Prediction of prostate biopsy outcomes at different cut-offs of prostate-specific antigen using machine learning: a multicenter study

Abstract Background Machine learning (ML) is a significant area of artificial intelligence, which can improve the accuracy of predictive or diagnostic models for differentiating between prostate biopsy outcomes. This study aims to develop a novel decision-support ML model for classifying patients wi...

Full description

Saved in:
Bibliographic Details
Main Authors: Mostafa A. Arafa, Karim H. Farhat, Sherin F. Aly, Farrukh K. Khan, Alaa Mokhtar, Abdulaziz M. Althunayan, Waleed Al-Taweel, Sultan S. Al-Khateeb, Sami Azhari, Danny M. Rabah
Format: Article
Language:English
Published: SpringerOpen 2025-03-01
Series:Journal of the Egyptian National Cancer Institute
Subjects:
Online Access:https://doi.org/10.1186/s43046-025-00265-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849390065485086720
author Mostafa A. Arafa
Karim H. Farhat
Sherin F. Aly
Farrukh K. Khan
Alaa Mokhtar
Abdulaziz M. Althunayan
Waleed Al-Taweel
Sultan S. Al-Khateeb
Sami Azhari
Danny M. Rabah
author_facet Mostafa A. Arafa
Karim H. Farhat
Sherin F. Aly
Farrukh K. Khan
Alaa Mokhtar
Abdulaziz M. Althunayan
Waleed Al-Taweel
Sultan S. Al-Khateeb
Sami Azhari
Danny M. Rabah
author_sort Mostafa A. Arafa
collection DOAJ
description Abstract Background Machine learning (ML) is a significant area of artificial intelligence, which can improve the accuracy of predictive or diagnostic models for differentiating between prostate biopsy outcomes. This study aims to develop a novel decision-support ML model for classifying patients with biopsy-negative (cancer-free), clinically significant, and non-clinically significant prostate cancer across two prostate-specific antigen (PSA) cut-offs ≤ 10 ng/ml and > 10 ng/ml. Methods The data for the current study were retrieved from the records of two main hospitals in Riyadh, Saudi Arabia from July 2018 through July 2024. Six machine learning algorithms were employed, and the dataset was randomly divided into a training set and a validation set at a ratio of 8:2. The following metrics were used as performance indicators across the six algorithms: Accuracy, Precision, Recall, F1-score, and area under the curve. Recent data from the two hospitals was utilized for external validation. Results The metrics for Random Forest, Extra Tree, and Decision Tree algorithms showed excellent capability in classifying the outcomes of prostate biopsy for the two PSA cut-offs. However, the metrics for the PSA cut-off > 10 ng/ml are higher than those for PSA ≤ 10 ng/ml. For the three-class classification, the accuracy and area under the curve for the cut-off > 10 ng/ml were 0.96 and 0.99, respectively. While for the cut-off ≤ 10 ng/ml they were 0.92 and 0.94 for Random Forest and 0.94 and 0.95 for the Extra Tree algorithm. The metrics of non-clinically significant and biopsy-negative cases outperformed those of clinically significant cases. Conclusion ML models are proving to be effective tools in differentiating between prostate biopsy outcomes, enhancing diagnostic accuracy, and potentially transforming clinical practices in prostate cancer management.
format Article
id doaj-art-775f5c93b26d4e4fb9b93bef245cc1cc
institution Kabale University
issn 2589-0409
language English
publishDate 2025-03-01
publisher SpringerOpen
record_format Article
series Journal of the Egyptian National Cancer Institute
spelling doaj-art-775f5c93b26d4e4fb9b93bef245cc1cc2025-08-20T03:41:47ZengSpringerOpenJournal of the Egyptian National Cancer Institute2589-04092025-03-013711810.1186/s43046-025-00265-3Prediction of prostate biopsy outcomes at different cut-offs of prostate-specific antigen using machine learning: a multicenter studyMostafa A. Arafa0Karim H. Farhat1Sherin F. Aly2Farrukh K. Khan3Alaa Mokhtar4Abdulaziz M. Althunayan5Waleed Al-Taweel6Sultan S. Al-Khateeb7Sami Azhari8Danny M. Rabah9The Cancer Research Chair, Surgery Department, College of Medicine, King Saud UniversityThe Cancer Research Chair, Surgery Department, College of Medicine, King Saud UniversityInformation Technology Department, Institute of Graduate Studies and Research, Alexandria UniversityThe Cancer Research Chair, Surgery Department, College of Medicine, King Saud UniversityDepartment of Urology, King Faisal Specialist Hospital and Research CenterThe Cancer Research Chair, Surgery Department, College of Medicine, King Saud UniversityDepartment of Urology, King Faisal Specialist Hospital and Research CenterDepartment of Urology, King Faisal Specialist Hospital and Research CenterCollege of Medicine, Alfaisal UniversityThe Cancer Research Chair, Surgery Department, College of Medicine, King Saud UniversityAbstract Background Machine learning (ML) is a significant area of artificial intelligence, which can improve the accuracy of predictive or diagnostic models for differentiating between prostate biopsy outcomes. This study aims to develop a novel decision-support ML model for classifying patients with biopsy-negative (cancer-free), clinically significant, and non-clinically significant prostate cancer across two prostate-specific antigen (PSA) cut-offs ≤ 10 ng/ml and > 10 ng/ml. Methods The data for the current study were retrieved from the records of two main hospitals in Riyadh, Saudi Arabia from July 2018 through July 2024. Six machine learning algorithms were employed, and the dataset was randomly divided into a training set and a validation set at a ratio of 8:2. The following metrics were used as performance indicators across the six algorithms: Accuracy, Precision, Recall, F1-score, and area under the curve. Recent data from the two hospitals was utilized for external validation. Results The metrics for Random Forest, Extra Tree, and Decision Tree algorithms showed excellent capability in classifying the outcomes of prostate biopsy for the two PSA cut-offs. However, the metrics for the PSA cut-off > 10 ng/ml are higher than those for PSA ≤ 10 ng/ml. For the three-class classification, the accuracy and area under the curve for the cut-off > 10 ng/ml were 0.96 and 0.99, respectively. While for the cut-off ≤ 10 ng/ml they were 0.92 and 0.94 for Random Forest and 0.94 and 0.95 for the Extra Tree algorithm. The metrics of non-clinically significant and biopsy-negative cases outperformed those of clinically significant cases. Conclusion ML models are proving to be effective tools in differentiating between prostate biopsy outcomes, enhancing diagnostic accuracy, and potentially transforming clinical practices in prostate cancer management.https://doi.org/10.1186/s43046-025-00265-3Machine learning prediction modelsProstate biopsy outcomesProstate-specific antigen cut-offs
spellingShingle Mostafa A. Arafa
Karim H. Farhat
Sherin F. Aly
Farrukh K. Khan
Alaa Mokhtar
Abdulaziz M. Althunayan
Waleed Al-Taweel
Sultan S. Al-Khateeb
Sami Azhari
Danny M. Rabah
Prediction of prostate biopsy outcomes at different cut-offs of prostate-specific antigen using machine learning: a multicenter study
Journal of the Egyptian National Cancer Institute
Machine learning prediction models
Prostate biopsy outcomes
Prostate-specific antigen cut-offs
title Prediction of prostate biopsy outcomes at different cut-offs of prostate-specific antigen using machine learning: a multicenter study
title_full Prediction of prostate biopsy outcomes at different cut-offs of prostate-specific antigen using machine learning: a multicenter study
title_fullStr Prediction of prostate biopsy outcomes at different cut-offs of prostate-specific antigen using machine learning: a multicenter study
title_full_unstemmed Prediction of prostate biopsy outcomes at different cut-offs of prostate-specific antigen using machine learning: a multicenter study
title_short Prediction of prostate biopsy outcomes at different cut-offs of prostate-specific antigen using machine learning: a multicenter study
title_sort prediction of prostate biopsy outcomes at different cut offs of prostate specific antigen using machine learning a multicenter study
topic Machine learning prediction models
Prostate biopsy outcomes
Prostate-specific antigen cut-offs
url https://doi.org/10.1186/s43046-025-00265-3
work_keys_str_mv AT mostafaaarafa predictionofprostatebiopsyoutcomesatdifferentcutoffsofprostatespecificantigenusingmachinelearningamulticenterstudy
AT karimhfarhat predictionofprostatebiopsyoutcomesatdifferentcutoffsofprostatespecificantigenusingmachinelearningamulticenterstudy
AT sherinfaly predictionofprostatebiopsyoutcomesatdifferentcutoffsofprostatespecificantigenusingmachinelearningamulticenterstudy
AT farrukhkkhan predictionofprostatebiopsyoutcomesatdifferentcutoffsofprostatespecificantigenusingmachinelearningamulticenterstudy
AT alaamokhtar predictionofprostatebiopsyoutcomesatdifferentcutoffsofprostatespecificantigenusingmachinelearningamulticenterstudy
AT abdulazizmalthunayan predictionofprostatebiopsyoutcomesatdifferentcutoffsofprostatespecificantigenusingmachinelearningamulticenterstudy
AT waleedaltaweel predictionofprostatebiopsyoutcomesatdifferentcutoffsofprostatespecificantigenusingmachinelearningamulticenterstudy
AT sultansalkhateeb predictionofprostatebiopsyoutcomesatdifferentcutoffsofprostatespecificantigenusingmachinelearningamulticenterstudy
AT samiazhari predictionofprostatebiopsyoutcomesatdifferentcutoffsofprostatespecificantigenusingmachinelearningamulticenterstudy
AT dannymrabah predictionofprostatebiopsyoutcomesatdifferentcutoffsofprostatespecificantigenusingmachinelearningamulticenterstudy