Purpose:Evidence suggests that visceral fat quantity may be associated with post-prostatectomy outcomes and risk of prostate cancer related death. We evaluated whether increased fat volume, normali...

Purpose:Venous thromboembolic events (VTEs) are a major cause of morbidity following abdominopelvic oncologic surgery. Enoxaparin, a subcutaneous injectable low molecular weight heparin, is commonl...

Symptomatic urinary tract infection is a complication of office based cystourethroscopy. Studies are mixed regarding the efficacy of antibiotic prophylaxis to prevent urinary tract infections. Our aim was to develop and evaluate an evidence-based protocol that reduces unnecessary antibiotic use while avoiding an increase in urinary tract infections. We created a clinic antibiogram based on all urology office visits performed during a 2-year period. Bacterial resistance rates, institutional risk related data and clinical guidelines were applied to create a protocol for antibiotic administration before cystourethroscopy. We then analyzed 1,245 consecutive patients without a renal transplant who underwent outpatient cystourethroscopy, including 610 after protocol initiation. Urinary tract infection rates and antibiotic use were analyzed for an association with the protocol change using the Fisher exact test. Cultures had an overall 20% rate of resistance to fluoroquinolones, representing 40% of the cultures that grew Escherichia coli. Before the protocol change 602 of 635 patients (94.8%) received a preprocedural antibiotic compared to 426 of 610 (69.9%) after protocol initiation (p <0.01). A total of 19 patients (3.0%) had a symptomatic urinary tract infection prior to the protocol change while 16 (2.6%) had a urinary tract infection after the change (p = 0.69). Regarding resistance, fluoroquinolone resistant organisms grew in the cultures of 12 of 19 patients (63.2%) with a urinary tract infection before the protocol change compared to 5 of 16 (31.3%) with a urinary tract infection after the change. Recent antibiotic administration, hospitalization and chronic catheterization were associated with urinary tract infection in the entire cohort (all p ≤0.01). A local antibiogram with infection related risk data effectively risk stratifies patients before cystourethroscopy, decreasing the use of antibiotics without increasing the rate of symptomatic urinary tract infection.

Purpose: Risk stratification underlies system-wide efforts to promote the delivery of appropriate prostate cancer care. Although the elements of risk stratum are available in the electronic medical record, manual data collection is resource intensive. Therefore, we investigated the feasibility and accuracy of an automated data extraction method using natural language processing (NLP) to determine prostate cancer risk stratum. Methods: Manually collected clinical stage, biopsy Gleason score, and preoperative prostate-specific antigen (PSA) values from our prospective prostatectomy database were used to categorize patients as low, intermediate, or high risk by D’Amico risk classification. NLP algorithms were developed to automate the extraction of the same data points from the electronic medical record, and risk strata were recalculated. The ability of NLP to identify elements sufficient to calculate risk (recall) was calculated, and the accuracy of NLP was compared with that of manually collected data using the weighted Cohen’s κ statistic. Results: Of the 2,352 patients with available data who underwent prostatectomy from 2010 to 2014, NLP identified sufficient elements to calculate risk for 1,833 (recall, 78%). NLP had a 91% raw agreement with manual risk stratification (κ = 0.92; 95% CI, 0.90 to 0.93). The κ statistics for PSA, Gleason score, and clinical stage extraction by NLP were 0.86, 0.91, and 0.89, respectively; 91.9% of extracted PSA values were within ± 1.0 ng/mL of the manually collected PSA levels. Conclusion: NLP can achieve more than 90% accuracy on D’Amico risk stratification of localized prostate cancer, with adequate recall. This figure is comparable to other NLP tasks and illustrates the known tradeoff between recall and accuracy. Automating the collection of risk characteristics could be used to power real-time decision support tools and scale up quality measurement in cancer care.