학술논문
Clinical application of machine learning models in patients with prostate cancer before prostatectomy.
Document Type
Academic Journal
Author
Guerra A; Department of Radiology, Hospital da Luz Lisbon, Rua Fernando Curado Ribeiro, 2, 7º esq, 1495-094, Algés, Lisboa, Portugal. gisaguerra@gmail.com.; Orton MR; Royal Marsden Hospital NHS Foundation Trust, London, England.; Wang H; Royal Surrey County Hospital NSH Foundation Trust, Royal Marsden Hospital NHS Foundation Trust, London, England.; Konidari M; Royal Marsden Hospital NHS Foundation Trust, London, England.; Maes K; Department of Urology, Hospital da Luz Lisbon, Lisbon, Portugal.; Papanikolaou NK; Royal Marsden Hospital NHS Foundation Trust, London, England.; Koh DM; Royal Marsden Hospital NHS Foundation Trust, London, England.
Source
Publisher: Springer Nature Country of Publication: England NLM ID: 101172931 Publication Model: Electronic Cited Medium: Internet ISSN: 1470-7330 (Electronic) Linking ISSN: 14707330 NLM ISO Abbreviation: Cancer Imaging Subsets: MEDLINE
Subject
Language
English
Abstract
Background: To build machine learning predictive models for surgical risk assessment of extracapsular extension (ECE) in patients with prostate cancer (PCa) before radical prostatectomy; and to compare the use of decision curve analysis (DCA) and receiver operating characteristic (ROC) metrics for selecting input feature combinations in models.
Methods: This retrospective observational study included two independent data sets: 139 participants from a single institution (training), and 55 from 15 other institutions (external validation), both treated with Robotic Assisted Radical Prostatectomy (RARP). Five ML models, based on different combinations of clinical, semantic (interpreted by a radiologist) and radiomics features computed from T2W-MRI images, were built to predict extracapsular extension in the prostatectomy specimen (pECE+). DCA plots were used to rank the models' net benefit when assigning patients to prostatectomy with non-nerve-sparing surgery (NNSS) or nerve-sparing surgery (NSS), depending on the predicted ECE status. DCA model rankings were compared with those drived from ROC area under the curve (AUC).
Results: In the training data, the model using clinical, semantic, and radiomics features gave the highest net benefit values across relevant threshold probabilities, and similar decision curve was observed in the external validation data. The model ranking using the AUC was different in the discovery group and favoured the model using clinical + semantic features only.
Conclusions: The combined model based on clinical, semantic and radiomic features may be used to predict pECE + in patients with PCa and results in a positive net benefit when used to choose between prostatectomy with NNS or NNSS.
(© 2024. The Author(s).)
Methods: This retrospective observational study included two independent data sets: 139 participants from a single institution (training), and 55 from 15 other institutions (external validation), both treated with Robotic Assisted Radical Prostatectomy (RARP). Five ML models, based on different combinations of clinical, semantic (interpreted by a radiologist) and radiomics features computed from T2W-MRI images, were built to predict extracapsular extension in the prostatectomy specimen (pECE+). DCA plots were used to rank the models' net benefit when assigning patients to prostatectomy with non-nerve-sparing surgery (NNSS) or nerve-sparing surgery (NSS), depending on the predicted ECE status. DCA model rankings were compared with those drived from ROC area under the curve (AUC).
Results: In the training data, the model using clinical, semantic, and radiomics features gave the highest net benefit values across relevant threshold probabilities, and similar decision curve was observed in the external validation data. The model ranking using the AUC was different in the discovery group and favoured the model using clinical + semantic features only.
Conclusions: The combined model based on clinical, semantic and radiomic features may be used to predict pECE + in patients with PCa and results in a positive net benefit when used to choose between prostatectomy with NNS or NNSS.
(© 2024. The Author(s).)