Using Electronic Health Record Data to Identify Prostate Cancer Patients That May Qualify for Active Surveillance

Dhavileswarapu AVL, Naik N, Karimi H, Hegde P, Rai BP, Somani BK. Big Data Analytics in urology: the story so far and the road ahead

Artificial intelligence (AI) has a proven record of application in the field of medicine and is used in various urological conditions such as oncology, urolithiasis, paediatric urology, urogynaecology, infertility and reconstruction. Data is the driving force of AI and the past decades have undoubtedly witnessed an upsurge in healthcare data. Urology is a specialty that has always been at the forefront of innovation and research and has rapidly embraced technologies to improve patient outcomes and experience. Advancements made in Big Data Analytics raised the expectations about the future of urology. This review aims to investigate the role of big data and its blend with AI for trends and use in urology. We explore the different sources of big data in urology and explicate their current and future applications. A positive trend has been exhibited by the advent and implementation of AI in urology with data available from several databases. The extensive use of big data for the diagnosis and treatment of urological disorders is still in its early stage and under validation. In future however, big data will no doubt play a major role in the management of urological conditions.

Health economic impact of a biopsy-based cell cycle gene expression assay in localized prostate cancer

Background: Prior studies have established that broader incorporation of active surveillance, guided by additional prognostic tools, may mitigate the growing economic burden of localized prostate cancer in the USA. This study sought to further explore the potential of a particular gene expression-based prognostic tool to address this unmet need. Materials & methods: A deterministic, decision-analytic model was developed to estimate the economic impact of the Prolaris^® test on a US commercial health plan. Results & conclusion: When adopted in patients classified by the American Urological Association as low or intermediate risk, the assay was projected to reduce costs by $1894 and $2129 per patient over 3 and 10 years, respectively, largely through the increased use of active surveillance.

Economic burden of illness associated with localized prostate cancer in the United States

Aim: Prior studies have established the economic burden of prostate cancer on society. However, changes to screening, novel therapies and increased use of active surveillance (AS) create a need for an updated analysis. Methods: A deterministic, decision-analytic model was developed to estimate medical costs associated with localized prostate cancer over 10 years. Results: 10-year costs averaged $45,957, $99,445 and $188,928 for low-, intermediate- and high-risk patients, respectively. For low-risk patients, AS 10-year costs averaged $33,912/patient, whereas definitive treatment averaged $49,667/patient. Despite higher failure rates in intermediate-risk patients, AS remained less costly than definitive treatment, with 10-year costs averaging $90,614/patient and $99,394/patient, respectively. Conclusion: Broader incorporation of AS, guided by additional prognostic tools, may mitigate this growing economic burden.

Active Surveillance Use Among a Low-risk Prostate Cancer Population in a Large US Payer System: 17-Gene Genomic Prostate Score Versus Other Risk Stratification Methods

Many men with low-risk prostate cancer (PCa) receive definitive treatment despite recommendations that have been informed by two large, randomized trials encouraging active surveillance (AS). We conducted a retrospective cohort study using the Optum™ Research Database (Eden Prairie, MN) of electronic health records and administrative claims data to assess AS use for patients tested with a 17-gene Genomic Prostate Score™ (GPS; Genomic Health, Redwood City, CA) assay and/or prostate magnetic resonance imaging (MRI). De-identified records were extracted on health plan members enrolled from June 2013 to June 2016 who had ≥1 record of PCa (n 5 291,876). Inclusion criteria included age ≥18 years, new diagnosis, American Urological Association low-risk PCa (stage T1-T2a, prostate-specific antigen ≤10 ng/mL, Gleason score 5 6), and clinical activity for at least 12 months before and after diagnosis. Data included baseline characteristics, use of GPS testing and/or MRI, and definitive procedures. GPS or MRI testing was performed in 17% of men (GPS, n 5 375, 4%; MRI, n 5 1174, 13%). AS use varied from a low of 43% for men who only underwent MRI to 89% for GPStested men who did not undergo MRI (P <.001). At 6-month follow-up, AS use was 31.0% higher (95% CI, 27.6%-34.5%; P <.001) for men receiving the GPS test only versus men who did not undergo GPS testing or MRI; the difference was 30.5% at 12-month follow-up. In a large US payer system, the GPS assay was associated with significantly higher AS use at 6 and 12 months compared with men who had MRI only, or no GPS or MRI testing.

Concordium 2015: Strategic Uses of Evidence to Transform Delivery Systems

In September 2015 the EDM Forum hosted AcademyHealth’s newest national conference, Concordium. The 11 papers featured in the eGEMs “Concordium 2015” special issue successfully reflect the major themes and issues discussed at the meeting. Many of the papers address informatics or methodological approaches to natural language processing (NLP) or text analysis, which is indicative of the importance of analyzing text data to gain insights into care coordination and patient-centered outcomes. Perspectives on the tools and infrastructure requirements that are needed to build learning health systems were also recurrent themes.