Digital Twins Accurately Predict Cancer Treatment Effectiveness in Virtual Trials
Key Insights
Digital twins, created from biological data of thousands of cancer (search) patients, accurately predicted outcomes in simulated clinical trials, offering a potential tool for virtual drug testing.
FarrSight-Twin (search), a platform utilizing digital twins, demonstrated a 75% response rate when patients received the treatment it predicted as optimal, compared to 53.5% with alternative treatments.
The technology is being developed to predict individual patient responses to chemotherapy, potentially aiding clinicians in selecting the most effective treatments.
Digital twins, representations of individual cancer (search) patients created from extensive biological data, have shown promising results in predicting the effectiveness of cancer treatments in virtual clinical trials. This approach, presented at the 36th EORTC-NCI-AACR Symposium on Molecular Targets and Cancer Therapeutics, could revolutionize cancer research by enabling virtual drug testing and personalized treatment selection.
Simulating Clinical Trials with Digital Twins
Dr. Uzma Asghar, co-founder and chief scientific officer at Concr (search), highlighted the potential of this technology to reduce the cost and improve the success rate of cancer (search) drug development. "We can use digital twins to represent individual patients, build clinical trial cohorts and compare treatments to see if they are likely to be successful before testing them out with real patients," she stated.
Each digital twin is constructed using biological data from thousands of cancer (search) patients treated with various methods. This data is then used to recreate a real patient's cancer, incorporating molecular data from their tumor. This allows researchers to predict how a patient is likely to respond to a specific treatment.
FarrSight-Twin's Predictive Accuracy
Dr. Asghar and her team used FarrSight-Twin (search) to recreate published Phase II and III clinical trials involving patients with breast, pancreatic, or ovarian cancer (search). These trials compared different drug therapies, including anthracyclines (search), taxanes (search), platinum-based drugs (search), capecitabine, and hormone treatments. The digital trials accurately predicted the outcomes of the actual clinical trials across all simulated studies.
Further analysis revealed that patients who received the treatment predicted by FarrSight-Twin (search) to be the most effective experienced a 75% response rate, compared to a 53.5% response rate in patients who received a different treatment. This suggests that digital twins could significantly improve treatment outcomes by guiding treatment decisions.
Ongoing Development and Future Applications
"We are excited to apply this type of technology by simulating clinical trials across different tumour types to predict patients' response to different chemotherapies and the results are encouraging," said Dr. Asghar. The technology is currently being developed to predict treatment response for individual patients in the clinic, helping doctors determine which chemotherapy regimens will be most beneficial.
Concr (search), The Institute of Cancer (search) Research, Durham University, and the Royal Marsden Hospital are collaborating on an observational trial to assess the technology's ability to predict treatment response in patients with triple-negative breast cancer (search). This research could pave the way for personalized cancer treatment strategies, improving patient outcomes and reducing the burden of ineffective therapies.