Description du projet :
Background: Modern healthcare relies on a sound methodological approach combining experimental observations and statistical analysis. The so-called evidence-based medicine collects empirical observations to confirm or infirm a
given clinical hypothesis. Unfortunately, clinical practice guidelines, which constitute the main clinical decisionsupport instrument, cover only a fraction of what a physician is likely to observe in practice. This problem is especially acute for rare diseases (RD) because physicians are then confronted with cases they have rarely met during their professional history. Although individually rare, physicians are very likely to meet patients suffering from RDs as rare diseases are estimated to affect about 8% of the patients. It has been shown that in such a context, where information is sparse, that health-related contents of the web, provided it is powered with appropriate access engines, can provide an effective source of evidence for both the medical practitioner and the patient. Objective: The WeIRD project aims to provide the informational instruments needed to navigate, search and ultimately question the web evidence space of RD by providing access to high-quality specific contents helpful to help diagnosing RD.
Deliverables: The project must deliver the following deliverables: 1. a library of web documents (WeIRD-Library), harvested from legacy sources (case report, knowledge bases such as Orphanet, OMIM, Swiss-Prot, locus-specific
databases'), to comprehensively store all information relevant for RD; 2. a decision-support system (WeIRD-DSS) to help end-users answering medical questions. In WeIRD-DSS, each answer will be provided with a set of links to
legacy sources so that erroneous answers can be easily discarded; thus iteratively improving the knowledge base of the WeIRD-DSS. Methods: the system will use advanced information retrieval and text mining methods to
holistically crawl, index and finally analyze all the explicit and implicit knowledge available on Rare Diseases.
Evaluation: 1. The evaluation will be using the Cranfield paradigm including to assess the best acquisition channels for health-related information; 2. Assess the best data acquisition channels for health-related information.
Exploitation and availability: the resulting web services and interfaces will be publicly available for clinicians, researchers and patients. Depending on the success, it could become an SIB (Swiss Institute of Bioinformatics)
infrastructure resource.
Research team within HES-SO:
Gaudinat Arnaud
, Mottin Luc
, Ruch Patrick
Partenaires académiques: 549,Information et documentation; Ruch Patrick, 549,Information et documentation
Durée du projet:
01.05.2015 - 30.11.2017
Montant global du projet: 183'000 CHF
Statut: Completed
SWITCH edu-ID
Administration
