Improving the accuracy of therapy descriptions in clinical trials using a bottom-up approach

Randomized clinical trial (RCT) reports commonly have complicated therapy descriptions that are written in free-text. Drug therapy is difficult to describe due to the dynamic nature of how protocols change and the many ways drugs can be administered. Details regarding protocol changes and drug administration must be explained clearly for reproducibility and reliability. A process model supplemented with concept ontologies can clarify the dynamics of how therapies change and make knowledge more explicit. We demonstrated the process to develop a representation model to reveal specific context concerning drug therapies within clinical trial report literature. A PubMed search was conducted to identify RCTs on non-small-cell lung cancer (NSCLC) pertaining to epithelial growth factor receptor (EGFR) mutations. Twenty-seven clinical trials were used to develop the model using a bottom-up approach. This representation describes drug dosage, administration details, and drug cycles within different experimental arms and control groups. We then presented preliminary evaluation of the clarity and understandability of the representation.