Deriving breast cancer chemotherapy patterns from real-world data.

Abstract

e13586 Background: Real World Data (RWD) collected during routine medical practice can help in clinical trial design, planning and execution. In addition, it can provide a compelling picture of safety of medical products, and account for all potential adverse events that can be encountered in routine clinical practice. However, raw drug information about chemotherapy in cancer care is not readily understandable in the format it is collected. Analytical techniques need to be applied to extract regimen information, which includes drugs, dosage, number of cycles and cycle length. Methods: A retrospective study was performed using data on 7,798 breast cancer patients from the TriNetX Network, a federated network of de-identified, HIPAA-compliant, health data from 21 healthcare organizations across North America as of May 2022. We investigated a method built on rule-based algorithm and clustering analysis to extract regimens and their patterns of administration and align them into lines of treatment (LOT). To derive drug administration patterns, we clustered administration time periods using three features: total number of drug administrations, median number of days between drug administrations, and standard deviation of the days between drug administrations. Results: The patterns of administration that correspond to the two most common regimens for Erb-B2 receptor tyrosine kinase 2 negative group (ERBB2-) stages 1, 2 and 3 are shown. We looked at patients with Hormone Receptor (HR+) positive and Triple Negative (TN) breast cancer. Results of our analysis were in a close agreement with NCCN Guidelines. However, regimen administration patterns varied. This information can be useful to characterize patients based on the adherence to the expected chemotherapy regimens. It can also provide meaningful insight into burden of illness, such that patients who have higher variability of the drug administration might be faced with clinical problems such as drug tolerability or side effects. The variability might also signify access to care challenges. Conclusions: Understanding regimen LOT and administration patterns is central to research based on RWD, but it can also be useful for clinical trial design, execution, as well as site selection and patient recruitment for clinical trials. [Table: see text]