Integrating radiological and clinical data for clinically significant prostate cancer detection with machine learning techniques
Abstract In prostate cancer (PCa), risk calculators have been proposed, relying on clinical parameters and magnetic resonance imaging (MRI) enable early prediction of clinically significant cancer (CsPCa). The prostate imaging–reporting and data system (PI-RADS) is combined with clinical variables p...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-88297-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862342091276288 |
|---|---|
| author | Luis Mariano Esteban Ángel Borque-Fernando Maria Etelvina Escorihuela Javier Esteban-Escaño Jose María Abascal Pol Servian Juan Morote |
| author_facet | Luis Mariano Esteban Ángel Borque-Fernando Maria Etelvina Escorihuela Javier Esteban-Escaño Jose María Abascal Pol Servian Juan Morote |
| author_sort | Luis Mariano Esteban |
| collection | DOAJ |
| description | Abstract In prostate cancer (PCa), risk calculators have been proposed, relying on clinical parameters and magnetic resonance imaging (MRI) enable early prediction of clinically significant cancer (CsPCa). The prostate imaging–reporting and data system (PI-RADS) is combined with clinical variables predominantly based on logistic regression models. This study explores modeling using regularization techniques such as ridge regression, LASSO, elastic net, classification tree, tree ensemble models like random forest or XGBoost, and neural networks to predict CsPCa in a dataset of 4799 patients in Catalonia (Spain). An 80–20% split was employed for training and validation. We used predictor variables such as age, prostate-specific antigen (PSA), prostate volume, PSA density (PSAD), digital rectal exam (DRE) findings, family history of PCa, a previous negative biopsy, and PI-RADS categories. When considering a sensitivity of 0.9, in the validation set, the XGBoost model outperforms others with a specificity of 0.640, followed closely by random forest (0.638), neural network (0.634), and logistic regression (0.620). In terms of clinical utility, for a 10% missclassification of CsPCa, XGBoost can avoid 41.77% of unnecessary biopsies, followed closely by random forest (41.67%) and neural networks (41.46%), while logistic regression has a lower rate of 40.62%. Using SHAP values for model explainability, PI-RADS emerges as the most influential risk factor, particularly for individuals with PI-RADS 4 and 5. Additionally, a positive digital rectal examination (DRE) or family history of prostate cancer proves highly influential for certain individuals, while a previous negative biopsy serves as a protective factor for others. |
| format | Article |
| id | doaj-art-cca879b773b64d338ba60bec89899fce |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-cca879b773b64d338ba60bec89899fce2025-02-09T12:33:09ZengNature PortfolioScientific Reports2045-23222025-02-0115112110.1038/s41598-025-88297-6Integrating radiological and clinical data for clinically significant prostate cancer detection with machine learning techniquesLuis Mariano Esteban0Ángel Borque-Fernando1Maria Etelvina Escorihuela2Javier Esteban-Escaño3Jose María Abascal4Pol Servian5Juan Morote6Department of Applied Mathematics, Escuela Universitaria Politécnica de La Almunia, Universidad de ZaragozaDepartment of Urology, Miguel Servet University HospitalDepartment of Applied Mathematics, Escuela Universitaria Politécnica de La Almunia, Universidad de ZaragozaDepartment of Electronic Engineering and Communications, Escuela Universitaria Politécnica de La Almunia, Universidad de ZaragozaDepartment of Urology, Department of Surgery, Parc de Salut Mar, Universitat Pompeu FabraDepartment of Urology, Hospital Germans Trias i PujolDepartment of Urology, Vall d’Hebron HospitalAbstract In prostate cancer (PCa), risk calculators have been proposed, relying on clinical parameters and magnetic resonance imaging (MRI) enable early prediction of clinically significant cancer (CsPCa). The prostate imaging–reporting and data system (PI-RADS) is combined with clinical variables predominantly based on logistic regression models. This study explores modeling using regularization techniques such as ridge regression, LASSO, elastic net, classification tree, tree ensemble models like random forest or XGBoost, and neural networks to predict CsPCa in a dataset of 4799 patients in Catalonia (Spain). An 80–20% split was employed for training and validation. We used predictor variables such as age, prostate-specific antigen (PSA), prostate volume, PSA density (PSAD), digital rectal exam (DRE) findings, family history of PCa, a previous negative biopsy, and PI-RADS categories. When considering a sensitivity of 0.9, in the validation set, the XGBoost model outperforms others with a specificity of 0.640, followed closely by random forest (0.638), neural network (0.634), and logistic regression (0.620). In terms of clinical utility, for a 10% missclassification of CsPCa, XGBoost can avoid 41.77% of unnecessary biopsies, followed closely by random forest (41.67%) and neural networks (41.46%), while logistic regression has a lower rate of 40.62%. Using SHAP values for model explainability, PI-RADS emerges as the most influential risk factor, particularly for individuals with PI-RADS 4 and 5. Additionally, a positive digital rectal examination (DRE) or family history of prostate cancer proves highly influential for certain individuals, while a previous negative biopsy serves as a protective factor for others.https://doi.org/10.1038/s41598-025-88297-6Clinically significant prostate cancerMachine learningClinical utilitySHAP values |
| spellingShingle | Luis Mariano Esteban Ángel Borque-Fernando Maria Etelvina Escorihuela Javier Esteban-Escaño Jose María Abascal Pol Servian Juan Morote Integrating radiological and clinical data for clinically significant prostate cancer detection with machine learning techniques Scientific Reports Clinically significant prostate cancer Machine learning Clinical utility SHAP values |
| title | Integrating radiological and clinical data for clinically significant prostate cancer detection with machine learning techniques |
| title_full | Integrating radiological and clinical data for clinically significant prostate cancer detection with machine learning techniques |
| title_fullStr | Integrating radiological and clinical data for clinically significant prostate cancer detection with machine learning techniques |
| title_full_unstemmed | Integrating radiological and clinical data for clinically significant prostate cancer detection with machine learning techniques |
| title_short | Integrating radiological and clinical data for clinically significant prostate cancer detection with machine learning techniques |
| title_sort | integrating radiological and clinical data for clinically significant prostate cancer detection with machine learning techniques |
| topic | Clinically significant prostate cancer Machine learning Clinical utility SHAP values |
| url | https://doi.org/10.1038/s41598-025-88297-6 |
| work_keys_str_mv | AT luismarianoesteban integratingradiologicalandclinicaldataforclinicallysignificantprostatecancerdetectionwithmachinelearningtechniques AT angelborquefernando integratingradiologicalandclinicaldataforclinicallysignificantprostatecancerdetectionwithmachinelearningtechniques AT mariaetelvinaescorihuela integratingradiologicalandclinicaldataforclinicallysignificantprostatecancerdetectionwithmachinelearningtechniques AT javierestebanescano integratingradiologicalandclinicaldataforclinicallysignificantprostatecancerdetectionwithmachinelearningtechniques AT josemariaabascal integratingradiologicalandclinicaldataforclinicallysignificantprostatecancerdetectionwithmachinelearningtechniques AT polservian integratingradiologicalandclinicaldataforclinicallysignificantprostatecancerdetectionwithmachinelearningtechniques AT juanmorote integratingradiologicalandclinicaldataforclinicallysignificantprostatecancerdetectionwithmachinelearningtechniques |