Jennifer Nayor

Natural Language Processing Accurately Calculates Adenoma and Sessile Serrated Polyp Detection Rates

BackgroundADR is a widely used colonoscopy quality indicator. Calculation of ADR is labor-intensive and cumbersome using current electronic medical databases. Natural language processing (NLP) is a method used to extract meaning from unstructured or free text data.Aims(1) To develop and validate an accurate automated process for calculation of adenoma detection rate (ADR) and serrated polyp detection rate (SDR) on data stored in widely used electronic health record systems, specifically Epic electronic health record system, Provation® endoscopy reporting system, and Sunquest PowerPath pathology reporting system.MethodsScreening colonoscopies performed between June 2010 and August 2015 were identified using the Provation® reporting tool. An NLP pipeline was developed to identify adenomas and sessile serrated polyps (SSPs) on pathology reports corresponding to these colonoscopy reports. The pipeline was validated using a manual search. Precision, recall, and effectiveness of the natural language processing pipeline were calculated. ADR and SDR were then calculated.ResultsWe identified 8032 screening colonoscopies that were linked to 3821 pathology reports (47.6%). The NLP pipeline had an accuracy of 100% for adenomas and 100% for SSPs. Mean total ADR was 29.3% (range 14.7–53.3%); mean male ADR was 35.7% (range 19.7–62.9%); and mean female ADR was 24.9% (range 9.1–51.0%). Mean total SDR was 4.0% (0–9.6%).ConclusionsWe developed and validated an NLP pipeline that accurately and automatically calculates ADRs and SDRs using data stored in Epic, Provation® and Sunquest PowerPath. This NLP pipeline can be used to evaluate colonoscopy quality parameters at both individual and practice levels.

A Multicenter Study Into Causes of Severe Acute Liver Injury

&NA; The differential diagnosis of an increase in alanine aminotransferase (ALT) level and/or aspartate aminotransferase (AST) level of ≥1000 IU/L often is stated to include 3 main etiologies: ischemic hepatitis, acute viral hepatitis (typically hepatitis A and hepatitis B), and drug‐induced (more specifically, acetaminophen/paracetamol) liver injury (DILI).1 Unfortunately, there are a paucity of studies examining the most common causes of acute liver injury (ALI) and those that have been published have been small,2 single‐center,2 or examined less severe increases in ALT or AST levels.3,4 We conducted a multicenter study of all patients with an ALT and/or AST level ≥1000 IU/L. Our study had 3 main goals: (1) to determine the most common causes of an ALT and/or AST level ≥1000 IU/L, along with their relative frequencies; (2) to determine differences in etiology based on hospital type (liver transplant center, community hospital, Veterans Affairs hospital); and (3) to confirm or disprove the differential heuristic that ischemic hepatitis, acute viral hepatitis, and acetaminophen toxicity are the most common etiologies.

Appointment-keeping behaviors and procedure day are associated with colonoscopy attendance in a patient navigator population.

BACKGROUND Patient navigator programs (PNP) have been shown to improve colonoscopy completion with demonstrated cost-effectiveness. Despite additional resources available to these patients, many still do not attend their colonoscopies. The aim of this study was to determine factors associated with colonoscopy attendance amongst patients in whom logistical barriers to attendance have been minimized through enrollment in a PNP. METHODS Retrospective case-control study of patients enrolled in a PNP for colonoscopy performed at a tertiary endoscopy center from 2009 to 2014. Cases were defined as patients who did not attend their first scheduled colonoscopy after PNP enrollment. Age- and gender-matched controls completed their first scheduled colonoscopy after PNP enrollment. RESULTS 514 subjects (257 cases, mean age 57.1years, 36.6% males) were included. Patients who attended their colonoscopy were less likely to be Spanish-speaking (64.6% vs 78.2%, p=0.0003) and uninsured (0.4% vs 3.9%, p=0.006). Attendance rates were significantly lower for screening colonoscopies compared to an indication of surveillance or diagnostic (45.5% vs 65.3%, p<0.0001). Fewer patients attended colonoscopies scheduled on Monday (39.2% vs 52.1%, p=0.04) and in December (10.7% vs 52.3%, p<0.0001). On multivariate analysis, poor appointment-keeping behaviors, including a prior missed colonoscopy (OR 0.20, 95% CI 0.10-0.39) or missed office visit (OR 0.44, 95% CI 0.26-0.73) and procedures scheduled on Mondays (OR 0.51, 95% CI 0.27-0.94) were negatively associated with attendance. CONCLUSIONS Appointment-keeping behaviors, in addition to insurance-status, language-barriers and medical comorbidities, influence colonoscopy attendance in a PNP population. Patients scheduled for colonoscopies on Mondays or in December may require more resources to ensure attendance.

INTERACTIVE MEDICAL CASE. Tracing the Cause of Abdominal Pain.

This interactive feature involves the case of a 19-year-old woman who presented to the ED with abdominal pain that had been progressively worsening for the past 2 days. Test your diagnostic and therapeutic skills at NEJM.org.

Evaluation and Surveillance Strategies for Patients at Increased Risk of Pancreatic Cancer

Pancreatic adenocarcinoma is a leading cause of cancer death due to the typical late stage at diagnosis, which results in few patients being candidates for potentially curative treatment. Although most cases of pancreatic adenocarcinomas are sporadic, 5–10 % may have an underlying hereditary basis. Family history is central to identifying individuals who have an elevated risk of pancreatic cancer and for quantifying their risk. Familial pancreatic cancer is defined as kindred with at least two first-degree relatives with pancreatic cancer. Other genetic syndromes that are associated with an increased risk of pancreatic cancer include Peutz–Jeghers syndrome, familial atypical multiple mole melanoma, hereditary breast and ovarian cancer syndrome, Lynch syndrome, Li–Fraumeni syndrome, and hereditary pancreatitis.

253 Natural Language Processing Accurately Calculates Adenoma and Sessile Serrated Polyp Detection Rates

Background ADR is a widely used colonoscopy quality indicator. Calculation of ADR is labor-intensive and cumbersome using current electronic medical databases. Natural language processing (NLP) is a method used to extract meaning from unstructured or free text data.

Sa1056 Predictors of Colonoscopy Attendance in a Patient Navigator Program Population

noma. The survey was distributed electronically via the American College of Physicians (ACP) Research Centers Internal Medicine Insider Panel, a representative group of ACP members who have voluntarily agreed to participate in periodic physician surveys. Participants were excluded if they reported spending less than 25% of their time in primary care or reported not placing any referrals for screening colonoscopy. Results: Of 442 PCPs invited to participate, 210 responded (response rate = 210/442, or 48%), and 29 were excluded, yielding 181 completed surveys. The mean age was 53 years. 48% practiced in a small group practice, solo practice, or community health center, and only 9% practiced in an academic center. Nearly all (96%) were board certified, and 44% had a medical school affiliation. In a 60-year-old with a normal high-quality screening colonoscopy, 88% (159/ 181) correctly recommended repeat colonoscopy in 10 years. However, if an endoscopist recommended a shorter interval (5 years) in such a patient, 41% (65/159) reported that they would follow the endoscopists recommendation. For a 55-year-old with a 4 mm adenoma, 73% (133/181) correctly recommended a 5-10 year interval. However, if an endoscopist recommended a shorter interval (3 years) in such a patient, 62% (83/133) reported that they would follow the endoscopists recommendation. In multivariable analysis, PCPs who referred to larger GI practices, referred more patients for colonoscopy, and worked in non-academic settings, were significantly more likely to follow an early surveillance recommendation. Conclusions: An endoscopists recommendation for when to repeat a colonoscopy has a powerful impact on the decision-making of referring PCPs. In situations where a guideline-discordant interval is recommended, endoscopists should specify their clinical reasoning and/or indicate the strength of their recommendation.