Anatomic and Advanced Adenoma Detection Rates as Quality Metrics Determined via Natural Language Processing

232 Background: Electronic health records (EHRs) are a widely adopted but underutilized source of data for systematic assessment of healthcare quality. Barriers for use of this data source include its vast complexity, lack of structure, and the lack of use of standardized vocabulary and terminology by clinicians. This project aims to develop generalizable algorithms to extract useful knowledge regarding prostate cancer quality metrics from EHRs. Methods: We used EHR ICD-9/10 codes to identify prostate cancer patients receiving care at our academic medical center. Patients were confirmed in the California Cancer Registry (CCR), which provided data on tumor characteristics, treatment data, treatment outcomes and survival. We focused on three potential pretreatment process quality measures, which included documentation within 6 months prior to initial treatment of prostate-specific antigen (PSA), digital rectal exam (DRE) performance, and Gleason score. Each quality metric was defined using target terms and concepts to extract from the EHRs. Terms were mapped to a standardized medical vocabulary or ontology, enabling us to represent the metric elements by a concept domain and its permissible values. The structured representation of the quality metric included rules that accounted for the temporal order of the metric components. Our algorithms used natural language processing for free text annotation and negation, to ensure terms such as ‘DRE deferred’ are appropriately categorized. Results: We identified 2,123 patients receiving prostate cancer treatment between 2008-2016, of whom 1413 (67%) were matched in the CCR. We compared accuracy of our data mining algorithm, a random sample of manual chart review, and the CCR. (See Table.) Conclusions: EHR systems can be used to assess and report quality metrics systematically, efficiently, and with high accuracy. The development of such systems can improve and reduce the burden of quality reporting and potentially reduce costs of measuring quality metrics through automation. [Table: see text]

Download Full-text

166 Natural Language Processing (NLP) As an Alternative to Manual Reporting of Colonoscopy Quality Metrics

Gastrointestinal Endoscopy ◽

10.1016/j.gie.2014.02.048 ◽

2014 ◽

Vol 79 (5) ◽

pp. AB116-AB117 ◽

Cited By ~ 2

Author(s):

Gottumukkala S. Raju ◽

William a. Ross ◽

Phillip Lum ◽

Patrick M. Lynch ◽

Rebecca S. Slack ◽

...

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Quality Metrics ◽

Colonoscopy Quality ◽

Manual Reporting

Download Full-text

Mo1974 Performing Against the Benchmark: Does Adenoma Detection Equally Reflect Proximal Serrated Polyp Detection in Individual Endoscopists? Analysis of a Large Single High Volume Center Using Natural Language Processing

Gastroenterology ◽

10.1016/s0016-5085(15)32583-x ◽

2015 ◽

Vol 148 (4) ◽

pp. S-755

Author(s):

Viral D. Patel ◽

William K. Thompson ◽

Vijay Anand ◽

Andrew J. Gawron ◽

Jay L. Goldstein ◽

...

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

High Volume ◽

Polyp Detection ◽

Serrated Polyp ◽

Adenoma Detection ◽

High Volume Center

Download Full-text

Endocuff-assisted colonoscopy is associated with a lower adenoma miss rate: a multicenter randomized tandem study

Endoscopy ◽

10.1055/s-0043-114412 ◽

2017 ◽

Vol 49 (11) ◽

pp. 1051-1060 ◽

Cited By ~ 18

Author(s):

Konstantinos Triantafyllou ◽

Dimitrios Polymeros ◽

Periklis Apostolopoulos ◽

Catarina Lopes Brandao ◽

Paraskevas Gkolfakis ◽

...

Keyword(s):

Proximal Colon ◽

Conventional Colonoscopy ◽

Advanced Adenoma ◽

Serious Adverse Events ◽

Colon Adenoma ◽

Detection Rates ◽

Index Procedure ◽

Adenoma Detection ◽

Adenoma Detection Rates ◽

Medical Design

Abstract Background and study aims The Endocuff (ARC Medical Design, Leeds, UK) is a device that, when mounted on the tip of an endoscope, may assist with inspection of a greater surface of the colonic mucosa by pulling backwards, flattening, and stretching the colonic folds as the endoscope is gradually withdrawn. We aimed to compare the adenoma miss rates of Endocuff-assisted colonoscopy with those of conventional colonoscopy. Patients and methods The included patients underwent same-day, back-to-back, (Endocuff-assisted colonoscopy as the index procedure followed by conventional colonoscopy or vice versa, randomly assigned 1:1) colonoscopies, performed by six endoscopists with documented adenoma detection rates > 35 %, in four tertiary endoscopy facilities. Results We randomized 200 patients (mean age 61.2 years [standard deviation 9.8]; 86.5 % colorectal cancer screening surveillance cases). Overall, there were seven incomplete examinations using Endocuff and one with conventional colonoscopy (P = 0.03). Times for endoscope insertion (5.0 minutes [0.8 – 21.0] vs. 5.0 minutes [1.0 – 16.0]; P = 0.49) and withdrawal (6.0 minutes [3.2 – 29.0] vs. 6.0 minutes [3.1 – 17.0]; P = 0.06) were similar for Endocuff-assisted and conventional colonoscopy. We detected one cancer and 195 adenomas; 84 in the proximal colon. Endocuff-assisted colonoscopy showed significantly lower overall and proximal colon adenoma miss rates compared with conventional colonoscopy (14.7 % [8.0 % – 21.0 %] vs. 38.4 % [28.1 % – 48.6 %] and 10.4 % [1.8 % – 19.1 %] vs. 38.9 % [23.0 % – 54.8 %], respectively). No difference between the two arms was shown regarding advanced adenoma miss rates, either overall or in the proximal colon. There were no serious adverse events related to the procedures. Conclusions In comparison with conventional colonoscopy, Endocuff-assisted colonoscopy has a significantly lower adenoma miss rate when performed by high-detector endoscopists. However, the incomplete colonoscopy rate with Endocuff is higher.ClinicalTrials.gov Identifier: NCT02340065.

Download Full-text