Analysis of Unstructured EHR Notes Could Inform Early-stage Prostate Cancer Research
Prostate cancer has one of the highest five-year relative survival rates (98%) according to aggregate stage data from the SEER (Surveillance, Epidemiology, and End Results) database.1 However, there is also clear evidence of overtreatment of prostate cancer patients. For example, a study based on data from the CAPSURE prostate cancer registry, found that 92% to 98% of patients with the lowest tumor risk scores (and presumably were eligible for a more conservative approach, such as active surveillance) were treated with prostatectomy, radiation, or hormone therapy.2
While often successful at eradicating the cancer, these treatments risk long-term side effects including skeletal disease, cardiovascular disease, loss of libido, erectile dysfunction, urinary incontinence, hot flashes, and more – all of which can negatively impact quality of life. As a result, we have seen urologists, oncologists, primary care physicians, and life science researchers take on the responsibility of enhancing their understanding of the underlying characteristics that influence prostate cancer progression and remission, enabling earlier detection and more precise, less intensive treatment or monitoring. Real-world evidence (RWE) has the potential to dramatically accelerate insights into precision medicine and improve outcomes.
Artificial Intelligence Enables Unprecedented Insight Into the Prostate Cancer Patient Journey
Although Prostate-Specific Antigen (PSA) levels and Gleason scores are primary measures used to identify disease severity and progression, this information is not present in claims data or other structured data sources. This vital clinical information is most frequently located in the unstructured data within the urologist’s electronic health record (EHR), stored as either part of the clinical narrative in physician notes or attached as a scanned or faxed document.
Successfully abstracting, aggregating, and analyzing this notes-based data across large cohorts of patients for the purpose of advancing disease management has historically been a challenge. However, Verana Health’s partnership with the American Urological Association (AUA,) combined with the use of clinician-guided artificial intelligence (AI) methods, are helping make the process easier.
AI approaches, such as machine learning (ML) and natural language processing (NLP), are applied to analyze data from EHRs participating in the AUA Quality Registry (AQUA)
AI approaches, such as machine learning (ML) and natural language processing (NLP), are applied to analyze data from EHRs participating in the AUA Quality Registry (AQUA). Physician-informed algorithms are applied to unstructured data at scale to help extract key information on PSA levels, Gleason scores, and other measures, which can then be analyzed across large populations in a reliable manner. This can give providers, researchers, and life science companies unprecedented insights into the journey of patients with prostate cancer.
For example, analysis of quality real-world data (RWD) can track patient PSA levels over time and help us better understand disease progression, therapeutic effectiveness, and the patient journey. Similarly, it can help researchers identify common characteristics among patients whose disease worsens over time.
RWD analysis can also help identify patients with localized cancer and evaluate treatment patterns and outcomes. Researchers can determine if patients are receiving treatments in line with AUA recommendations, based on disease severity. Additionally, they can track patient response to a prescribed therapy.
RWE has the potential to help support and advance prostate cancer research and subsequent care in several ways, including:
- Early detection and intervention – RWD analysis could help identify urinary biomarkers and pathology indicators that enable earlier disease detection and better risk stratification. Disease progression patterns could also inform earlier intervention for those with high-risk forms of the cancer, helping reduce mortality.
- Treatment path validation – Data trends could be analyzed to verify that prescribed treatment plans or active surveillance are appropriate and effective in managing the disease. For example, PSA scores could be tracked throughout a course of treatment to help determine therapeutic efficacy. This data could help inform research that has the potential to modify future standards of care for the newly diagnosed, helping to improve patient outcomes.
- Clinical trial recruitment – RWE has the power to deliver insights that could help accelerate and improve prostate cancer trials by identifying urology practices treating patients with specific early-stage prostate cancer profiles. This could help advance the application of investigational therapies to patients while reducing the time and resources necessary to secure optimal trial sites.
About Real-World Data from the American Urological Association’s AQUA Registry
Verana Health has partnered with the American Urological Association to curate and analyze data from the AQUA Registry real-world data network. The registry has more than 2,100 urologists who contribute their EHR data. In total, it contains data from more than 8 years of longitudinal patient records, including more than 75 million patient encounters from more than 9.7 million de-identified patients.
Verana Health takes the structured and unstructured AQUA Registry data a step further to inform research, transforming it—through the VeraQ™ population health data engine—into high-quality, real-world data modules, known as Qdata™.
Qdata Early-stage Prostate Cancer is the first Urology Qdata module and will be formally announced at the AUA 2022 Annual Meeting May 13-16. This is an exciting development for urologists, researchers, and our patients.
For more information about Qdata Early-stage Prostate Cancer, or to schedule a meeting with Verana Health at the AUA 2022 Annual Meeting, click here.
- Survival rates for prostate cancer – American Cancer Society
- Overdiagnosis and Overtreatment of Prostate Cancer – Ian M. Thompson, Jr. MD – American Association of Clinical Oncology Education Book
- Improving diversity in medical research – Ashwarya Sharma & Latha Palaniappan – Nature Reviews Disease Primers – 14 October 2021
- Why do African American men face higher risks for lethal prostate cancer? – Sujit S. Nair, Dimple Chakravarty, Zachary S. Dovey, Xiangfu Zhang, K. Ashutosh – Current Opinion in Urology – January 2022