G Vigneswaran, N Doshi, D Maclean, T Bryant, M Harris, N Hacking, K Farrahi, M Niranjan, S Modi
{"title":"通过机器学习预测前列腺动脉栓塞术的结果。","authors":"G Vigneswaran, N Doshi, D Maclean, T Bryant, M Harris, N Hacking, K Farrahi, M Niranjan, S Modi","doi":"10.1007/s00270-024-03776-z","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>This study leverages pre-procedural data and machine learning (ML) techniques to predict outcomes at one year following prostate artery embolization (PAE).</p><p><strong>Materials and methods: </strong>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.</p><p><strong>Results: </strong>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<sup>2 </sup>= 0.2, p < 0.001), forming the basis for our digital user interface.</p><p><strong>Conclusion: </strong>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.</p>","PeriodicalId":9591,"journal":{"name":"CardioVascular and Interventional Radiology","volume":null,"pages":null},"PeriodicalIF":2.8000,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11379731/pdf/","citationCount":"0","resultStr":"{\"title\":\"Machine Learning to Predict Prostate Artery Embolization Outcomes.\",\"authors\":\"G Vigneswaran, N Doshi, D Maclean, T Bryant, M Harris, N Hacking, K Farrahi, M Niranjan, S Modi\",\"doi\":\"10.1007/s00270-024-03776-z\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>This study leverages pre-procedural data and machine learning (ML) techniques to predict outcomes at one year following prostate artery embolization (PAE).</p><p><strong>Materials and methods: </strong>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.</p><p><strong>Results: </strong>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<sup>2 </sup>= 0.2, p < 0.001), forming the basis for our digital user interface.</p><p><strong>Conclusion: </strong>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.</p>\",\"PeriodicalId\":9591,\"journal\":{\"name\":\"CardioVascular and Interventional Radiology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2024-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11379731/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"CardioVascular and Interventional Radiology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s00270-024-03776-z\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/6/19 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q2\",\"JCRName\":\"CARDIAC & CARDIOVASCULAR SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"CardioVascular and Interventional Radiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s00270-024-03776-z","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/6/19 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
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 (R2 = 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.
期刊介绍:
CardioVascular and Interventional Radiology (CVIR) is the official journal of the Cardiovascular and Interventional Radiological Society of Europe, and is also the official organ of a number of additional distinguished national and international interventional radiological societies. CVIR publishes double blinded peer-reviewed original research work including clinical and laboratory investigations, technical notes, case reports, works in progress, and letters to the editor, as well as review articles, pictorial essays, editorials, and special invited submissions in the field of vascular and interventional radiology. Beside the communication of the latest research results in this field, it is also the aim of CVIR to support continuous medical education. Articles that are accepted for publication are done so with the understanding that they, or their substantive contents, have not been and will not be submitted to any other publication.