WBC Associates with Readmission Following Cystectomy

Population-based analysis of perioperative chemotherapy use, interventions requiring hospitalization and atheroembolic events among patients with non-metastatic muscle-invasive bladder cancer

Introduction

Utilization of neoadjuvant chemotherapy (NC) in muscle invasive bladder cancer (MIBC) is increasingly recognized as standard of care but trends of use in Ontario remain unknown. Currently, there remains knowledge gaps regarding the effects of perioperative chemotherapy on the rates of interventions requiring hospitalization (IRH) and atheroembolic events (ATEs).

Methods

We conducted a population‐based retrospective study within the province of Ontario over 16 years. Patients with non‐metastatic MIBC receiving surgery only or planned for perioperative chemotherapy were included. Primary outcomes included 2‐year IRH and ATE rates. Univariate/multivariate analysis was used to identify predictors associated with IRHs and ATEs. Cochrane‐Armitage was used to assess treatment trends over time.

Results

Our study included 3281 patients. RC alone occurred in 2030 (60.9%), NC in 974 (29.6%) and adjuvant chemotherapy in 8.4% (n = 277). A total of 490/974 (50.3%) patients whom initiated NC with RC intent failed to undergo RC. This improved to 20.5% by 2015 (p < 0.001). Use of NC increased by an absolute value of 33% (p < 0.001). Overall, 4.2% of patients experienced IRHs and 11.5% ATEs. On multivariate analysis, advanced age and Charlson index score (CI) were strong predictors of outcomes, not timing of perioperative chemotherapy (p < 0.05.)

Conclusion

A total of 29.6% of MIBC patients are planned for NC with 20.5% not progressing to their surgery. Use of NC has substantially increased over time. IRHs and ATEs remain stubbornly high at 4.2% and 11.5% respectively. Older age and higher CI scores are the strongest predictors of IRHs and ATEs (p < 0.05), not perioperative chemotherapy.

Different models for prediction of radical cystectomy postoperative complications and care pathways

Background:

Radical cystectomy for bladder cancer has one of the highest rates of morbidity among urologic surgery, but the ability to predict postoperative complications remains poor. Our study objective was to create machine learning models to predict complications and factors leading to extended length of hospital stay and discharge to a higher level of care after radical cystectomy.

Methods:

Using the American College of Surgeons National Surgical Quality Improvement Program, peri-operative adverse outcome variables for patients undergoing elective radical cystectomy for bladder cancer from 2005 to 2016 were extracted. Variables assessed include occurrence of minor, infectious, serious, or any adverse events, extended length of hospital stay, and discharge to higher-level care. To develop predictive models of radical cystectomy complications, we fit generalized additive model (GAM), least absolute shrinkage and selection operator (LASSO) logistic, neural network, and random forest models to training data using various candidate predictor variables. Each model was evaluated on the test data using receiver operating characteristic curves.

Results:

A total of 7557 patients were identified who met the inclusion criteria, and 2221 complications occurred. LASSO logistic models demonstrated the highest area under curve for predicting any complications (0.63), discharge to a higher level of care (0.75), extended length of stay (0.68), and infectious (0.62) adverse events. This was comparable with random forest in predicting minor (0.60) and serious (0.63) adverse events.

Conclusions:

Our models perform modestly in predicting radical cystectomy complications, highlighting both the complex cystectomy process and the limitations of large healthcare datasets. Identifying the most important variable leading to each type of adverse event may allow for further strategies to model cystectomy complications and target optimization of modifiable variables pre-operative to reduce postoperative adverse events.