Time to progression is the main predictor of survival in patients with high-risk nonmuscle invasive bladder cancer: Results from a machine learning-based analysis of a large multi-institutional database.

BACKGROUND: In patients affected by high-risk nonmuscle invasive bladder cancer (HR-NMIBC) progression to muscle invasive status is considered as the main indicator of local treatment failure. We aimed to investigate the effect of progression and time to progression on overall survival (OS) and to investigate their validity as surrogate endpoints. METHODS: A total of 1,510 patients from 18 different institutions treated for T1 high grade NMIBC, followed by a secondary transurethral resection and BCG intravesical instillation. We relied on random survival forest (RSF) to rank covariates based on OS prediction. Cox's regression models were used to quantify the effect of covariates on mortality. RESULTS: During a median follow-up of 49.0 months, 485 (32.1%) patients progressed to MIBC, while 163 (10.8%) patients died. The median time to progression was 82 (95%CI: 78.0-93.0) months. In RSF time-to-progression and age were the most predictive covariates of OS. The survival tree defined 5 groups of risk. In multivariable Cox's regression models accounting for progression status as time-dependent covariate, shorter time to progression (as continuous covariate) was associated with longer OS (HR: 9.0, 95%CI: 3.0-6.7; P < 0.001). Virtually same results after time to progression stratification (time to progression ≥10.5 months as reference). CONCLUSION: Time to progression is the main predictor of OS in patients with high risk NMIBC treated with BCG and might be considered a coprimary endpoint. In addition, models including time to progression could be considered for patients' stratification in clinical practice and at the time of clinical trials design.

A longitudinal study evaluating interim assessment of neoadjuvant chemotherapy for bladder cancer.

OBJECTIVES: To evaluate the usefulness of radiological re-staging after two and four cycles of neoadjuvant chemotherapy (NAC), the impact of re-staging on further patient management, and the correlation between clinical and final pathological tumour stage at radical cystectomy (RC). PATIENTS AND METHODS: We conducted a longitudinal, single-centre, cohort study of prospectively collected consecutive patients who underwent NAC and RC for urothelial muscle-invasive bladder cancer between July 2001 and December 2017. Patients underwent repeated computed tomography scans for re-staging after two cycles of NAC and after completion of NAC before RC. RESULTS: Of 180 patients, 110 had ≥four cycles of NAC and had complete imaging available. In the entire cohort, further patient management was only changed in 2/180 patients (1.1%) after two cycles of NAC based on radiological findings. Patients who were stable after two cycles but then downstaged after at least four cycles of NAC had a similarly lowered risk of death (hazard ratio [HR] 0.53). Only one patient downstaged after two cycles was subsequently upstaged after four cycles. Clinical downstaging was observed in 51 patients (46%), 55 patients (50%) had no change in clinical stage and four patients (3.6%) were clinically upstaged. Patients clinically downstaged after four cycles of NAC had a lower risk of death (HR 0.49, 95% confidence interval 0.25-0.94; P = 0.033) compared to those with no change or upstaged after completion of NAC. CONCLUSIONS: Re-staging of muscle-invasive bladder cancer after two cycles of NAC offers little additional information, rarely changes patient management, and may therefore be omitted, whereas re-staging after completion of NAC by CT is a strong predictor of overall survival.