# Explainable machine learning model predicts response to adjuvant therapy after radical cystectomy in bladder cancer

## TL;DR

A machine learning model predicts how bladder cancer patients will respond to therapy after surgery, using factors like tumor features and molecular markers.

## Contribution

The study introduces an explainable machine learning model combining clinical and molecular features to predict adjuvant therapy response in bladder cancer.

## Key findings

- The random forest model achieved high predictive performance (AUC = 0.92 in training; 0.74 in testing).
- Vascular invasion, perineural invasion, and PD-L1/HER2 expression were key predictors identified via SHAP analysis.
- Decision curve analysis showed favorable net benefit within a moderate-risk threshold.

## Abstract

Radical cystectomy (RC) is the standard treatment for muscle-invasive and select high-risk non–muscle-invasive bladder cancer. Despite definitive surgery, recurrence and progression remain major clinical concerns. Adjuvant chemotherapy and immunotherapy may improve outcomes, but therapeutic response varies due to tumor heterogeneity. Robust predictive models are needed to guide individualized treatment strategies.

This study retrospectively analyzed bladder cancer patients undergoing RC. Data included tumor morphology (e.g., vascular and perineural invasion), demographic variables (e.g., age, sex), and molecular markers (e.g., PD-L1, HER2, GATA3). LASSO regression identified key features, followed by model development using nine machine learning algorithms, including XGBoost and LightGBM. Model performance was assessed via area under the ROC curve (AUC), and Shapley Additive Explanations (SHAP) were used for model interpretability.

The random forest model achieved the highest predictive performance (AUC = 0.92 in training; 0.74 in testing). SHAP analysis identified vascular invasion, perineural invasion, and PD-L1/HER2 expression as major contributors. Decision curve analysis showed favorable net benefit within a moderate-risk threshold.

A machine learning model integrating pathological, demographic, and molecular features demonstrates promising potential to predict response to adjuvant therapy post-RC in bladder cancer. Decreased performance in the external test cohort highlights the need for further validation. Prospective studies incorporating multi-center and longitudinal data are warranted to enhance model generalizability and clinical applicability.