Deep Neural Networks Outperform the CAPRA Score in Predicting Biochemical Recurrence After Prostatectomy
BackgroundUse of predictive models for the prediction of biochemical recurrence (BCR) is gaining attention for prostate cancer (PCa). Specifically, BCR occurs in approximately 20–40% of patients five years after radical prostatectomy (RP) and the ability to predict BCR may help clinicians to make be...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-02-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2020.607923/full |
| _version_ | 1818944131099000832 |
|---|---|
| author | Paul Sargos Nicolas Leduc Nicolas Giraud Giorgio Gandaglia Mathieu Roumiguié Guillaume Ploussard Francois Rozet Michel Soulié Romain Mathieu Pierre Mongiat Artus Tamim Niazi Vincent Vinh-Hung Jean-Baptiste Beauval |
| author_facet | Paul Sargos Nicolas Leduc Nicolas Giraud Giorgio Gandaglia Mathieu Roumiguié Guillaume Ploussard Francois Rozet Michel Soulié Romain Mathieu Pierre Mongiat Artus Tamim Niazi Vincent Vinh-Hung Jean-Baptiste Beauval |
| author_sort | Paul Sargos |
| collection | DOAJ |
| description | BackgroundUse of predictive models for the prediction of biochemical recurrence (BCR) is gaining attention for prostate cancer (PCa). Specifically, BCR occurs in approximately 20–40% of patients five years after radical prostatectomy (RP) and the ability to predict BCR may help clinicians to make better treatment decisions. We aim to investigate the accuracy of CAPRA score compared to others models in predicting the 3-year BCR of PCa patients.Material and MethodsA total of 5043 men who underwent RP were analyzed retrospectively. The accuracy of CAPRA score, Cox regression analysis, logistic regression, K-nearest neighbor (KNN), random forest (RF) and a densely connected feed-forward neural network (DNN) classifier were compared in terms of 3-year BCR predictive value. The area under the receiver operating characteristic curve was mainly used to assess the performance of the predictive models in predicting the 3 years BCR of PCa patients. Pre-operative data such as PSA level, Gleason grade, and T stage were included in the multivariate analysis. To measure potential improvements to the model performance due to additional data, each model was trained once more with an additional set of post-operative surgical data from definitive pathology.ResultsUsing the CAPRA score variables, DNN predictive model showed the highest AUC value of 0.7 comparing to the CAPRA score, logistic regression, KNN, RF, and cox regression with 0.63, 0.63, 0.55, 0.64, and 0.64, respectively. After including the post-operative variables to the model, the AUC values based on KNN, RF, and cox regression and DNN were improved to 0.77, 0.74, 0.75, and 0.84, respectively.ConclusionsOur results showed that the DNN has the potential to predict the 3-year BCR and outperformed the CAPRA score and other predictive models. |
| first_indexed | 2024-12-20T07:38:20Z |
| format | Article |
| id | doaj.art-f227e8b8b57d46cdbc4742d6827c7712 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-20T07:38:20Z |
| publishDate | 2021-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-f227e8b8b57d46cdbc4742d6827c77122022-12-21T19:48:12ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2021-02-011010.3389/fonc.2020.607923607923Deep Neural Networks Outperform the CAPRA Score in Predicting Biochemical Recurrence After ProstatectomyPaul Sargos0Nicolas Leduc1Nicolas Giraud2Giorgio Gandaglia3Mathieu Roumiguié4Guillaume Ploussard5Francois Rozet6Michel Soulié7Romain Mathieu8Pierre Mongiat Artus9Tamim Niazi10Vincent Vinh-Hung11Jean-Baptiste Beauval12Department of Radiation Oncology, Institut Bergonié, Bordeaux, FranceDepartment of Radiation Oncology, Institut Bergonié, Bordeaux, FranceDivision of Radiation Oncology, Department of Oncology, McGill University, Montreal, QC, CanadaDivision of Oncology, Unit of Urology, Urological Research Institute, IRCCS Ospedale San Raffaele, Milan, ItalyDepartment of Urology, CHU de Toulouse, Toulouse, FranceDepartment of Urology, Clinique La Croix du Sud, Quint-Fonsegrives, FranceDepartment of Urology, Institut Mutualiste Montsouris, Paris, FranceDepartment of Urology, CHU de Toulouse, Toulouse, FranceDepartment of Urology, CHU de Rennes, Rennes, FranceDepartment of Urology, Hôpital Saint Louis, Paris, FranceDivision of Radiation Oncology, Department of Oncology, McGill University, Montreal, QC, CanadaDepartment of Radiation Oncology, Hôpital Clarac, CHU de la Martinique, Fort-de-France, FranceDepartment of Urology, CHU de Toulouse, Toulouse, FranceBackgroundUse of predictive models for the prediction of biochemical recurrence (BCR) is gaining attention for prostate cancer (PCa). Specifically, BCR occurs in approximately 20–40% of patients five years after radical prostatectomy (RP) and the ability to predict BCR may help clinicians to make better treatment decisions. We aim to investigate the accuracy of CAPRA score compared to others models in predicting the 3-year BCR of PCa patients.Material and MethodsA total of 5043 men who underwent RP were analyzed retrospectively. The accuracy of CAPRA score, Cox regression analysis, logistic regression, K-nearest neighbor (KNN), random forest (RF) and a densely connected feed-forward neural network (DNN) classifier were compared in terms of 3-year BCR predictive value. The area under the receiver operating characteristic curve was mainly used to assess the performance of the predictive models in predicting the 3 years BCR of PCa patients. Pre-operative data such as PSA level, Gleason grade, and T stage were included in the multivariate analysis. To measure potential improvements to the model performance due to additional data, each model was trained once more with an additional set of post-operative surgical data from definitive pathology.ResultsUsing the CAPRA score variables, DNN predictive model showed the highest AUC value of 0.7 comparing to the CAPRA score, logistic regression, KNN, RF, and cox regression with 0.63, 0.63, 0.55, 0.64, and 0.64, respectively. After including the post-operative variables to the model, the AUC values based on KNN, RF, and cox regression and DNN were improved to 0.77, 0.74, 0.75, and 0.84, respectively.ConclusionsOur results showed that the DNN has the potential to predict the 3-year BCR and outperformed the CAPRA score and other predictive models.https://www.frontiersin.org/articles/10.3389/fonc.2020.607923/fullprostate cancermachine learningpredictiverecurrencebiochemical |
| spellingShingle | Paul Sargos Nicolas Leduc Nicolas Giraud Giorgio Gandaglia Mathieu Roumiguié Guillaume Ploussard Francois Rozet Michel Soulié Romain Mathieu Pierre Mongiat Artus Tamim Niazi Vincent Vinh-Hung Jean-Baptiste Beauval Deep Neural Networks Outperform the CAPRA Score in Predicting Biochemical Recurrence After Prostatectomy Frontiers in Oncology prostate cancer machine learning predictive recurrence biochemical |
| title | Deep Neural Networks Outperform the CAPRA Score in Predicting Biochemical Recurrence After Prostatectomy |
| title_full | Deep Neural Networks Outperform the CAPRA Score in Predicting Biochemical Recurrence After Prostatectomy |
| title_fullStr | Deep Neural Networks Outperform the CAPRA Score in Predicting Biochemical Recurrence After Prostatectomy |
| title_full_unstemmed | Deep Neural Networks Outperform the CAPRA Score in Predicting Biochemical Recurrence After Prostatectomy |
| title_short | Deep Neural Networks Outperform the CAPRA Score in Predicting Biochemical Recurrence After Prostatectomy |
| title_sort | deep neural networks outperform the capra score in predicting biochemical recurrence after prostatectomy |
| topic | prostate cancer machine learning predictive recurrence biochemical |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2020.607923/full |
| work_keys_str_mv | AT paulsargos deepneuralnetworksoutperformthecaprascoreinpredictingbiochemicalrecurrenceafterprostatectomy AT nicolasleduc deepneuralnetworksoutperformthecaprascoreinpredictingbiochemicalrecurrenceafterprostatectomy AT nicolasgiraud deepneuralnetworksoutperformthecaprascoreinpredictingbiochemicalrecurrenceafterprostatectomy AT giorgiogandaglia deepneuralnetworksoutperformthecaprascoreinpredictingbiochemicalrecurrenceafterprostatectomy AT mathieuroumiguie deepneuralnetworksoutperformthecaprascoreinpredictingbiochemicalrecurrenceafterprostatectomy AT guillaumeploussard deepneuralnetworksoutperformthecaprascoreinpredictingbiochemicalrecurrenceafterprostatectomy AT francoisrozet deepneuralnetworksoutperformthecaprascoreinpredictingbiochemicalrecurrenceafterprostatectomy AT michelsoulie deepneuralnetworksoutperformthecaprascoreinpredictingbiochemicalrecurrenceafterprostatectomy AT romainmathieu deepneuralnetworksoutperformthecaprascoreinpredictingbiochemicalrecurrenceafterprostatectomy AT pierremongiatartus deepneuralnetworksoutperformthecaprascoreinpredictingbiochemicalrecurrenceafterprostatectomy AT tamimniazi deepneuralnetworksoutperformthecaprascoreinpredictingbiochemicalrecurrenceafterprostatectomy AT vincentvinhhung deepneuralnetworksoutperformthecaprascoreinpredictingbiochemicalrecurrenceafterprostatectomy AT jeanbaptistebeauval deepneuralnetworksoutperformthecaprascoreinpredictingbiochemicalrecurrenceafterprostatectomy |