SophiA GENETICS (Nasdaq: SOPH), a cloud-native software company and leader in data-driven medicine, and the French Kidney Cancer Research Network (UroCCR) have collaborated on a study that uses a multimodal algorithm to help predict postoperative results for those treating renal cell carcinoma (RCC), with results recently published in npj Precision Oncology. Study findings showed that the artificial intelligence (AI) model co-constructed by SOPhia GENETICS and UroCCR provided strong prediction of postoperative outcomes compared to conventional prognostic scores. This publication follows a previous collaboration that demonstrated the value of multimodality analysis in the preoperative staging of renal cancer.
UroCCR is one of the largest renal cancer collaborative networks in the world with 51 multidisciplinary clinical groups across France. In close relationship with the French Union of Urology (AFU), the goal of UroCCR is to connect a national, multidisciplinary network of physicians and scientific professionals focused on therapeutic management and applied research in kidney cancer. In 2021, UroCCR collaborated with SOPhia GENETICS to develop an AI-based model to predict whether kidney cancer will develop from a localized tumor after surgery.
The UroCCR database provided multimodal real-world data, including radiological, clinical and biological data from more than 3,300 patients across France operated between May 2000 and January 2020. The researchers applied SOPhiA GENETICS’ proprietary artificial intelligence that offers the analysis of of data into easily visualized. reliable predictions measured against and outperforming the most common risk scores.
The volume and complexity of available health data continues to grow, and while this can aid in personalized diagnosis and treatment, it is most effective when combined with AI. Our work with UroCCR over the past three years has significantly advanced its RCC research and demonstrated the power of AI to provide insights from multimodal real-world data. We are extremely pleased with the findings of this study and look forward to continuing our collaboration with UroCCR.”
Thierry Colin, VP, Multimodal Research and Development, SOPhia GENETICS
SOPhia GENETICS’ technology and global decentralized network are designed to break down data silos and empower researchers with data-driven insights to drive the use of precision medicine. The UroCCR and SOPhia GENETICS study shows that an AI-based predictive model has the potential to support clinical treatment decision-making and provide an indication of which patients can potentially benefit from adjuvant systemic therapy versus those who may not. to be kept under surveillance.
“At UroCCR, our research is focused on the idea that a shared database helps facilitate and expand the use of precision medicine for patients facing kidney cancer,” said President Jean-Christophe Bernhard, MD, PhD., Urological Surgeon at CHU Bordeaux and head. of UroCCR. “Our work with SOPhia GENETICS and the results of our latest study demonstrated the benefits of using AI to analyze real-world multimodal data. SophieA GENETICS’ technology and network have been key to the success of our research and will be imperative as we continue to progress with increased data inputs.”
UroCCR was created in 2011 and funded and labeled by the French National Cancer Institute (INCa) as one of the fourteen official national clinical and biological databases (BCB). The network makes it possible to identify and document clinical, biological and radiological data – in a common database – for all newly diagnosed patients at participating centers. The network has been cited in 2023 by the High Authority for Health (HAS) as a provider of real data of interest. For more information connect to X and LinkedIn.
The SOPhiA DDM™ platform has the ability to analyze multimodal data due to its cloud-based AI-based environment that integrates and standardizes a variety of data methods to fuel the development of predictive models capable of answering research questions.
Source:
Journal Reference:
Margue, G., et al. (2024). UroPredict: Machine learning model on real-world data to predict kidney cancer recurrence (UroCCR-120). npj Precision Oncology. doi.org/10.1038/s41698-024-00532-x.
