NEW YORK – Biotech firm Concr on Wednesday said it began an observational clinical trial using its artificial intelligence-based FarrSight platform to identify biomarkers of treatment response in patients with triple-negative breast cancer.
The trial, dubbed VISION, will be conducted at sites in the UK and Australia, with the Royal Marsden NHS Foundation Trust hospital serving as the primary trial site. London-based Concr received a grant from Innovate UK Precision Medicine to support the VISION study earlier this year, and the firm has also partnered with the Institute of Cancer Research, London, and the Institute for Computational Cosmology at Durham University on the trial.
The VISION trial will enroll 200 TNBC patients and retrospectively analyze their clinical, genomic, and whole-slide imaging data. Researchers will collect tissue samples and perform DNA, RNA, and other next-generation sequencing on them. Patients in the trial will be stratified into two arms based on whether they received neoadjuvant chemotherapy with or without immunotherapy and had a complete pathological response or whether they had residual cancer after neoadjuvant treatment.
Concr will use its FarrSight-Twin technology to create a "digital twin" for each TNBC patient enrolled in the study using their genomic data from diagnostic and surgical breast cancer samples together with whole-slide imaging and clinical data. The "twin" will be used to predict which chemotherapy and immunotherapy treatments each patient is most likely to respond to. Concr will also use the FarrSight platform in the study to explore the biological mechanisms driving patients' sensitivity to chemotherapy with or without immunotherapy.
"Triple-negative breast cancer is an aggressive subtype of breast cancer," Uzma Asghar, Concr CSO and VISION project lead, said in a statement. "Hence, Concr has prioritized this clinical indication as a key research area by sponsoring the VISION study. The VISION study will test the value created through the combination of clinical data, genomic data, and machine learning approaches for enabling treatment stratification at an individual level."