Feichen Shen and Sourav Jana, software architecture and software engineering computer science Ph.D. students working with their faculty advisor Dr. Yugi Lee, presented their work on “Semantic Search Engine for Clinical Trials” at the SHARPn Summit 2012, at Mayo Clinic in Rochester, MN, organized by Mayo Clinic on June 11-12. Feichen Shen is currently working this summer in an Intern-Biostats (PHD) position at the Department of Health Sciences Research at Mayo Clinic. The Mayo Clinic is one of the top most highly reputed institutes for advanced research in the United States. Sourav Jana received a CSEE department travel grant for the trip to the SHARPn Summit 2012.
Abstract of the presentation: Semantic Search Engine for Clinical Trials Standardizing the representation and content of eligibility criteria is an important step for obtaining enhanced efficiency of clinical trials. There have been several attempts to formalize eligibility criteria through establishing the creation of ontologies and other structured representations. This poster presents a semantic approach for facilitating accurate matches between clinical trials and eligible subjects. For this purpose, firstly, clinical trial studies from Clinicaltrials.gov have been clustered. Secondly, the clinical trial ontology called the MindTrial Eligibility ontology (MEO) was modeled based on the inclusion and exclusion criteria for obtained clusters. Thirdly, an open-ended query is generated using the Semantic Web Rule Language (SWRL) to discover potential participants in clinical trials via facilitating partial matching through relaxation of eligibility criteria. Two kinds of search interfaces are designed for selecting patients and/or potential volunteers. One is based on a detailed fine-grained checklist view where fields identical to those in the query can be selected as inclusion (desired) or exclusion (NOT desired) criteria. The second kind of query interface is based on summarized queries and reasoning that are expanded by the MEO ontology and computed on a subset of volunteer responses. The prototype system for the proposed model has been implemented to support customized searches for potential recruiters. This system allows for the flexibility of using free text while capturing the semantics of the criteria for computer readability. This approach surely leads to better characterization of both human volunteers and clinical study requirements, thus resulting in accurate and efficient matching of subjects with clinical studies. The outcomes obtained through the application of our approach can be used to generate an atomic set of eligibility criteria that would be readily incorporated into intelligent search engines in databases of clinical trials and subjects.