An interactive retrieval system for clinical trial studies with context-dependent protocol elements

An interactive retrieval system for clinical trial studies with context-dependent protocol elements

Publication date: Dec 01, 2019

A clinical trial protocol defines the procedures that should be performed during a clinical trial. Every clinical trial begins with the design of its protocol. While designing the protocol, most researchers refer to electronic databases and extract protocol elements using a keyword search. However, state-of-the-art retrieval systems only offer text-based searches for user-entered keywords. In this study, we present an interactive retrieval system with a context-dependent and protocol-element-selection function for successfully designing a clinical trial protocol. To do this, we first introduce a database for a protocol retrieval system constructed from individual protocol data extracted from 184,634 clinical trials and 13,210 frame structures of clinical trial protocols. The database contains various semantic information that enables the protocols to be filtered during the search operation. Based on the database, we developed a web application called the clinical trial protocol database system (CLIPS; available at, which enables an interactive search by utilizing protocol elements. CLIPS provides the options to select the next element according to the previous element in the form of a connected tree, thus enabling an interactive search for combinations of protocol elements. The validation results show that our method achieves better performance than existing databases in predicting phenotypic features.


Concepts Keywords
Accounting Previously selected protocol
Atherosclerosis Retrieval technology
Biomedical Selected protocol
Cambridge Http
CB2 MeSH cover protocols
Chemical Compound Search engine
Clinical Protocol Relational database
Clinical Trial Conditions trial protocols
Clinical Trial Protocol Obtains protocol
Clinical Trials High objective protocol
Crossover HPO
Daejeon Download detailed protocol
Dispersion Identifiers NCTID protocols
Gender JSON
Google Scholar Label code protocol
Graph API
Immunity VOLUME protocol
Interval Ratio Communication protocol
JSON Protocol
KAIST Preprint
Kaist Clinical trial
Korea Open science
Mail Design of experiments
MeSH Digital libraries
Patient Safety Clinical research
Perpetuity Knowledge
Phase III Articles
Phenotype Health
Phenotypic Clinical protocols
Protocol Clinical protocol
PubMed G Adrenocortical Carcinoma
Related Rights Clinicaltrials gov Cancers
Relational Database VOLUME Neoplasms
Schema Diseases disorders
Scopus Large biological networks
Semantic Phenotypes chemical compounds
Semantic Search Fig keyword search
Semantic Search Engine Search interface
Skeleton Phenotype chemical compound
Statistical Sampling Interactive search
Statistical Significance Clinical protocols
Table Key Massive biological networks
Tree Retrieval technology
Cover protocols
Database suitable protocol
Imperfect protocol
Conventional search system
Selected protocol
Obtains protocol
Search operation
Download detailed protocol
Suitable references protocol
Label code protocol
Individual protocol
Structural protocol
Raw text protocol
Desired protocol
Ultimate search system
Chemical compound entities
Protocol search task
Search keyword mining
Search systems
Objective protocol
Search filters
Lower keyword search


Type Source Name
drug DRUGBANK Tropicamide
disease MESH Park12
drug DRUGBANK Spinosad
disease MESH growth
disease MESH multiple
disease MESH cancer
disease MESH atherosclerosis
drug DRUGBANK 2′-deoxyuridylic acid
disease MESH Congenital Abnormality
disease MESH Syndrome
drug DRUGBANK Alpha-1-proteinase inhibitor
drug DRUGBANK Gold
disease MESH Abdominal neoplasm
disease MESH Adrenocortical Carcinoma
disease MESH satisfaction
drug DRUGBANK Pentaerythritol tetranitrate
disease MESH Cardiovascular Infections


Download Document

Leave a Comment

Your email address will not be published. Required fields are marked *