Prostate cancer risk estimation tool use by members of the American Urological Association: a survey based study

Machine learning applications in radiation oncology

Machine learning technology has a growing impact on radiation oncology with an increasing presence in research and industry. The prevalence of diverse data including 3D imaging and the 3D radiation dose delivery presents potential for future automation and scope for treatment improvements for cancer patients. Harnessing this potential requires standardization of tools and data, and focused collaboration between fields of expertise. The rapid advancement of radiation oncology treatment technologies presents opportunities for machine learning integration with investments targeted towards data quality, data extraction, software, and engagement with clinical expertise. In this review, we provide an overview of machine learning concepts before reviewing advances in applying machine learning to radiation oncology and integrating these techniques into the radiation oncology workflows. Several key areas are outlined in the radiation oncology workflow where machine learning has been applied and where it can have a significant impact in terms of efficiency, consistency in treatment and overall treatment outcomes. This review highlights that machine learning has key early applications in radiation oncology due to the repetitive nature of many tasks that also currently have human review. Standardized data management of routinely collected imaging and radiation dose data are also highlighted as enabling engagement in research utilizing machine learning and the ability integrate these technologies into clinical workflow to benefit patients. Physicists need to be part of the conversation to facilitate this technical integration.

A national survey of radiation oncologists and urologists on prediction tools and nomograms for localized prostate cancer

PURPOSE

Although prediction tools for prostate cancer (PCa) are essential for high-quality treatment decision-making, little is known about the degree of confidence in existing tools and whether they are used in clinical practice from radiation oncologists (RO) and urologists (URO). Herein, we performed a national survey of specialists about perceived attitudes and use of prediction tools.

METHODS

In 2017, we invited 940 URO and 911 RO in a national survey to query their confidence in and use of the D'Amico criteria, Kattan Nomogram, and CAPRA score. The statistical analysis involved bivariate association and multivariable logistic regression analyses to identify physician characteristics (age, gender, race, practice affiliation, specialty, access to robotic surgery, ownership of linear accelerator and number of prostate cancer per week) associated with survey responses and use of active surveillance (AS) for low-risk PCa.

RESULTS

Overall, 691 (37.3%) specialists completed the surveys. Two-thirds (range 65.6-68.4%) of respondents reported being "somewhat confident", but only a fifth selected "very confident" for each prediction tool (18.0-20.1%). 19.1% of specialists in the survey reported not using any prediction tools in clinical practice, which was higher amongst URO than RO (23.9 vs. 13.4%; p < 0.001). Respondents who reported not using prediction tools were also associated with low utilization of AS in their low-risk PCa patients (adjusted OR 2.47; p = 0.01).

CONCLUSIONS

While a majority of RO and URO view existing prediction tools for localized PCa with some degree of confidence, a fifth of specialists reported not using any such tools in clinical practice. Lack of using such tools was associated with low utilization of AS for low-risk PCa.

Current beliefs and practice patterns among urologists regarding prostate magnetic resonance imaging and magnetic resonance-targeted biopsy

INTRODUCTION AND OBJECTIVE

Multiparametric magnetic resonance imaging (MRI) and magnetic resonance (MR) -targeted biopsy have a growing role in the screening and evaluation of prostate cancer. We aim to evaluate the current knowledge, attitude, and practice patterns of urologists regarding this new technique.

METHODS

An anonymous online questionnaire was designed to collect information on urologists' beliefs and use of prostate multiparametric MRI and MR-targeted biopsy. The survey was sent to members of the Society of Urologic Oncology, the Endourological Society, and European Association of Urology. Multivariate logistic regression analysis was performed to determine predictors for use of prostate MRI and MR-targeted biopsy.

RESULTS

A total of 302 responses were received (Endourological Society: 175, European Association of Urology: 23, and Society of Urologic Oncology: 104). Most respondents (83.6%) believe MR-targeted biopsy to be moderately to extremely beneficial in the evaluation of prostate cancer. Overall, 85.7% of responders use prostate MRI in their practice, and 63.0% use MR-targeted biopsy. The 2 most common settings for use of MR-targeted biopsy include patients with history of prior negative biopsy result (96.3%) and monitoring patients on active surveillance (72.5%). In those who do not use MR-targeted biopsy, the principal reasons were lack of necessary infrastructure (64.1%) and prohibitive costs (48.1%). On multivariate logistic regression analysis, practice in an academic setting (1.86 [1.02-3.40], P = 0.043) and performing greater than 25 radical prostatectomies per year (2.32 [1.18-4.56], P = 0.015) remained independent predictors for using MR-targeted biopsy.

CONCLUSIONS

Most respondents of our survey look favorably on use of prostate MRI and MR-targeted biopsy in clinical practice. Over time, reduction in fixed costs and easier access to equipment may lead to further dissemination of this novel and potentially transformative technology.