AUTHOR=Wang Ziye , Xu Chan , Liu Wencai , Zhang Meiying , Zou Jian’an , Shao Mingfeng , Feng Xiaowei , Yang Qinwen , Li Wenle , Shi Xiue , Zang Guangxi , Yin Chengliang 

TITLE=A clinical prediction model for predicting the risk of liver metastasis from renal cell carcinoma based on machine learning

JOURNAL=Frontiers in Endocrinology

VOLUME=Volume 13 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2022.1083569

DOI=10.3389/fendo.2022.1083569

ISSN=1664-2392

ABSTRACT=Abstract
BACKGROUND: Renal cell carcinoma (RCC) is a highly metastasis urological cancer. RCC with liver metastasis (LM) carries a dismal prognosis. The objective of this study is to develop a machine learning (ML) model that predicts the risk of RCC with LM, which is used to assist clinical treatment.  
METHODS: A retrospective study of 42,547 patients with RCC were extracted from the Surveillance, Epidemiology and End Results (SEER) database. Machine learning (ML) includes algorithmic methods is an fast-rising field which has been widely used in the biomedical field. Logistic regression (LR), Gradient boosting machine (GBM), Extreme gradient boosting (XGB), Random Forest (RF), Decision Tree (DT) and Naïve Bayesian Model (NBC) were applied to develop prediction models in combination with the clinical characters of patients to predict the risk of RCC with LM. The six models were cross-validated tenfold and the best performing model was selected based on the area under the curve (AUC) value. Further validation was performed using the data of 852 patients from the Second Affiliated Hospital of Dalian Medical University. The corresponding web online calculator was finally constructed.
RESULTS: Bone metastasis, lung metastasis, grade, T stage, N stage, and tumor size were independent risk factors for the development of RCC with LM by multivariate regression analysis. In addition, the correlation of relative proportions of these six clinical variables were showed by heatmap. In the prediction models of RCC with LM, mean AUC of XGB model among the six machine algorithms was 0.947. Base on the XGB model, the web calculator(https://share.streamlit.io/liuwencai4/renal_liver/main/renal_liver.py) was developed to evaluate the risk of RCC with LM.
CONCLUSIONS: This ML model has the best prediction effect on RCC with LM. The web calculator constructed based on the XGB model has a great potential for clinicians to make clinical decisions and improving prognosis of RCC patients with LM.