Researchers have developed a "digital twin" model that leverages clinical and molecular data to predict how cancer patients will respond to specific chemotherapy regimens. This innovative approach aims to optimize treatment selection using readily available clinical tests.
The digital twin model, built using FarrSight®-Twin technology, integrates clinical data with extensive gene panel or whole-exome and transcriptome sequencing. This allows for the simulation of individual therapeutic responses to chemotherapy, according to the study presented at the 36th EORTC-NCI-AACR Symposium on Molecular Targets and Cancer Therapeutics.
Methodology
The study involved creating composite digital twins of clinical trial participants with various cancers, including early-stage and metastatic breast cancer, metastatic pancreatic cancer, and relapsed ovarian cancer. These twins were used to simulate eight historical clinical trials across different cancer types and treatment regimens. The trials compared different chemotherapy regimens, such as anthracyclines, taxanes, platinum-based drugs, capecitabine, and hormone treatments.
The research team compared the predicted log odds ratio for overall response rates (ORR) generated by the digital twin model against the reported log odds ratios from the actual trials. The model was then applied to predict the optimal standard-of-care treatment for different patient cohorts.
Key Findings
The study demonstrated that the predicted log odds ratios for overall response rates in each treatment arm were concordant across the eight clinical trials. The model showed significant improvement in drug response rates (ORR = 2.55, Fisher’s exact test P < .001) and increased overall survival with cohort enrichment (log rank P < .0001). Furthermore, the model accurately predicted overall survival across 23 solid tumors with an AUC of 0.78.
Further analysis revealed that patients in The Cancer Genome Atlas cohort who received treatments recommended by the digital twin model had significantly better therapeutic responses (Fisher’s exact test P < .0001) and survival outcomes (log rank P < .0001) compared to those receiving alternative standard-of-care therapies.
Expert Commentary
Uzma Asghar, MBBS, PhD, MRCP, Co-Founder and Chief Scientific Officer at Concr, stated, "We are excited to apply this type of technology by simulating clinical trials across different tumor types to predict patients’ response to different chemotherapies, and the results are encouraging."
Timothy Yap, MBBS, PhD, FRCP, a medical oncologist at The University of Texas MD Anderson Cancer Center and Co-Chair of the EORTC-NCI-AACR Symposium, commented, "If we can exploit digital tools to make this process quicker and easier, that should help us find better treatments for patients more efficiently in the future."
Clinical Implications
The study authors suggest that the digital twin model can accurately predict treatment responses for different chemotherapy drug classes, optimizing treatment choice for individual patients using currently available clinical tests. Additionally, digital twins can serve as synthetic controls in clinical trials, enhancing the interpretation of single-arm studies when novel agents are combined with standard-of-care treatments.
