Search

Introduction: Reduction of opioids is an important goal in the care of patients undergoing radical cystectomy (RC). Liposomal bupivacaine (LB) has been shown to be a safe and effective pain reliever in the immediate postoperative period and has been reported to reduce postoperative opioid requirements. Since the liposomal formulation is predicated on slow systemic absorption, the amount of bupivacaine administered is notably higher than that typically used with standard bupivacaine (SB) formulations. In addition, LB is costly, not universally available, and studies comparing this formulation to SB are lacking. We sought to determine if there is a difference in postoperative opioid requirements in patients who receive LB vs. high dose SB at the time of RC.Methods: In May 2019 we transitioned to administration of high-volume SB injected intraoperatively at the time of RC. This prospective cohort was compared to a historical cohort of patients who received injection of LB at the time of surgery. Primary endpoints included postsurgical opioid use measured in morphine equivalent dose (MED) and patient-reported Numeric Rating Scale (NRS) pain scores and length of stay. All patients were managed using principles of enhanced recovery after surgery (ERAS).Results: From May 2019 through August 2019, 28 patients underwent RC and met eligibility criteria to receive SB at the time of surgery. They were compared to a historical cohort of 34 patients who received LB between November 2017 and July 2018. There was no difference in MED exposure either in the postanesthesia care unit (SB 9.0 ± 8.9 MED vs. LB 6.5 ± 9.4 MED, P= 0.29) or during the remainder of the hospital stay (SB 36.8 ± 56.9 MED vs. LB 42.1 ± 102.5 MED, P= 0.81), no difference in NRS pain scores on postoperative day 1 (SB 2.6 ± 1.6 vs. LB 2.1 ± 1.7, P= 0.23), day 2 (SB 2.4 ± 1.8 vs. LB 1.9 ± 1.6, P= 0.19), or day 3 (SB 1.9 ± 1.8 vs. LB 1.7 ± 1.7, P= 0.69) and no difference in length of stay (SB 5.0 ± 1.7 days, LB 4.9 ± 3.3 days, P= 0.93). Subgroup analysis of open RC and robotic-assisted RC showed no significant difference in MED or pain scores between LB and SB patients.Conclusions: Among patients undergoing RC under ERAS protocol there was no significant difference in postoperative opioid consumption, NRS pain scores, or length of stay among patients receiving SB compared to LB. [ABSTRACT FROM AUTHOR]

Purpose: When exploring survival outcomes for patients with bladder cancer, most studies rely on conventional statistical methods such as proportional hazards models. Given the successful application of machine learning to handle big data in many disciplines outside of medicine, we sought to determine if machine learning could be used to improve our ability to predict survival in bladder cancer patients. We compare the performance of artificial neural networks (ANN), a type of machine learning algorithm, with that of multivariable Cox proportional hazards (CPH) models in the prediction of 5-year disease-specific survival (DSS) and overall survival (OS) in patients with bladder cancer.Subjects and Methods: The National Cancer Institute's Surveillance, Epidemiology, and End Results (SEER) 18 program database was queried to identify adult patients with bladder cancer diagnosed between 1995 and 2010, yielding 161,227 patients who met our inclusion criteria. ANNs were trained and tested on an 80/20 split of the dataset. Multivariable CPH models were developed in parallel. Variables used for prediction included age, sex, race, grade, SEER stage, tumor size, lymph node involvement, degree of extension, and surgery received. The primary outcomes were 5-year DSS and 5-year OS. Receiver operating characteristic curve analysis was conducted, and ANN models were tested for calibration.Results: The area under the curve for the ANN models was 0.81 for the OS model and 0.80 for the DSS model. Area under the curve for the CPH models was 0.70 for OS and 0.81 for DSS. The ANN OS model achieved a calibration slope of 1.03 and a calibration intercept of -0.04, while the ANN DSS model achieved a calibration slope of 0.99 and a calibration intercept of -0.04.Conclusions: Machine learning algorithms can improve our ability to predict bladder cancer prognosis. Compared to CPH models, ANNs predicted OS more accurately and DSS with similar accuracy. Given the inherent limitations of administrative datasets, machine learning may allow for optimal interpretation of the complex data they contain. [ABSTRACT FROM AUTHOR]