Abstract
Background: Clinical registries provide physicians with a means for making data-driven decisions but few opportunities exist for patients to interact with registry data to help make decisions. Objective: We sought to develop a web-based system that uses a prostate cancer (CaP) registry to provide newly diagnosed men with a platform to view predicted treatment decisions based on patients with similar characteristics. Design, setting, and participants: The Michigan Urological Surgery Improvement Collaborative (MUSIC) is a quality improvement consortium of urology practices that maintains a prospective registry of men with CaP. We used registry data from 45 MUSIC urology practices from 2015 to 2017 to develop and validate a random forest machine learning model. After fitting the random forest model to a derivation cohort consisting of a random two-thirds sample of patients after stratifying by practice location, we evaluated the model performance in a validation cohort consisting of the remaining one-third of patients using a multiclass area under the curve (AUC) measure and calibration plots. Results and limitations: We identified 7543 men diagnosed with CaP, of whom 45% underwent radical prostatectomy, 30% surveillance, 17% radiation therapy, 5.6% androgen deprivation, and 1.8% watchful waiting. The personalized prediction for patients in the validation cohort was highly accurate (AUC 0.81). Conclusions: Using clinical registry data and machine learning methods, we created a web-based platform for patients that generates accurate predictions for most CaP treatments. Patient summary: We have developed and tested a tool to help men newly diagnosed with prostate cancer to view predicted treatment decisions based on similar patients from our registry. We have made this tool available online for patients to use.
Original language | English (US) |
---|---|
Pages (from-to) | 901-907 |
Number of pages | 7 |
Journal | European urology |
Volume | 75 |
Issue number | 6 |
DOIs | |
State | Published - Jun 2019 |
Funding
Financial disclosures: Karandeep Singh certifies that all conflicts of interest, including specific financial interests and relationships and affiliations relevant to the subject matter or materials discussed in the manuscript (eg, employment/affiliation, grants or funding, consultancies, honoraria, stock ownership or options, expert testimony, royalties, or patents filed, received, or pending), are the following: Gregory B. Auffenberg has received funding from the National Cancer Institute (grant 1T32-CA180984). Khurshid R. Ghani has received contract support from Blue Cross Blue Shield of Michigan for serving as the co-director of the Michigan Urological Surgery Improvement Collaborative and serving as a consultant for Boston Scientific Corporation and Lumenis. Shreyas Ramani and Etiowo Usoro have received salary support from an MCubed grant from the University of Michigan. David C. Miller has received contract support from Blue Cross Blue Shield of Michigan for serving as the director of the Michigan Urological Surgery Improvement Collaborative. Karandeep Singh has received grant support from the National Institute of Diabetes and Digestive and Kidney Diseases (grant 5K12DK111011). The remaining authors have nothing to disclose. Funding/Support and role of the sponsor : This work was supported by Blue Cross Blue Shield of Michigan. The sponsor played no direct role in the study.
Keywords
- Machine learning
- Patient education
- Prostate cancer
ASJC Scopus subject areas
- Urology