Format: HTML | BibTeX | DC | MARC | MARCXML

Association Studies Assisted by Inference and Semantic Technologies (ASSIST)

Project Id: IST-2002-027510

Abstract: ASSIST aims to provide medical researchers of cervical cancer with an integrated environment that will virtually unify multiple patient record repositories, physically located at different laboratories, clinics and/or hospitals. Researchers will be able to combine phenotypic and genotypic data and perform association studies on larger sets of patient records from several clinics.

Keywords: Biomedical Informatics, Electronic Health Record, eHealth Networks and Architectures, Association Studies, Health Professionals' Knowledge, Semantic Inference

Description

Objectives of the project: Cervical cancer is the second most common cancer worldwide with 60000 new cases and 30000 deaths each year in Europe alone, despite a significant progress in early diagnosis and treatment. Infection by the human papillomavirus (HPV) is accepted as the central risk factor for cervical cancer. However, it is unlikely to be the sole cause for developing cancer. Ongoing research includes investigating the role of specific genetic and environmental factors in determining HPV-persistence and subsequent progression of disease.
Association studies among (i) genetic characteristics and environmental agents and virus characteristics can suggest pathogenetic mechanisms that will provide new markers of risk, diagnosis and prognosis, and possibly treatment.

The main objectives of assist are to :
Unify multiple patient record repositories
Automate the process of evaluating medical hypotheses (association studies type)
Allow researchers to combine phenotypic and genotypic data
Provide an inference engine capable of statistically evaluating medical
Offer expressive, graphical tools for medical researchers to post their queries.

Project description: In order to facilitate association studies (associating genotypic and phenotypic factors related to cervical cancer) ASSIST resorts to medical inference applied on real patient data. Following the semantic approach, ASSIST will step on the standards and research results briefly presented earlier in order to build its Medical Knowledge Base. The targeted virtual unification of the participating archives and interpretation of their content relies upon the semantic indexing of their records. Unlike the conventional way of treating stored medical information as alphanumeric data structures whose interpretation is carried out by the human user, ASSIST’s inference engine will :

Support the virtual unification of the participating archives by translating medical concepts into syntactic values that the legacy systems of the participating archives may perceive and
Undertake the whole process of (statistically) evaluating medical hypotheses and producing medically important associations based on the collected data.

In addition to this inference engine, the proposed architecture will incorporate two important interfacing modules :
a) The first is the interface to its users (mainly medical researchers). It will offer expressive tools for posing their queries. The most interesting among these tools would be a graphical environment for submitting research hypotheses whose validity is to be evaluated. This interface will be medical knowledge aware in the sense that it will allow expression of domain specific queries and particular hypotheses by referring to medical ontologies (including gene related ones) contained in the Medical Knowledge Base.
b) The second type of interfaces will support exchange of data between ASSIST’s core engine and the participating medical archives in a way transparent to the end user.

Assist will respect and promote the ethical principles that guide current medical research activities and will be designed in full compliance to the legal and ethical national EU requirements and code of practice. Special care will be taken so as to avoid violation of any form of patient privacy during system operation. To this end, only anonymised patient information will be handled by the assist system, produced by state-of- the art anonymisation techniques and standards.

Expected Results & Impacts: Upon successful completion, the assist platform aspires to function as an important technologiy enabler for cevical cancer research by allowing any medical group active this area to use this facilities and/or contribute their own results. Therefore, assist will adress the need of a large sample sizes and will help to promote collaborative international biomedical research in the area of cervical cancer.

Assist will enable the cervical cancer medical researchers to use various HVP data, environmental, lifestyle and medical history items from diverse medical records, with minimal effort and cost. The investigation of associations among all these factors and genetic data will identify risk factors that can then be used at the point of care by gynecologists to identify women, who are high risk of developing cervical cancer. Consequently, low-risk women can avoid costly and potentially morbid diagnostic and therapeutic procedures while high-risk women will receive appropriate treatment.

Through assist, clinical researchers will be able to ask complex questions in order to extract the subset of data they need. As a result, old examination results and past findings will be easily reusable. This feature is excepted to be of particular benefit for cervical cancer, whose evaluation requires long-term studies including also referral to patients' antecedents and descendants.

Coordinator

Centre for Research and Technology Hellas Informatics and Telematics Institute (CERTH-IT)

Contacts

Pericles A. Mitkas[PPL-200701-007]
Detailed record - Similar records

General information

Timetable: From 01/2006 to 12/2008

Instrument: Specific Targeted Research Projects (STREP)

Website: [www.assist.iti.gr]

Budget

Total cost: € 4,190,946.00

Grants: € 2,630,000.00 [EC]

Knowledge ID: #PRJ-200701-006

Record created 2007-05-29, last modified 2007-07-04

Rate this document:

Be the first to review this document.

Discuss this document: