Correlating eligibility criteria generalizability and adverse events using Big Data for patients and clinical trials

• DOI: 10.1111/nyas.13195
• Publication Date: 2016-09-06T14:46:46Z
• Authors: Anando Sen; Patrick B. Ryan; Andrew Goldstein; Shreya Chakrabarti; Shuang Wang; Eileen Koski; Chunhua Weng
• Keywords: Adult; Clinical Trials as Topic; Patient Selection; Computational Biology; Systemic Inflammatory Response Syndrome; 3. Good health; Translational Research, Biomedical; 03 medical and health sciences; 0302 clinical medicine; Anti-Infective Agents; Sepsis; Data Mining; Electronic Health Records; Humans; Software

Randomized controlled trials can benefit from proactive assessment of how well their participant selection strategies during the design eligibility criteria influence study generalizability. In this paper, we present a quantitative metric called generalizability index for traits 2.0 (GIST 2.0) to assess priori (based on population representativeness) clinical trial by accounting dependencies among multiple criteria. The was evaluated 16 sepsis identified ClinicalTrials.gov , with adverse event reports extracted results sections. correlation between GIST scores and events analyzed. We found that score significantly correlated total serious (weighted coefficients 0.825 0.709, respectively, P < 0.01). This exemplifies promising use Big Data in electronic health records optimizing studies.