Search

Background: An accurate system for tracking of colonoscopy quality and surveillance intervals could improve the effectiveness and cost-effectiveness of colorectal cancer (CRC) screening and surveillance. The purpose of this study was to create and test such a system across multiple institutions utilizing natural language processing (NLP)., Methods: From 42,569 colonoscopies with pathology records from 13 centers, we randomly sampled 750 paired reports. We trained (n=250) and tested (n=500) an NLP-based program with 19 measurements that encompass colonoscopy quality measures and surveillance interval determination, using blinded, paired, annotated expert manual review as the reference standard. The remaining 41,819 nonannotated documents were processed through the NLP system without manual review to assess performance consistency. The primary outcome was system accuracy across the 19 measures., Results: A total of 176 (23.5%) documents with 252 (1.8%) discrepant content points resulted from paired annotation. Error rate within the 500 test documents was 31.2% for NLP and 25.4% for the paired annotators (P=0.001). At the content point level within the test set, the error rate was 3.5% for NLP and 1.9% for the paired annotators (P=0.04). When eight vaguely worded documents were removed, 125 of 492 (25.4%) were incorrect by NLP and 104 of 492 (21.1%) by the initial annotator (P=0.07). Rates of pathologic findings calculated from NLP were similar to those calculated by annotation for the majority of measurements. Test set accuracy was 99.6% for CRC, 95% for advanced adenoma, 94.6% for nonadvanced adenoma, 99.8% for advanced sessile serrated polyps, 99.2% for nonadvanced sessile serrated polyps, 96.8% for large hyperplastic polyps, and 96.0% for small hyperplastic polyps. Lesion location showed high accuracy (87.0-99.8%). Accuracy for number of adenomas was 92%., Conclusions: NLP can accurately report adenoma detection rate and the components for determining guideline-adherent colonoscopy surveillance intervals across multiple sites that utilize different methods for reporting colonoscopy findings.

Objectives: Our aim was to quantify the effect of provider adherence on the risk of NSAID-related upper gastrointestinal events (UGIE)., Methods: We identified from national pharmacy records veterans > or = 65 yr prescribed an NSAID, a coxib, or salicylate (>325 mg/day) at any Veterans Affairs (VA) facility (January 1, 2000 to December 31, 2002). Prescription fill data were linked in longitudinal fashion to VA inpatient, outpatient, and death files and merged with demographic, inpatient, outpatient, and provider data from Medicare. Each person-day of follow-up was assessed for exposure to NSAID alone, NSAID+proton pump inhibitor (PPI), coxib, or coxib+PPI. UGIE was defined using our published, validated algorithm. Unadjusted incidence density ratios were calculated for the 365 days following exposure. We assessed risk of UGIE using Cox proportional hazards models, while adjusting for demographics, UGIE risk factors, comorbidity, prescription channeling (i.e., propensity score), geographic location, and multiple time-dependent pharmacological covariates, including aspirin, steroids, anticoagulants, antiplatelets, statins, and selective serotonin reuptake inhibitors., Results: In our cohort of 481,980 (97.8% male, 85.3% white, mean age 73.9, standard deviation 5.6), a safer strategy was prescribed for 19.8%, and 2,753 UGIE occurred in 220,662 person-years of follow-up. When adjusted for prescription channeling, confounders, and effect modification-associated PPI, risk of UGIE was 1.8 (95% confidence interval [CI] 1.6-2.0) on NSAID alone, 1.8 (95% CI 1.5-2.0) on coxib alone, 1.1 (95% CI 0.7-4.6) on NSAID+PPI, and 1.1 (0.6-5.2) on coxib+PPI. When the analysis was adjusted for cumulative percent time spent on a PPI, risk of UGIE decreased from HR 3.0 (95% CI 2.6-3.7) when a PPI was prescribed 0-20% of the time to 1.1 (95% CI 1.0-1.3) when a PPI was prescribed 80-100% of the time., Conclusions: Provider adherence to safer NSAID prescribing strategies is associated with fewer UGIE among the elderly. An adherent strategy lowers, but does not eliminate, risk of an NSAID-related UGIE.

This case documents scintigraphically that gastric dysmotility associated with hypoadrenalism secondary to hypothalamic-pituitary dysfunction was reversed when the adrenal insufficiency was treated. The patient reported upon received almost immediate relief of symptoms after corticosteroid replacement therapy and improvement of gastric motility, as demonstrated by both liquid and solid phase 99mTc-labeled studies. This experience suggests that glucocorticoids are important permissive hormones for normal gastrointestinal motor function and may have a role in the pathophysiology of gastrointestinal tract disease.