Home Aims & Objectives NaCTeM Services Text Mining Tools Text Mining Infrastructures Text Mining for Biodiversity Resources Terms & Conditions FAQ News & Events People Projects Current Projects 10BE5 AIRC EPHOR Mental Health Past Projects ADVISES Arabic WordNet ASSIST ASSERT AstraZeneca Project Automated screening for systematic reviews BBC Big Mechanism BOOTStrep Bott and Co. CheTA Clinical Trials COPIOUS DECA eScholar EMPATHY Europe PMC FixRep FLaReNet Graphene HSE Lloyds Infectious Diseases INTUTE ISHER KISTI Pathway META-NET Mining for Public Health Mining the History of Medicine MMPathIC NCS TOX ONDEX OpenMinTeD OSSMETER Pacific Life Re PathText/
Refine SLiM Thalia Turing Project Publications Community External Collaboration Vacancies Teaching & Tuorials Feedback How to find us Site Map Search

Clinical Trials

The large amount of clinical trial data has lead to an information overload problem, making it difficult to locate the precise information that is required. This project aims to address this problem through the development of a search application that can help users to narrow down their search efficiently, and assist in the creation of new protocols.

ASCOT

ASCOT (Assisting Search and Creation Of clinical Trials) is the search application being developed during this project. It applies text mining and data mining methods to large clinical trial collections, in order to enrich them with metadata. The different types of metadata added serve as effective tools for narrowing down searches. ASCOT additionally integrates a component for recommending eligibility criteria based on a set of selected protocols.

Search begins with a textual query. Then, it can be narrowed down in a multitude of ways:

• by selecting values for properties that correspond to XML fields of the clinical trial protocols.
• by selecting one of the automatically induced and labelled clusters of clinical trial protocols.
• by selecting a UMLS or SNOMED CT concept to occur in the (inclusion or exclusion) eligibility criteria of the clinical trial protocols.
• by selecting one of the multiword terms, automatically extracted by the C-Value algorithm.

The above alternatives can be applied iteratively until the result seems satisfactory to the user. The user can select documents and add them to a separate selection board for further processing. Probable eligibility criteria based on the selected documents are generated automatically.

Block diagram describing the interacting software components

A demonstration video and an online demonstrator are available.

Project information

The project started in 2010 and is funded by the Manchester Biomedical Research Centre and JISC.

Project Team

Principal Investigator: Prof. Sophia Ananiadou

Researchers: Dr. Ioannis Korkontzelos and Dr. Rafal Rak

Software Engineers: Jacob Carter, Andrew Rowley

Publications

Ioannis Korkontzelos, Tingting Mu and Sophia Ananiadou (2012). ASCOT: a text mining-based web-service for efficient search and assisted creation of clinical trials. BMC Medical Informatics and Decision Making, 12(Suppl 1), S3

Ioannis Korkontzelos and Sophia Ananiadou (2012). ASCOT: Assisting Search and Creation of clinical Trials. Proceedings of the ACM SIGHIT International Health Informatics Symposium (IHI 2012), Miami, Florida, USA. Demo paper.

Ioannis Korkontzelos, Tingting Mu, Angelo Restificar and Sophia Ananiadou (2011). Text mining for efficient search and assisted creation of clinical trials. Proceedings of the ACM Fifth International Workshop on Data Mining in Biomedical Informatics in Conjunction with CIKM, Glasgow, Scotland.