(UroToday.com) The 2022 IKCS North American annual meeting featured a presentation by Dr. Hesham Yasin discussing artificial intelligence modeling to predict the risk of cardiotoxicity among renal cell carcinoma (RCC) patients treated with vascular endothelial growth factor receptors tyrosine kinase inhibitors (VEGFRi). VEGFRi are standards of care in RCC, but despite efficacy and safety, there is a risk for cardiotoxicity with an estimated incidence between 3-8%.
Importantly, cardiotoxicity can occur months or years after treatment and can be life-threatening. Historically, an oncologist refers patients to a cardiologist when cardiotoxicity is suspected/observed. However, general cardiologists may be unfamiliar with VEGFRi cardiotoxicity. Cardio-oncology, an emerging subspecialty, aims to prevent and/or treat cardiovascular complications among cancer patients/survivors, and great progress has been made in utilizing this subspecialty, but standardized referral workflow is limited. Machine learning is a discipline of artificial intelligence and computer science that utilizes algorithms to find patterns in data and help create models to predict future events. Using artificial intelligence may help identify patients who face risk of cardiotoxicity to promote referral to cardio-oncology in a timely manner.
For this study, de-identified data on RCC patients were obtained from the Vanderbilt University Medical Center electronic medical record. VEGFRi’s included in this study were as follows: sunitinib, sorafenib, bevacizumab, axitinib, cabozantinib, pazopanib, tivozanib, lenvatinib, regorafenib, and vandetanib. Random forest and artificial neural network machine learning models were applied to analyze the cohort. A global team of cardio-oncologists devised cardiotoxicity risk factors used in calculating the risk groups (potential/mild/moderate/major):
There were 2,047 RCC records analyzed. Data were randomly divided into training (80%) and validation (20%) sets. Random forest and artificial neural network, applied to analyze patient records extracted to specifications outlined in the clinical risk model, performed > 95% for accuracy and at >94% precision. Limited validation showed 58% of the RCC patients treated with VEGFRi with major risk for cardiotoxicity, were not referred to cardio-oncology.
Dr. Yasin concluded his presentation by discussing artificial intelligence modeling to predict the risk of cardiotoxicity among RCC patients treated with VEGFRi with the following concluding statements:
- Artificial intelligence models accurately predict RCC patients with cardiotoxicity risk
- Integration of artificial intelligence models into the electronic medical record can assist oncologists with identifying these patients and referring them for proactive cardio-oncology treatment/monitoring
- A pilot project is underway to integrate model predictions in Epic workflow as a report of patients who should be referred to cardio-oncology for monitoring and/or tailored treatments
- Further studies comparing differences in outcomes between high-risk group patients who were referred to cardio-oncology versus patients who were not referred are warranted
Presented by: Hesham Yasin, MD, Vanderbilt University Medical Center, Nashville, TN
Written by: Zachary Klaassen, MD, MSc – Urologic Oncologist, Assistant Professor of Urology, Georgia Cancer Center, Augusta University/Medical College of Georgia, @zklaassen_md on Twitter during the 2022 International Kidney Cancer Symposium (IKCS) North America, November 4-5, Austin, Texas, USA