Rebecca A. Gourevitch

Challenges in adapting existing clinical natural language processing systems to multiple, diverse health care settings

Objective Widespread application of clinical natural language processing (NLP) systems requires taking existing NLP systems and adapting them to diverse and heterogeneous settings. We describe the challenges faced and lessons learned in adapting an existing NLP system for measuring colonoscopy quality. Materials and Methods Colonoscopy and pathology reports from 4 settings during 2013-2015, varying by geographic location, practice type, compensation structure, and electronic health record. Results Though successful, adaptation required considerably more time and effort than anticipated. Typical NLP challenges in assembling corpora, diverse report structures, and idiosyncratic linguistic content were greatly magnified. Discussion Strategies for addressing adaptation challenges include assessing site-specific diversity, setting realistic timelines, leveraging local electronic health record expertise, and undertaking extensive iterative development. More research is needed on how to make it easier to adapt NLP systems to new clinical settings. Conclusions A key challenge in widespread application of NLP is adapting existing systems to new clinical settings.

Variation in Pathologist Classification of Colorectal Adenomas and Serrated Polyps

Objectives:Endoscopist quality measures such as adenoma detection rate (ADR) and serrated polyp detection rates (SPDRs) depend on pathologist classification of histology. Although variation in pathologic interpretation is recognized, we add to the literature by quantifying the impact of pathologic variability on endoscopist performance.Methods:We used natural language processing to abstract relevant data from colonoscopy and related pathology reports performed over 2 years at four clinical sites. We quantified each pathologist’s likelihood of classifying polyp specimens as adenomas or serrated polyps. We estimated the impact on endoscopists’ ADR and SPDR of sending their specimens to pathologists with higher or lower classification rates.Results:We observed 85,526 colonoscopies performed by 119 endoscopists; 50,453 had a polyp specimen, which were analyzed by 48 pathologists. There was greater variation across pathologists in classification of serrated polyps than in classification of adenomas. We estimate the endoscopist’s average SPDR would be 0.5% if all their specimens were analyzed by the pathologist in our sample with the lowest classification rate and 12.0% if all their specimens were analyzed by the pathologist with the highest classification rate. In contrast, the endoscopist’s average ADR would be 28.5% and 42.4% if their specimens were analyzed by the pathologist with lowest and highest classification rate, respectively.Conclusions:There is significant variation in pathologic interpretation, which more substantially affects endoscopist SPDR than ADR.

Endoscopist factors that influence serrated polyp detection: a multicenter study

BACKGROUND Serrated polyps are important colorectal cancer precursors that are variably detected during colonoscopy. We measured serrated polyp detection rate (SPDR) in a large, multicenter, cross-sectional study of colonoscopy quality to identify drivers of SPDR variation. METHODS Colonoscopy and pathology reports were collected for a 2-year period (10/2013-9/2015) from four sites across the United States. Data from reports, including size, location, and histology of polyps, were abstracted using a validated natural language processing algorithm. SPDR was defined as the proportion of colonoscopies with ≥ 1 serrated polyp (not including hyperplastic polyps). Multivariable logistic regression was performed to determine endoscopist characteristics associated with serrated polyp detection. RESULTS A total of 104 618 colonoscopies were performed by 201 endoscopists who varied with respect to specialty (86 % were gastroenterologists), sex (18 % female), years in practice (range 1 - 51), and number of colonoscopies performed during the study period (range 30 - 2654). The overall mean SPDR was 5.1 % (SD 3.8 %, range 0 - 18.8 %). In multivariable analysis, gastroenterology specialty training (odds ratio [OR] 1.89, 95 % confidence interval [CI] 1.33 - 2.70), fewer years in practice (≤ 9 years vs. ≥ 27 years: OR 1.52, 95 %CI 1.14 - 2.04)], and higher procedure volumes (highest vs. lowest quartile: OR 1.77, 95 %CI 1.27 - 2.46)] were independently associated with serrated polyp detection. CONCLUSIONS Gastroenterology specialization, more recent completion of training, and greater procedure volume are associated with serrated polyp detection. These findings imply that both repetition and training are likely to be important contributors to adequate detection of these important cancer precursors. Additional efforts to improve SPDR are needed.

Who Uses a Price Transparency Tool? Implications for Increasing Consumer Engagement:

Despite the recent proliferation of price transparency tools, consumer use and awareness of these tools is low. Better strategies to increase the use of price transparency tools are needed. To inform such efforts, we studied who is most likely to use a price transparency tool. We conducted a cross-sectional study of use of the Truven Treatment Cost Calculator among employees at 2 large companies for the 12 months following the introduction of the tool in 2011-2012. We examined frequency of sign-ons and used multivariate logistic regression to identify which demographic and health care factors were associated with greater use of the tool. Among the 70 408 families offered the tool, 7885 (11%) used it at least once and 854 (1%) used it at least 3 times in the study period. Greater use of the tool was associated with younger age, living in a higher income community, and having a higher deductible. Families with moderate annual out-of-pocket medical spending (

How do pregnant women use quality measures when choosing their obstetric provider

1000-

Insurance Churning Rates For Low-Income Adults Under Health Reform: Lower Than Expected But Still Harmful For Many

2779) were also more likely to use the tool. Consistent with prior work, we find use of this price transparency tool is low and not sustained over time. Employers and payers need to pursue strategies to increase interest in and engagement with health care price information, particularly among consumers with higher medical spending.

Physician Characteristics Associated with Higher Adenoma Detection Rate.

Abstract Background Given increased public reporting of the wide variation in hospital obstetric quality, we sought to understand how women incorporate quality measures into their selection of an obstetric hospital. Methods We surveyed 6141 women through Ovia Pregnancy, an application used by women to track their pregnancy. We used t tests and chi‐square tests to compare response patterns by age, parity, and risk status. Results Most respondents (73.2%) emphasized their choice of obstetrician/midwife over their choice of hospital. Over half of respondents (55.1%) did not believe that their choice of hospital would affect their likelihood of having a cesarean delivery. While most respondents (74.9%) understood that quality of care varied across hospitals, few prioritized reported hospital quality metrics. Younger women and nulliparous women were more likely to be unfamiliar with quality metrics. When offered a choice, only 43.6% of respondents reported that they would be willing to travel 20 additional miles farther from their home to deliver at a hospital with a 20 percentage point lower cesarean delivery rate. Discussion Womens lack of interest in available quality metrics is driven by differences in how women and clinicians/researchers conceptualize obstetric quality. Quality metrics are reported at the hospital level, but women care more about their choice of obstetrician and the quality of their outpatient prenatal care. Additionally, many women do not believe that a hospitals quality score influences the care they will receive. Presentations of hospital quality data should more clearly convey how hospital‐level characteristics can affect womens experiences, including the fact that their chosen obstetrician/midwife may not deliver their baby.