Overview
Assessing real-world response rates (rwRR) is essential for understanding clinical outcomes in cancer patients beyond clinical trial settings. This study utilizes machine learning to evaluate rwRR in cohorts of lung, colon, and breast cancer patients aligned with clinical trials. By analyzing real-world data and leveraging machine learning techniques, the study aims to uncover insights into clinical outcomes across different cancer types in a significantly more scalable and flexible manner.
Why this matters
Analyzing response as an outcome and measuring response rate as an endpoint are essential aspects of conducting effective studies in oncology clinical research. This study offers significant insights into treatment response rates among cancer patients beyond clinical trial settings, to enhance our understanding of the relationships between endpoints in clinical trials and real-world data, which is crucial for advancing the utilization of real-world evidence (RWE). The study findings also emphasize the importance of refining methods for matching trial characteristics to improve the robustness of the study results and findings.
View the abstract on the ISPOR website
More from Flatiron Health at ISPOR US 2024
Read about Flatiron's accepted research and presence at ISPOR US.
