According to an expert, the first results of the study show that an artificial intelligence model can help oncologists better stratify prostate cancer patients into risk groups than existing methods.
According to an expert, a multimodal artificial intelligence model may have the ability to accurately stratify patients with prostate cancer into risk subgroups.
During the American Society for Radiation Oncology (ASTRO) 2022 Annual Meeting, Cancer Network® spoke with Louis Potters, MD, FACR, FABS, FASTRO, about the potential benefits of artificial intelligence.
Potters, who is chairman of the Department of Radiation Medicine and deputy chief medical officer at Northwell Health Cancer Institute in New Hyde Park, New York, said further development of this prognostic tool could be useful in more accurately identifying patients who are suitable for enrollment in future clinical trials.
Transcription:
The theme of the ASTRO meeting was really to explore the idea of artificial intelligence and neural networks in the use of data. During the plenary session, a very good study was presented on prostate cancer and looked at the risk stratification based on approximately 5600 patients enrolled in the NRG group cooperative studies, creating a kind of risk stratification multimodal to identify statistical differences and results. . This is now partnered with a third-party software vendor who will be looking to create this prognostic tool, which will help stratify patients better than the typical risk stratification that has been used in the past for prostate cancer. This will be useful in identifying patients who will be enrolled in clinical trials.
What’s also interesting is that the number of patients who would otherwise be stratified between intermediate-risk and high-risk diseases, and the number who actually fall into a more favorable category somewhere between intermediate-risk and high, is actually higher than what you would think we’re seeing with high-risk patients right now. We probably over-stratify high-risk patients today. It will be interesting to see the validity of this data. [in the] in the long term and what the prognosis tool will be able to bring us in the clinic and for the recruitment of patients in clinical trials.
Reference
Tward JD, Zhang J, Esteva A, et al. Prostate Cancer Risk Stratification in NRG Oncology Phase III Randomized Trials Using Multimodal Deep Learning with Digital Histopathology. Presented at the 2022 American Society for Radiation Oncology (ASTRO) Annual Meeting; October 23-26, 2022; San Antonio, Texas. Abstract 2. Accessed November 7, 2022.