Skip to content

Evaluation of real-world response rate in clinical trial-aligned cohorts of patients with lung, colon and breast cancer using machine learning


April 2024


Zhang C, Krismer K, Wang X, et al. Evaluating real-world response-based endpoint in the clinical trial settings among aNSCLC, mCRC and mBC patients. Poster presented at: ISPOR US 2024; May 5-8, 2024; Atlanta, GA. Accessed May 7, 2024.


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.