New Phesi proof of concept demonstrates potential of AI-powered digital twins to replace external control arms in clinical trials

Study published in Bone Marrow Transplantation uses real-world clinical data to create virtual digital twin cohorts instead of placebo and standard-of-care comparator arms

Boston, USA, 20 June, 2024: Phesi, a leading clinical development analytics company, has today published new research in the journal Bone Marrow Transplantation (BMT-Nature). The study demonstrates that AI-powered digital twin solutions can potentially replace the standard-of-care (SOC) control arm of a clinical trial, and is co-authored by Dr Yi-Bin Chen, Director for the Blood and Marrow Transplant Program at Massachusetts General Hospital. 

Phesi created a digital twin for cGvHD (chronic graft versus host disease) in the primary treatment setting; cGvHD is a serious complication of allogeneic hematopoietic cell transplantation (HCT). The digital twin was developed to replicate patients receiving prednisone, the first-line treatment currently used as the standard-of-care for cGvHD, and commonly used in control arms of prospective clinical trials. Phesi constructed the cGvHD digital twin informed by real-world data from its Trial Accelerator™ platform. The platform contains data from more than 108 million patients in almost 367,000 cohorts; 2,042 patients (32 cohorts) with cGvHD were selected and used to construct the (first-line therapy) flGvHD digital twin cohort and 438 patients from 8 cohorts were used to construct the flGvHD digital twin standard-of-care cohort.  

“Digital twins can support the industry to overcome longstanding challenges faced in patient recruitment, the ethical issues associated with placebo arms, and the impact these constraints have on cycle and approval times,” said Dr Gen Li, President, Phesi. “We have demonstrated that digital twins offer real potential to replace standard-of-care comparator arms to streamline the implementation of clinical trials and dramatically reduce patient burden. This study shows the use of digital twins for clinical trials could benefit many other disease indications as well as cGvHD. Our hope is this approach will gain regulatory approval in the future and find its place in the design and implementation of clinical trials. We look forward to working with regulatory bodies such as the FDA to explore the use of digital twin solutions in clinical development.” 

More than 50,000 cancer patients receive HCT each year worldwide; cGvHD occurs in 30-50% of these patients as a complication that can significantly impair long-term quality of life. Corticosteroids are the front-line treatment for this condition, but the long-term effects of corticosteroids combined with the chronic nature of cGvHD has highlighted the urgent need for alternative treatments.

“With a significant number of patients continuing to suffer from cGvHD in a given year, recruiting patients for clinical trials into this condition is challenging. When half of trial participants must be assigned to a control arm, clinical trial accrual is oftentimes difficult,” explained Dr Yi-Bin Chen, co-author and Director for the Blood and Marrow Transplant Program at Massachusetts General Hospital. “This digital twin would allow clinical researchers to accelerate clinical trials into this challenging condition by automating an external control arm and allowing sponsors to test new therapies faster. I am delighted to have collaborated with the Phesi team to demonstrate the feasibility of using digital twins in cGvHD trials to accelerate research and reduce patient burden.”  

The Phesi Digital Twin solution aims to replace control arms in clinical trials; Phesi’s Trial Accelerator platform yields additional significant incremental benefits for trial sponsors in several areas. Phesi’s Digital Patient Profiles (DPP) optimize trial and protocol design, and enable sponsors to generate a Patient Access Score (PAS) to identify leading investigator sites with highest enrollment potential. The DPP and PAS empower patient-centered analysis and serve as the precursor to digital twin implementation. The integrated and contextualized analysis addresses the three evergreen challenges in clinical development –  to reduce protocol amendments, identify the best enrolling investigator sites, and reduce patient burden.

The full study is published in Bone Marrow Transplantation: https://www.nature.com/articles/s41409-024-02324-0.

The cGvHD digital twin is the latest in Phesi’s series of published digital twins for clinical development. These include a digital twin for non-small cell lung cancer (NSCLC) KRAS G12C patients, and a digital twin for CAR-T Cytokine Release Syndrome (CRS) patients.

To access the full Phesi Digital Patient Profile Catalog, visit: https://info.phesi.com/dpp. 

For more information on Phesi’s Digital Twins, visit https://info.phesi.com/digital-twins-ebook.