A Prognostic Index Derived From LASSO-Selected Preoperative Inflammation and Nutritional Markers for Non–Muscle-Invasive Bladder Cancer

Background

There is an urgent need to identify a robust predictor for BCG response in patients with non–muscle-invasive bladder cancer (NMIBC). We aimed to employ the Lasso regression model for the selection and construction of an index (BCGI) utilizing inflammation and nutrition indicators to predict the response to BCG therapy.

Methods

After acquiring the ethics approval, we searched the electric medical records in our institution and performed data screening. Then, we developed the BCGI using a Lasso regression model and subsequently evaluated its performance in both the train and internal test datasets through Kaplan-Meier survival curves and Cox regression analysis. Then, we also evaluated the prognostic value of BCGI alongside the EAU2021 model.

Results

The training dataset and internal test dataset contained 295 and 196 patients, respectively. Referring to the Lasso results, BCGI consisted of hemoglobin, albumin, and platelet count, which could significantly predict the recurrence of NMIBC patients who accepted BCG in train (P = .012) and test (P = .004) datasets. The BCGI also exhibited statistically prognostic value in no smoking history, World Health Organization high grade, and T1 subgroups, both in train and test datasets. In multivariable analysis, BCGI exhibited independent prognostic value in train (P = .012) and test (P = .012) datasets. Finally, we constructed a nomogram that consisted of smoking history, T stage, World Health Organization grade, tumor size, and BCGI. Then, BCGI demonstrated significant independent prognostic value in NMIBC patients treated with BCG, a result not observed with the EAU2021 score or classification.

Conclusion

Based on the results, we reasonably suggest that BCGI may be a useful predictor for NMIBC patients who accepted BCG. Furthermore, we have demonstrated the efficacy of constructing a prognostic index using clinical factors and a Lasso regression model, a versatile approach applicable to various medical conditions.