Machine learning to predict prostate artery embolization outcomes
Machine learning to predict prostate artery embolization outcomes
Purpose: This study leverages pre-procedural data and machine learning (ML) techniques to predict outcomes at one year following prostate artery embolization (PAE). Materials and Methods: This retrospective analysis combines data from the UK-ROPE registry and patients that underwent PAE at our institution between 2012 and 2023. Traditional ML approaches, including linear regression, lasso regression, ridge regression, decision trees and random forests, were used with leave-one-out cross-validation to predict international prostate symptom score (IPSS) at baseline and change at 1 year. Predictors included age, prostate volume, Qmax (maximum urinary flow rate), post-void residual volume, Abrams-Griffiths number (urodynamics score) and baseline IPSS (for change at 1 year). We also independently confirmed our findings using a separate dataset. An interactive digital user interface was developed to facilitate real-time outcome prediction. Results: Complete data were available in 128 patients (66.7 ± 6.9 years). All models predicting IPSS demonstrated reasonable performance, with mean absolute error ranging between 4.9–7.3 for baseline IPSS and 5.2–8.2 for change in IPSS. These numbers represent the differences between the patient-reported and model-predicted IPSS scores. Interestingly, the model error in predicting baseline IPSS (based on objective measures alone) significantly correlated with the change in IPSS at 1-year post-PAE (R
2= 0.2, p < 0.001), forming the basis for our digital user interface. Conclusion: This study uses ML methods to predict IPSS improvement at 1 year, integrated into a user-friendly interface for real-time prediction. This tool could be used to counsel patients prior to treatment.
Artificial intelligence, Embolization, Prostate
Vigneswaran, G.
4e3865ad-1a15-4a27-b810-55348e7baceb
Doshi, N.
a49ab1be-51b3-4e4c-b06a-7dc8e375cbac
Maclean, D.
9a01537b-1471-4ea2-9273-23f4a86157b0
Bryant, T.
851b4201-e79c-4c44-a236-c53661187b79
Harris, M.
cad0c55d-92a5-4fb5-8b89-b003a00ebfaa
Hacking, N.
b6287f0b-1b80-49a6-a01a-f52f9da671c8
Farrahi, K.
bc848b9c-fc32-475c-b241-f6ade8babacb
Niranjan, M.
5cbaeea8-7288-4b55-a89c-c43d212ddd4f
Modi, S.
c773fbe9-d0d7-4ac6-bb0d-6f635cfe4b49
19 June 2024
Vigneswaran, G.
4e3865ad-1a15-4a27-b810-55348e7baceb
Doshi, N.
a49ab1be-51b3-4e4c-b06a-7dc8e375cbac
Maclean, D.
9a01537b-1471-4ea2-9273-23f4a86157b0
Bryant, T.
851b4201-e79c-4c44-a236-c53661187b79
Harris, M.
cad0c55d-92a5-4fb5-8b89-b003a00ebfaa
Hacking, N.
b6287f0b-1b80-49a6-a01a-f52f9da671c8
Farrahi, K.
bc848b9c-fc32-475c-b241-f6ade8babacb
Niranjan, M.
5cbaeea8-7288-4b55-a89c-c43d212ddd4f
Modi, S.
c773fbe9-d0d7-4ac6-bb0d-6f635cfe4b49
Vigneswaran, G., Doshi, N., Maclean, D., Bryant, T., Harris, M., Hacking, N., Farrahi, K., Niranjan, M. and Modi, S.
(2024)
Machine learning to predict prostate artery embolization outcomes.
Cardiovascular and Interventional Radiology.
(doi:10.1007/s00270-024-03776-z).
Abstract
Purpose: This study leverages pre-procedural data and machine learning (ML) techniques to predict outcomes at one year following prostate artery embolization (PAE). Materials and Methods: This retrospective analysis combines data from the UK-ROPE registry and patients that underwent PAE at our institution between 2012 and 2023. Traditional ML approaches, including linear regression, lasso regression, ridge regression, decision trees and random forests, were used with leave-one-out cross-validation to predict international prostate symptom score (IPSS) at baseline and change at 1 year. Predictors included age, prostate volume, Qmax (maximum urinary flow rate), post-void residual volume, Abrams-Griffiths number (urodynamics score) and baseline IPSS (for change at 1 year). We also independently confirmed our findings using a separate dataset. An interactive digital user interface was developed to facilitate real-time outcome prediction. Results: Complete data were available in 128 patients (66.7 ± 6.9 years). All models predicting IPSS demonstrated reasonable performance, with mean absolute error ranging between 4.9–7.3 for baseline IPSS and 5.2–8.2 for change in IPSS. These numbers represent the differences between the patient-reported and model-predicted IPSS scores. Interestingly, the model error in predicting baseline IPSS (based on objective measures alone) significantly correlated with the change in IPSS at 1-year post-PAE (R
2= 0.2, p < 0.001), forming the basis for our digital user interface. Conclusion: This study uses ML methods to predict IPSS improvement at 1 year, integrated into a user-friendly interface for real-time prediction. This tool could be used to counsel patients prior to treatment.
Text
s00270-024-03776-z
- Version of Record
More information
Accepted/In Press date: 26 May 2024
e-pub ahead of print date: 19 June 2024
Published date: 19 June 2024
Additional Information:
Publisher Copyright:
© The Author(s) 2024.
Keywords:
Artificial intelligence, Embolization, Prostate
Identifiers
Local EPrints ID: 492124
URI: http://eprints.soton.ac.uk/id/eprint/492124
ISSN: 0174-1551
PURE UUID: 12207ad5-9673-4781-9e9d-6ca1f8197611
Catalogue record
Date deposited: 17 Jul 2024 16:33
Last modified: 24 Jul 2024 02:02
Export record
Altmetrics
Contributors
Author:
N. Doshi
Author:
D. Maclean
Author:
T. Bryant
Author:
M. Harris
Author:
N. Hacking
Author:
K. Farrahi
Author:
M. Niranjan
Author:
S. Modi
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics