and informal support from family or friends. RESULTS: Overall, 76 (15.2%) hospital admissions were rated as medically inappropriate by the Appropriateness Evaluation Protocol. In multivariate analysis, the likelihood of an inappropriate admission was increased by better physical functioning of the patient (odds ratio [OR], 1.5; 95% confidence interval [CI], 1.1-2.1 [for 1 SD in Physical Functioning scores]), lower mental health status of the patient's spouse (OR, 2.6; 95% CI, 1.3-5.6), receipt of informal help from family or friends (OR, 3.3; 95% CI, 1.5-7.2), and hospitalization by one's physician (OR, 3.6; 95% CI, 1.7-7.5). Receiving formal adult home care was not associated with inappropriateness of hospitalization. CONCLUSIONS: Inappropriate admissions to internal medicine wards are determined by a mix of factors, including the patient's health and social environment. In addition, the private practitioners' discretionary ability to hospitalize their patients directly may also favor medically inappropriate admissions.

Adolescent↗

PubMed1997

C-reactive protein as a marker for acute coronary syndromes.

BACKGROUND: For several years, acute coronary syndromes have been perceived as causing the most hospital admissions, and even hospital mortality. The syndrome of unstable angina frequently progresses to acute myocardial infarction but its pathogenesis is poorly understood, and prognosis determination is still problematic. We tested the hypothesis that measurement of the C-reactive protein in patients admitted for chest pain could be a marker for acute coronary syndromes. METHODS AND RESULTS: We studied 110 patients admitted with suspected ischaemic heart disease, but without elevated serum creatine-kinase levels at the time of hospital admission. Patients were subsequently divided into two groups based on their final diagnosis: group 1 comprised patients with unstable angina; group 2 patients with acute myocardial infarction. We measured the C-reactive protein at the time of hospital admission. The concentration of C-reactive protein was elevated in 59% of the patients with a final diagnosis of acute myocardial infarction, and in 5% of the patients with a final diagnosis of unstable angina, (P < 0.001). CONCLUSION: This study indicates that C-reactive protein levels measured at the time of admission in patients with suspected ischaemic heart disease could be a marker for acute coronary syndromes, and helpful in identifying patients at high risk for acute myocardial infarction. Measurement of C-reactive protein may have practical clinical significance in the management of patients hospitalized for suspected acute coronary syndromes.

Acute Disease↗

PubMed1997

An improved rapid troponin T test with a decreased detection limit: a multicentre study of the analytical and clinical performance in suspected myocardial damage.

In a multicentre study, we evaluated the analytical and diagnostic performance of the second version of the TROPT rapid test (TROPT 2, CARDIACT in the US). We tested TROPT 2 on 796 blood samples from 487 patients admitted on suspicion of myocardial infarction between 1 and 72 h after onset of symptoms and determined cTnT ELISA and CK MB mass in the corresponding serum samples. Frequency distributions of the results with TROPT 2 showed a detection limit of 0.18 microgram/l (for 50% positive results) as determined by the quantitative cTnT ELISA method. In a total of 796 samples the sensitivities in the detection of myocardial infarction (WHO criteria) 8-12 h after onset of symptoms were highest for cTnT ELISA (98%), followed by the rapid assay and CK MB mass (92%). A subgroup of 87 patients was primarily classified by the WHO criteria for definite infarction. Based on the maximum values within each patient time-series, diagnostic sensitivities for infarction were 100% for TROPT2, cTnT ELISA and CK MB mass. The corresponding specificities were 90%, 82% and 100%, respectively. After reclassification summarizing all cases of myocardial damage (acute and subacute myocardial infarctions and minor myocardial damage) the sensitivities were 87% (TROPT2), 100% (cTnT ELISA) and 71% (CK MB mass). The specificities of all three markers were 100%. Over 50% of all cases of minor myocardial damage were detected by TROPT 2. The clinical evaluation showed that the diagnostic performance of TROPT 2 is only slightly lower than that of cTnT ELISA.

Angina, Unstable↗