Advancing Precision Oncology with Artificial Intelligence: Ushering in the ArteraAI Prostate Test

Due to the negative effects of excessive and inadequate treatment, prostate cancer (PCa) represents the most common cause of cancer-related disability and the leading cause of cancer-related mortality in men. 1 Carroll P.H. Mohler J.L. NCCN guidelines updates: prostate cancer and prostate cancer early detection. Journal of the National Comprehensive Cancer Network. 2018; 16: 620-623https://doi.org/10.6004/jnccn.2018.0036 Crossref PubMed Scopus (227) Google Scholar , 2 Ward E.M. Sherman R.L. Henley S.J. et al. Annual report to the nation on the status of cancer, featuring cancer in men and women age 20–49 years. JNCI: Journal of the National Cancer Institute. 2019; 111: 1279-1297https://doi.org/10.1093/jnci/djz106 Crossref PubMed Scopus (0) Google Scholar As such designing treatment regimens for PCa patients is complex. Optimal therapy involves assessing overall health, specific characteristics of their cancer, side effects of treatments, future disease progression, as well as data from clinical trials involving patients with similar diseases. 3 Esteva A. Feng J. van der Wal D. et al. Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials. NPJ Digital Medicine. 2022; 5: 71https://doi.org/10.1038/s41746-022-00613-w Crossref PubMed Scopus (29) Google Scholar Historically, clinicians have relied on conventional prognostic tools in the management of PCa. These prognostic tools help clinicians identify which patients are at risk of developing disease recurrence or distant metastasis. For example, the National Comprehensive Cancer Network (NCCN) is one of the most commonly used systems to risk-stratify patients worldwide. 3 Esteva A. Feng J. van der Wal D. et al. Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials. NPJ Digital Medicine. 2022; 5: 71https://doi.org/10.1038/s41746-022-00613-w Crossref PubMed Scopus (29) Google Scholar This system includes age, PSA, Gleason score, and TNM staging. The Gleason score is commonly recognized as the strongest predictor of PCa prognosis. 4 Chu T.N. Wong E.Y. Ma R. et al. Exploring the Use of Artificial Intelligence in the Management of Prostate Cancer. Current Urology Reports. 2023; 24: 231-240https://doi.org/10.1007/s11934-023-01149-6 Crossref Scopus (5) Google Scholar Importantly this system has been used for years now without substantial improvements. Studies have shown that these factors have suboptimal prognostic and discriminatory performance likely due to their subjective and non-specific nature. 3 Esteva A. Feng J. van der Wal D. et al. Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials. NPJ Digital Medicine. 2022; 5: 71https://doi.org/10.1038/s41746-022-00613-w Crossref PubMed Scopus (29) Google Scholar , 5 Daskivich T.J. Wood L.N. Skarecky D. et al. Limitations of the National Comprehensive Cancer Network®(NCCN®) guidelines for prediction of limited life expectancy in men with prostate cancer. The Journal of Urology. 2017; 197: 356-362https://doi.org/10.1016/j.juro.2016.08.096 Crossref PubMed Scopus (9) Google Scholar Tissue based genomic markers have shown great promise as superior prognostic models over the last several years, however, nearly all of these lack validation in large, randomized clinical trials. 3 Esteva A. Feng J. van der Wal D. et al. Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials. NPJ Digital Medicine. 2022; 5: 71https://doi.org/10.1038/s41746-022-00613-w Crossref PubMed Scopus (29) Google Scholar , 6 Kornberg Z. Cooperberg M.R. Spratt D.E. Feng F.Y. Genomic biomarkers in prostate cancer. Translational andrology and urology. 2018; 7: 459https://doi.org/10.21037/tau.2018.06.02 Crossref Scopus (34) Google Scholar