Home Medizin Von SOPHiA GENETICS und UroCCR entwickeltes KI-Modell sagt postoperative Ergebnisse in Nierenkrebsstudie voraus

Von SOPHiA GENETICS und UroCCR entwickeltes KI-Modell sagt postoperative Ergebnisse in Nierenkrebsstudie voraus

von NFI Redaktion

SOPHiA GENETICS (Nasdaq: SOPH), a cloud-native software company leading in data-driven medicine, collaborated with the French Kidney Cancer Research Network (UroCCR) on a study using a multimodal algorithm to predict postoperative outcomes in patients with renal cell carcinoma (RCC). The results were recently published in npj Precision Oncology. The study showed that the artificial intelligence (AI) model developed jointly by SOPHiA GENETICS and UroCCR delivered strong predictions for postoperative outcomes compared to standard prognostic values. This publication follows a previous collaboration demonstrating the value of multimodal analysis for upstaging preoperative kidney cancer.

UroCCR is one of the largest collaborative networks for kidney cancer worldwide, with 51 multidisciplinary clinical teams across France. Working closely with the French Association of Urology (AFU), UroCCR aims to connect a national, multidisciplinary network of medical and scientific professionals focusing on therapeutic management and applied research in kidney cancer. In 2021, UroCCR partnered with SOPHiA GENETICS to develop an AI-based model to predict the progression of kidney cancer after surgery from a localized tumor.

The UroCCR database provided real-world multi-modal data, including radiological, clinical, and biological data from over 3,300 patients operated on across France between May 2000 and January 2020. Researchers used SOPHiA GENETICS‘ proprietary AI offering to transform the data into easily visualized, reliable predictions that outperformed common risk assessments.

The quantity and complexity of available health data continues to grow, and while this can be useful for personalized diagnosis and treatment, it is most effective when combined with AI. Our collaboration with UroCCR over the past three years has significantly advanced RCC research and demonstrated the power of AI in extracting insights from real-world multimodal data. We are extremely pleased with the results of this study and look forward to further collaboration with UroCCR.

Thierry Colin, Vice President, 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 advance the use of precision medicine. The study by UroCCR and SOPHiA GENETICS illustrates how an AI-based predictive model has the potential to support clinical treatment decision-making and provide clues on which patients may benefit from adjuvant systemic therapy compared to those who may endure surveillance.

“Our research at UroCCR focuses on the idea that a shared database helps facilitate and expand the use of precision medicine for patients with kidney cancer,” said Prof. Jean-Christophe Bernhard, MD, PhD., Urologic Surgeon at CHU Bordeaux and Head of UroCCR. “Our work with SOPHiA GENETICS and the results of our latest study have shown the benefits of using AI to analyze real-world multimodal data. SOPHiA GENETICS‘ technology and network have been key to the success of our research and will be crucial as we progress with increasing data inputs.“

UroCCR was founded in 2011 and funded by the French National Cancer Institute (INCa), being recognized as one of the fourteen official nationwide clinical and biological databases (BCB). The network enables the identification and documentation of clinical, biological, and radiological data of all newly diagnosed patients in participating centers in a shared database. The network was designated by the High Authority on Health (HAS) in 2023 as an interesting provider of real-world data. For more information, visit X and LinkedIn.

The SOPHiA DDM™ platform, due to its cloud-based, AI-driven environment that integrates and standardizes various data modalities, is capable of analyzing multimodal data to advance the development of predictive models to address research questions.


Journal Reference:

Margue, G., et al. (2024). UroPredict: Machine learning model on real data to predict relapse of kidney cancer (UroCCR-120). npj Precision Oncology. doi.org/10.1038/s41698-024-00532-x.

Related Posts

Adblock Detected

Please support us by disabling your AdBlocker extension from your browsers for our website.