Deriving breast cancer chemotherapy patterns from real-world data.

• DOI: 10.1200/jco.2023.41.16_suppl.e13586
• Publication Date: 2023-06-04T14:59:30Z
• Authors: Jack W. London; Julia ORourke; Jeff Warnick; John Doole; Luc De Keyser; Zuzanna Drebert; Olivia Wan; Courtney Thompson; Matvey Palchuk
• Keywords: Regimen; Medical record

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