Bone metastasis risk and prognosis assessment models for kidney cancer based on machine learning

Abstract

BackgroundBone metastasis is a common adverse event in kidney cancer, often resulting in poor survival. However, tools for predicting KCBM and assessing survival after KCBM have not performed well.MethodsThe study uses machine learning to build models for assessing kidney cancer bone metastasis risk, prognosis, and performance evaluation. We selected 71,414 kidney cancer patients from SEER database between 2010 and 2016. Additionally, 963 patients with kidney cancer from an independent medical center were chosen to validate the performance. In the next step, eight different machine learning methods were applied to develop KCBM diagnosis and prognosis models while the risk factors were identified from univariate and multivariate logistic regression and the prognosis factors were analyzed through Kaplan-Meier survival curve and Cox proportional hazards regression. The performance of the models was compared with current models, including the logistic regression model and the AJCC TNM staging model, applying receiver operating characteristics, decision curve analysis, and the calculation of accuracy and sensitivity in both internal and independent external cohorts.ResultsOur prognosis model achieved an AUC of 0.8269 (95%CI: 0.8083–0.8425) in the internal validation cohort and 0.9123 (95%CI: 0.8979–0.9261) in the external validation cohort. In addition, we tested the performance of the extreme gradient boosting model through decision curve analysis curve, Precision-Recall curve, and Brier score and two models exhibited excellent performance.ConclusionOur developed models can accurately predict the risk and prognosis of KCBM and contribute to helping improve decision-making.

CCL5: a novel biomarker in a diagnostic model for bone metastasis in prostate cancer

“…Composite diagnostic and prognostic models have been applied clinically for diagnosing various bone metastases. For example, a machine learning-based renal cancer bone metastasis risk model constructed based on the SEER database can accurately predict the risk and prognosis of renal cancer bone metastasis, which improves decision-making in the care of patients with renal cancer 20 . A previous study showed that a diagnostic risk model based on colon cancer pathology classi cation, lymph node metastasis, and visceral metastasis could identify patients with colon cancer at high risk of bone metastasis 21 .…”

The Present and Future of Artificial Intelligence in Urological Cancer

“…Ji et al developed an ML model (KCBM) utilizing the SEER database of 71,414 kidney cancer patients to evaluate bone metastasis and long-term survival in this population. The KCBM achieved an AUC of 0.8269 (95% CI: 0.8083-0.8425) [64]. Another study conducted by Feng et al also utilized the SEER database and analyzed data from 39,016 patients to develop six ML models for predicting lymphatic metastasis in kidney cancer.…”

Construction of Prediction Model of Early Glottic Cancer Based on machine learning

“…Among them, the ML method has been widely used in cancer prognosis research, such as laryngeal cancer, lung cancer, breast cancer, kidney cancer, malignant pleural mesothelioma, etc. [7,[10][11][12][13] . Indeed, it effectively offers accurate prognoses based on the cancer sample data [14] .…”