Asset Details
Do you wish to reserve the book?
Predicting intermediate-risk prostate cancer using machine learning
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
Predicting intermediate-risk prostate cancer using machine learning
Do you wish to request the book?
Predicting intermediate-risk prostate cancer using machine learning
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
Predicting intermediate-risk prostate cancer using machine learning
2025
Overview
Purposes
Intermediate-risk prostate cancer (IR PCa) is the most common risk group for localized prostate cancer. This study aimed to develop a machine learning (ML) model that utilizes biopsy predictors to estimate the probability of IR PCa and assess its performance compared to the traditional clinical model.
Methods
Between January 2017 and December 2022, patients with prostate-specific antigen (PSA) values of ≤ 20 ng/mL underwent transrectal ultrasonography-guided prostate biopsies. Patient's age, PSA, digital rectal exam, prostate volume, PSA density (PSAD), and previous negative biopsy, number of positive cores, Gleason score, and biopsy outcome were recorded. Patients are categorized into no cancer, very low, low-, and intermediate-risk categories. The relationship between the model and IR PCa was investigated using binary generalized linear model (GLM) and assessed its discriminatory ability by calculating the area under the receiver operating characteristic curve (AUC).
Results
Among 729 patients, PCa was detected in 234 individuals (32.1%), with 120 (16.5%) diagnosed with IR PCa. The AUC for the novel model compared to the clinical model was 0.806 (95% CI: 0.722–0.889) versus 0.669 (95% CI: 0.543–0.790), with a
p
-value of 0.018. In DCA, the GLM outperformed the clinical model by over 7%, potentially allowing for an additional 44.3% reduction in unnecessary biopsies. The PSAD emerged as the most significant predictor.
Conclusion
We developed a GLM utilizing pre-biopsy features to predict IR PCa. The model demonstrated good discrimination and clinical applicability, which could assist urologists in determining the necessity of a prostate biopsy.
Publisher
Springer Netherlands,Springer Nature B.V
Subject
