Related Experiment Video
Updated: Jul 26, 2025
Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments
Published on: April 30, 2021
Modeling tumor size dynamics based on real-world electronic health records and image data in advanced melanoma
Perrine Courlet1,2, Daniel Abler1,3, Monia Guidi2,4
1Precision Oncology Center, Department of Oncology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
Abstract:
The development of immune checkpoint inhibitors (ICIs) has revolutionized cancer therapy but only a fraction of patients benefits from this therapy. Model-informed drug development can be used to assess prognostic and predictive clinical factors or biomarkers associated with treatment response. Most pharmacometric models have thus far been developed using data from randomized clinical trials, and further studies are needed to translate their findings into the real-world setting. We developed a tumor growth inhibition model based on real-world clinical and imaging data in a population of 91 advanced melanoma patients receiving ICIs (i.e., ipilimumab, nivolumab, and pembrolizumab). Drug effect was modeled as an ON/OFF treatment effect, with a tumor killing rate constant identical for the three drugs. Significant and clinically relevant covariate effects of albumin, neutrophil to lymphocyte ratio, and Eastern Cooperative Oncology Group (ECOG) performance status were identified on the baseline tumor volume parameter, as well as NRAS mutation on tumor growth rate constant using standard pharmacometric approaches. In a population subgroup (n = 38), we had the opportunity to conduct an exploratory analysis of image-based covariates (i.e., radiomics features), by combining machine learning and conventional pharmacometric covariate selection approaches. Overall, we demonstrated an innovative pipeline for longitudinal analyses of clinical and imaging RWD with a high-dimensional covariate selection method that enabled the identification of factors associated with tumor dynamics. This study also provides a proof of concept for using radiomics features as model covariates.
Insights
This study developed a tumor growth model using real-world data from advanced melanoma patients treated with immune checkpoint inhibitors (ICIs). The model identified key clinical factors and radiomics features influencing treatment response, improving predictive capabilities.
Area of Science:
- Pharmacometrics
- Oncology
- Machine Learning
- Radiomics
Background:
- Immune checkpoint inhibitors (ICIs) have transformed cancer therapy, yet patient response varies significantly.
- Model-informed drug development (MIDD) is crucial for understanding treatment response and identifying predictive biomarkers.
- Translating findings from clinical trials to real-world data (RWD) is essential for broader applicability.
Purpose of the Study:
- To develop a tumor growth inhibition model using RWD from advanced melanoma patients receiving ICIs.
- To identify clinical and imaging-based covariates associated with tumor dynamics and treatment response.
- To demonstrate an innovative pipeline for longitudinal analysis of RWD incorporating radiomics.
Main Methods:
- Developed a tumor growth inhibition model using RWD (clinical and imaging) from 91 advanced melanoma patients.
- Applied standard pharmacometric approaches to identify covariate effects on baseline tumor volume and growth rate.
- Utilized a combined machine learning and pharmacometric approach for exploratory analysis of radiomics features in a subgroup.
Main Results:
- Identified significant covariate effects of albumin, neutrophil-to-lymphocyte ratio, and ECOG performance status on baseline tumor volume.
- Found NRAS mutation to be a significant covariate affecting tumor growth rate.
- Demonstrated the feasibility of incorporating radiomics features as model covariates, showing their association with tumor dynamics.
Conclusions:
- The developed model effectively characterizes tumor dynamics in advanced melanoma patients treated with ICIs using RWD.
- Clinical factors (albumin, NLR, ECOG, NRAS mutation) and radiomics features are important predictors of treatment response.
- This study validates an innovative approach for analyzing longitudinal RWD and highlights the potential of radiomics in MIDD.
