Your browser doesn't support javascript.
loading
Explainable and visualizable machine learning models to predict biochemical recurrence of prostate cancer.
Lu, Wenhao; Zhao, Lin; Wang, Shenfan; Zhang, Huiyong; Jiang, Kangxian; Ji, Jin; Chen, Shaohua; Wang, Chengbang; Wei, Chunmeng; Zhou, Rongbin; Wang, Zuheng; Li, Xiao; Wang, Fubo; Wei, Xuedong; Hou, Wenlei.
Afiliação
  • Lu W; Collaborative Innovation Centre of Regenerative Medicine and Medical BioResource Development and Application Co-Constructed By the Province and Ministry, Guangxi Medical University, No. 22, Shuangyong Road, Qingxiu District, Nanning City, 530021, Guangxi Zhuang Autonomous Region, People's Republic o
  • Zhao L; Center for Genomic and Personalized Medicine, Guangxi Key Laboratory for Genomic and Personalized Medicine, Guangxi Collaborative Innovation Center for Genomic and Personalized Medicine, Guangxi Medical University, Nanning, 530021, Guangxi, People's Republic of China.
  • Wang S; Department of Urology, the First Affiliated Hospital of Guangxi Medical University, Guangxi Medical University, Guangxi, 530021, People's Republic of China.
  • Zhang H; School of Life Sciences, Guangxi Medical University, Nanning, 530021, Guangxi, People's Republic of China.
  • Jiang K; Department of Urology, Shanghai Changhai Hospital, Second Military Medical University, Shanghai, 200433, People's Republic of China.
  • Ji J; Department of Urology, Shanghai Changhai Hospital, Second Military Medical University, Shanghai, 200433, People's Republic of China.
  • Chen S; Center for Genomic and Personalized Medicine, Guangxi Key Laboratory for Genomic and Personalized Medicine, Guangxi Collaborative Innovation Center for Genomic and Personalized Medicine, Guangxi Medical University, Nanning, 530021, Guangxi, People's Republic of China.
  • Wang C; School of Life Sciences, Guangxi Medical University, Nanning, 530021, Guangxi, People's Republic of China.
  • Wei C; Department of Urology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, 362000, People's Republic of China.
  • Zhou R; Department of Urology, Shanghai Changhai Hospital, Second Military Medical University, Shanghai, 200433, People's Republic of China.
  • Wang Z; Center for Genomic and Personalized Medicine, Guangxi Key Laboratory for Genomic and Personalized Medicine, Guangxi Collaborative Innovation Center for Genomic and Personalized Medicine, Guangxi Medical University, Nanning, 530021, Guangxi, People's Republic of China.
  • Li X; Department of Urology, the First Affiliated Hospital of Guangxi Medical University, Guangxi Medical University, Guangxi, 530021, People's Republic of China.
  • Wang F; Center for Genomic and Personalized Medicine, Guangxi Key Laboratory for Genomic and Personalized Medicine, Guangxi Collaborative Innovation Center for Genomic and Personalized Medicine, Guangxi Medical University, Nanning, 530021, Guangxi, People's Republic of China.
  • Wei X; Center for Genomic and Personalized Medicine, Guangxi Key Laboratory for Genomic and Personalized Medicine, Guangxi Collaborative Innovation Center for Genomic and Personalized Medicine, Guangxi Medical University, Nanning, 530021, Guangxi, People's Republic of China.
  • Hou W; Department of Urology, the First Affiliated Hospital of Guangxi Medical University, Guangxi Medical University, Guangxi, 530021, People's Republic of China.
Clin Transl Oncol ; 26(9): 2369-2379, 2024 Sep.
Article em En | MEDLINE | ID: mdl-38602643
ABSTRACT

PURPOSE:

Machine learning (ML) models presented an excellent performance in the prognosis prediction. However, the black box characteristic of ML models limited the clinical applications. Here, we aimed to establish explainable and visualizable ML models to predict biochemical recurrence (BCR) of prostate cancer (PCa). MATERIALS AND

METHODS:

A total of 647 PCa patients were retrospectively evaluated. Clinical parameters were identified using LASSO regression. Then, cohort was split into training and validation datasets with a ratio of 0.750.25 and BCR-related features were included in Cox regression and five ML algorithm to construct BCR prediction models. The clinical utility of each model was evaluated by concordance index (C-index) values and decision curve analyses (DCA). Besides, Shapley Additive Explanation (SHAP) values were used to explain the features in the models.

RESULTS:

We identified 11 BCR-related features using LASSO regression, then establishing five ML-based models, including random survival forest (RSF), survival support vector machine (SSVM), survival Tree (sTree), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and a Cox regression model, C-index were 0.846 (95%CI 0.796-0.894), 0.774 (95%CI 0.712-0.834), 0.757 (95%CI 0.694-0.818), 0.820 (95%CI 0.765-0.869), 0.793 (95%CI 0.735-0.852), and 0.807 (95%CI 0.753-0.858), respectively. The DCA showed that RSF model had significant advantages over all models. In interpretability of ML models, the SHAP value demonstrated the tangible contribution of each feature in RSF model.

CONCLUSIONS:

Our score system provide reference for the identification for BCR, and the crafting of a framework for making therapeutic decisions for PCa on a personalized basis.
Assuntos
Palavras-chave
Texto completo
Adicionar na Minha BVS
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Neoplasias da Próstata / Aprendizado de Máquina / Recidiva Local de Neoplasia Limite: Aged / Humans / Male / Middle aged Idioma: En Revista: Clin Transl Oncol Ano de publicação: 2024 Tipo de documento: Article País de publicação: Itália
Texto completo
Adicionar na Minha BVS
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Neoplasias da Próstata / Aprendizado de Máquina / Recidiva Local de Neoplasia Limite: Aged / Humans / Male / Middle aged Idioma: En Revista: Clin Transl Oncol Ano de publicação: 2024 Tipo de documento: Article País de publicação: Itália