Imaging-based patient inclusion model for clinical trial performance optimization.

Abstract

105 Background: In the era of precision medicine, development of new cancer therapies relies strongly on effective selection of target patient population. We hypothesize that computational analysis of imaging data can be used for development of a quantitative population enrichment strategy in clinical trials and thus we aim to establish an appropriate framework for this analysis. Methods: This hypothesis was tested among soft-tissue sarcoma (STS) patients accrued into a randomized Phase III clinical trial (SARC021) that evaluated the efficacy of evofosfamide (Evo), a hypoxia activated prodrug, in combination with doxorubicin (Dox). Notably, SARC021 failed to meet its survival objective (PMC7771354). We tested whether an inclusion/exclusion model based on radiomic analysis and relevant clinical covariates could have been employed to result in a significant treatment benefit of the Evo+Dox combination compared to the standard Dox monotherapy. A total of 163 radiomics features were extracted from lung metastases of 303 patients from the SARC021 trial, divided into demographically matched training and test sets. Stability analysis identified the most reproducible features. Univariable and multivariable models were utilized to discriminate OS in the two treatment groups. Results: A bespoke enrichment framework was established for individualized patient selection, based on model-derived risk score threshold. A radiomic feature, Short Run Emphasis, was identified as the most informative. When combined with tumor histology and smoking history information, an enriched subset (42%) of patients had longer OS in Evo+Dox vs. Dox groups [p = 0.01, Hazard Ratio (HR) = 0.57 (0.36-0.90)], overperforming a clinical-only approach. Application of the same model and threshold value in an independent test set confirmed the significant survival difference (p = 0.002, HR = 0.29 (0.13-0.63), 38% patients included). The breakdown of Dox+Evo treatment benefit depending on proportion of patients included based on the model is shown in the Table. Notably, this process also identified patients most likely to benefit from doxorubicin alone. Conclusions: The study presents a first of its kind radiomic approach for patient enrichment in clinical trials based on a quantitative score. In particular, we have shown that had the novel model been used for selective patient inclusion into the SARC021 trial, it would have met its primary survival objective for patients with metastatic STS.[Table: see text]