Abstract 2611: A crowdsourcing-based clinical trial information curation and searching system

Targeted cancer therapies based on actionable mutations identified are the future of cancer treatment. Besides those approved by the Food and Drug Administration (FDA) for different types of cancers, many other target therapy drugs are in development under different phases of clinical trials. Access to information about these clinical trials is important to health care professionals and patients. Public clinical trials database (www.clinicaltrials.gov) provides a very comprehensive resource for clinicians and researches to search for relevant clinical trials based on different kinds of searching criteria. However, due to the complexity of wording and phasing upon submission, some of the searching results returned by native search engine did not perfectly match the search criteria. Many undesired results are presented with false positives and false negatives when users are searching for clinical trials targeting specific actionable mutations. To tackle this problem, we developed a crowd-sourcing based clinical trial curation and searching system on top of the information extracted from public database. We divide the information extracted from clinicaltrials.gov into three different levels: standard, easy-to-clean and unstructured. With the crowdsourcing approach, our online system can harness the brainpower of biological scientists to translate the most unstructured information such as cancer types, gene mutations into standard format that is easy to be queried. In the searching phase, we combine the aspects of actionable mutation, cancer type, location, and clinical trial phase to select the best matches between patient conditions and clinical trials in our curated database. With the same searching criteria, our system can provide more relevant clinical trials compared with those provided by clinicaltrials.gov. The curation system is currently open to reviewers with eligibility check. And the search engine is publicly available at: https://agis.admerahealth.com/AGIS/ClinTrials/. Citation Format: Pengfei Yu, Qingxuan Song, Yang Han, Guanghui Hu. A crowdsourcing-based clinical trial information curation and searching system [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2017; 2017 Apr 1-5; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2017;77(13 Suppl):Abstract nr 2611. doi:10.1158/1538-7445.AM2017-2611