'Digital twins' to predict cancer treatment outcomes

International researchers have used ‘digital twins’ of real cancer patients to recreate clinical trials of new treatments. The approach uses a technology called FarrSight-Twin to run virtual clinical trials before testing new treatments on patients.

The approach could be used alongside clinical trials with a digital twin for each patient taking part, which together could form a control group for any trial. Ultimately, it might mean that patients could have different treatments tested on their digital twin to help select the most suitable treatment ahead of time. The research was presented by Dr Uzma Asghar, co-founder and Chief Scientific Officer at Concr and a consultant medical oncologist, at the 36th EORTC-NCI-AACR Symposium on Molecular Targets and Cancer Therapeutics in Barcelona.

“Around the world, we spend billions of dollars on developing new cancer treatments. Some will turn out to be successful, but most will not,” said Asghar, who currently works at The Royal Marsden NHS Foundation Trust, London.

“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.”

Each digital twin is created from biological data from thousands of patients with cancer who have been treated in different ways. This information is combined to recreate the cancer of a real patient with molecular data on their tumour. This digital twin makes it possible to predict how a patient is likely to respond to a treatment.

Asghar and her colleagues used this approach to recreate published clinical trials with a digital twin representing each real patient who took part in the trial.

Overall, the digital trials accurately predicted the outcome of the actual clinical trials in all simulated clinical studies. Further testing showed that where patients received the treatment predicted by FarrSight-Twin to be best, they had a 75% response rate, compared to 53.5% response where patients received a different treatment. ‘Response rate’ means the proportion of patients whose tumours shrank following treatment.

The trials used in the study were in patients with either breast, pancreatic or ovarian cancer. They were phase II or III trials that compared two different drug therapies, including anthracyclines, taxanes, platinum-based drugs, capecitabine and hormone treatments.

The researchers are currently developing this technology so that it can predict treatment response for individual patients in the clinic and help doctors understand which chemotherapy will or will not be helpful, and this work is ongoing.

Asghar and her colleagues are testing the technology to see if it could help predict which available treatments will work best for patients with triple-negative breast cancer, in an observational collaborative trial between Concr, The Institute of Cancer Research, Durham University and The Royal Marsden Hospital.

Professor Timothy A Yap, from the University of Texas MD Anderson Cancer Center, is Co-Chair of the EORTC-NCI-AACR Symposium and was not involved in the research.

“Despite major improvements in cancer treatment, there are still many types of cancer where treatment options are limited,” Yap said. “Designing and testing new cancer treatments is challenging, time-consuming and costly. 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.”

Image credit: iStock.com/Ridofranz