Jean Charlet

Building an ontology of pulmonary diseases with natural language processing tools using textual corpora.

Pathologies and acts are classified in thesauri to help physicians to code their activity. In practice, the use of thesauri is not sufficient to reduce variability in coding and thesauri are not suitable for computer processing. We think the automation of the coding task requires a conceptual modeling of medical items: an ontology. Our task is to help lung specialists code acts and diagnoses with software that represents medical knowledge of this concerned specialty by an ontology. The objective of the reported work was to build an ontology of pulmonary diseases dedicated to the coding process. To carry out this objective, we develop a precise methodological process for the knowledge engineer in order to build various types of medical ontologies. This process is based on the need to express precisely in natural language the meaning of each concept using differential semantics principles. A differential ontology is a hierarchy of concepts and relationships organized according to their similarities and differences. Our main research hypothesis is to apply natural language processing tools to corpora to develop the resources needed to build the ontology. We consider two corpora, one composed of patient discharge summaries and the other being a teaching book. We propose to combine two approaches to enrich the ontology building: (i) a method which consists of building terminological resources through distributional analysis and (ii) a method based on the observation of corpus sequences in order to reveal semantic relationships. Our ontology currently includes 1550 concepts and the software implementing the coding process is still under development. Results show that the proposed approach is operational and indicates that the combination of these methods and the comparison of the resulting terminological structures give interesting clues to a knowledge engineer for the building of an ontology.

Authoring business rules grounded in OWL ontologies

This paper describes an approach in the double context of business rules and techniques of the semantic web, the ontologies. This approach consists of enabling the use of business rules to automate the decisions on domains which semantic is formalized with an ontological language. Our main objective is to enable business users to edit, manage and execute business rules grounded in ontologies without resorting to an expert. The implementation is based on the Business Rule Management System (BRMS) IBM WebSphere ILOG JRules.

Causal model-based knowledge acquisition tools: discussion of experiments☆

Abstract The aim of this paper is to study causal knowledge and demonstrate how it can be used to support the knowledge acquisition process. The discussion is based on three experiments we have been involved in. First, we identify two classes of Causal Model-Based Knowledge Acquisition Tools (CMBKATs): bottom-up designed causal models and top-down designed causal models. We then go on to discuss the properties of each type of tool and how they contribute to the whole knowledge acquisition process.

Building medical ontologies based on terminology extraction from texts: methodological propositions

In the medical field, it is now established that the maintenance of unambiguous thesauri is accomplished by the building of ontologies. Our task in the PertoMed project is to help pneumologists code acts and diagnoses with a software that represents medical knowledge by an ontology of the concerned specialty. We apply natural language processing tools to corpora to develop the resources needed to build this ontology. In this paper, our objective is to develop a methodology for the knowledge engineer to build various types of medical ontologies based on terminology extraction from texts according to the differential semantics theory. Our main research hypothesis concerns the joint use of two methods: distributional analysis and recognition of semantic relationships by lexico-syntactic patterns. The expected result is the building of an ontology of pneumology.

ACTE: a causal model-based knowledge acquisition tool

In this paper, knowledge acquisition is presented as the instantiation of the so-called conceptual model by domain knowledge. In this framework we describe Acte, a causal model-based knowledge acquisition tool designed to assist in knowledge acquisition for a heuristic classification problemsolver.

Managing free text for secondary use of health data.

OBJECTIVE To summarize the best papers in the field of Knowledge Representation and Management (KRM). METHODS A comprehensive review of medical informatics literature was performed to select some of the most interesting papers of KRM and natural language processing (NLP) published in 2013. RESULTS Four articles were selected, one focuses on Electronic Health Record (EHR) interoperability for clinical pathway personalization based on structured data. The other three focus on NLP (corpus creation, de-identification, and co-reference resolution) and highlight the increase in NLP tools performances. CONCLUSION NLP tools are close to being seriously concurrent to humans in some annotation tasks. Their use could increase drastically the amount of data usable for meaningful use of EHR.

Implementation and management of a biomedical observation dictionary in a large healthcare information system

OBJECTIVE This study shows the evolution of a biomedical observation dictionary within the Assistance Publique Hôpitaux Paris (AP-HP), the largest European university hospital group. The different steps are detailed as follows: the dictionary creation, the mapping to logical observation identifier names and codes (LOINC), the integration into a multiterminological management platform and, finally, the implementation in the health information system. METHODS AP-HP decided to create a biomedical observation dictionary named AnaBio, to map it to LOINC and to maintain the mapping. A management platform based on methods used for knowledge engineering has been put in place. It aims at integrating AnaBio within the health information system and improving both the quality and stability of the dictionary. RESULTS This new management platform is now active in AP-HP. The AnaBio dictionary is shared by 120 laboratories and currently includes 50 000 codes. The mapping implementation to LOINC reaches 40% of the AnaBio entries and uses 26% of LOINC records. The results of our work validate the choice made to develop a local dictionary aligned with LOINC. DISCUSSION AND CONCLUSIONS This work constitutes a first step towards a wider use of the platform. The next step will support the entire biomedical production chain, from the clinician prescription, through laboratory tests tracking in the laboratory information system to the communication of results and the use for decision support and biomedical research. In addition, the increase in the mapping implementation to LOINC ensures the interoperability allowing communication with other international health institutions.

The management of medical knowledge : between non-structured documents and ontologies

In this paper, we study the ways of representing medical knowledge in an information system. We argue that the data-processing support is not neutral and conditions the representations that are built. In addition, the requirements of medical activity — work with the computerized record, needs for indexing, constraints of coding, etc. — have consequences for modelling and for applications which each correspond to different assumptions about the handling of information and knowledge. In particular, the diversity of the activity is such that the question of the documents and their supports has to be considered, as they generally provide poorly structured information; formal models of knowledge as ontologies also have to be addressed.We propose to model the exchange and the production of information and knowledge within care units of the hospital in the context of the knowledge management, so as to account for these diversities of modelling and to direct future research and development. In addition, we consider the organisational training made possible by this type of analysis grid.These proposals are illustrated by research and medical applications developed in a hospital context.RésuméDans cet article, nous étudions les façons de représenter les connaissances médicales dans un système informatique. Nous argumentons que le support informatique n’est pas neutre et conditionne les représentations construites. Par ailleurs, les nécessités de l’activité médicale — travail avec le dossier informatisé, nécessités d’indexation, contraintes de codages, etc. — obligent à réfléchir des modélisations puis des applications qui correspondent chacune à des prises en charge de l’information et des connaissances différentes. En particulier, la diversité de l’activité implique de s’intéresser, d’un côté, à la question des documents et de leurs supports, modèles d’informations non structurés par excellence et, d’un autre côté, à des modèles formels des connaissances que sont les ontologies.Nous proposons de modéliser l’échange et la production d’informations et de connaissances au sein de l’unité de soin hospitalière dans le contexte de la gestion des connaissances pour tenir compte de ces diversités de modélisation et pour orienter des recherches et développements futurs. Nous essayons par ailleurs de questionner les apprentissages orga-nisationnels qu’une telle grille d’analyse permet de prendre en compte et d’accompagner.Ces propositions sont illustrées par des recherches et applications médicales développées en milieu hospitalier.

Causal Model-Based Knowledge Acquisition Tools: Discussion of Experiments

The aim of this paper is to study causal knowledge and demonstrate how it can be used to support the knowledge acquisition process. The discussion is based on three experiments we have been involved in. First, two classes of Causal Model-Based Knowledge Acquisition Tools are identified: bottom-up designed causal models and top-down designed causal models. The properties of each type of tool and how they contribute to the whole knowledge acquisition process is then discuted.

Developing a knowledge base to support the annotation of ultrasound images of ectopic pregnancy

BackgroundEctopic pregnancy is a frequent early complication of pregnancy associated with significant rates of morbidly and mortality. The positive diagnosis of this condition is established through transvaginal ultrasound scanning. The timing of diagnosis depends on the operator expertise in identifying the signs of ectopic pregnancy, which varies dramatically among medical staff with heterogeneous training. Developing decision support systems in this context is expected to improve the identification of these signs and subsequently improve the quality of care. In this article, we present a new knowledge base for ectopic pregnancy, and we demonstrate its use on the annotation of clinical images.ResultsThe knowledge base is supported by an application ontology, which provides the taxonomy, the vocabulary and definitions for 24 types and 81 signs of ectopic pregnancy, 484 anatomical structures and 32 technical elements for image acquisition. The knowledge base provides a sign-centric model of the domain, with the relations of signs to ectopic pregnancy types, anatomical structures and the technical elements. The evaluation of the ontology and knowledge base demonstrated a positive feedback from a panel of 17 medical users. Leveraging these semantic resources, we developed an application for the annotation of ultrasound images. Using this application, 6 operators achieved a precision of 0.83 for the identification of signs in 208 ultrasound images corresponding to 35 clinical cases of ectopic pregnancy.ConclusionsWe developed a new ectopic pregnancy knowledge base for the annotation of ultrasound images. The use of this knowledge base for the annotation of ultrasound images of ectopic pregnancy showed promising results from the perspective of clinical decision support system development. Other gynecological disorders and fetal anomalies may benefit from our approach.