Procedure volume influences adherence to celiac disease guidelines

Machine Learning Approaches for Measuring Neighborhood Environments in Epidemiologic Studies

Purpose of review

Innovations in information technology, initiatives by local governments to share administrative data, and growing inventories of data available from commercial data aggregators have immensely expanded the information available to describe neighborhood environments, supporting an approach to research we call Urban Health Informatics. This review evaluates the application of machine learning to this new wealth of data for studies of the effects of neighborhood environments on health.

Recent findings

Prominent machine learning applications in this field include automated image analysis of archived imagery such as Google Street View images, variable selection methods to identify neighborhood environment factors that predict health outcomes from large pools of exposure variables, and spatial interpolation methods to estimate neighborhood conditions across large geographic areas.

Summary

In each domain, we highlight successes and cautions in the application of machine learning, particularly highlighting legal issues in applying machine learning approaches to Google’s geo-spatial data.

The role of female endoscopists: are women gastroenterologists better at obtaining biopsies for celiac disease than men?

OBJECTIVES

Celiac disease (CD) is commonly found in women. Given the sex differences in diagnosed patients, we hypothesized sex differences in physicians obtaining biopsies for CD may exist.

MATERIALS AND METHODS

We retrospectively reviewed duodenal biopsies for suspected CD excluding pre-existing CD patients. Appropriate biopsy practice was defined as ≥5 specimens per ACG guidelines.

RESULTS

We included 125 patients (females, 92). There were 85 properly (68%) biopsied. Presence of a female endoscopist was associated with better adherence to biopsy guidelines (OR, 2.99, 95% CI, 1.19-7.54; p = .02) which remained significant after multivariable adjustment (adjusted OR, 2.7; p = .047).

CONCLUSIONS

Physician sex-based differences in biopsy patterns may exist.

Rates of Duodenal Biopsy During Upper Endoscopy Differ Widely Between Providers: Implications for Diagnosis of Celiac Disease

GOAL

The goal of this study is to determine factors associated with performance of duodenal biopsy during upper endoscopy.

BACKGROUND

Celiac disease (CD) prevalence approaches 1% in the United States and Europe, yet CD remains underdiagnosed, in part because of low rates of duodenal biopsy during upper endoscopy. We aimed to identify patient and provider factors associated with performance of duodenal biopsy during upper endoscopy.

STUDY

In our hospital-based endoscopy suite, we identified all patients not previously diagnosed with CD who underwent upper endoscopy during a 5-year period for one of the following indications: abdominal pain/dyspepsia, gastroesophageal reflux (GERD), anemia/iron deficiency, diarrhea, and weight loss. We employed univariate and multivariate analysis to determine the association between clinical factors and the performance of duodenal biopsy.

RESULTS

Of 8572 patients included in the study, 4863 (57%) underwent duodenal biopsy. Of those who underwent duodenal biopsy, 24 (0.49%) were found to have CD. On multivariate analysis, age, gender, indication, gross endoscopic appearance, physician affiliation with a celiac disease center, and absence of a participating trainee were all significantly associated with the performance of duodenal biopsy. There was wide variability among providers, with duodenal biopsy rates ranging from 27% to 91% during these procedures.

CONCLUSIONS

A duodenal biopsy is more likely to be performed in younger patients, females, and for key indications such as weight loss, diarrhea, and anemia. Providers varied widely in the performance of duodenal biopsy. Further study is warranted to better understand the decision to perform duodenal biopsy and to determine the optimal scenarios for its performance.

Adherence to Endoscopy Biopsy Guidelines for Celiac Disease

OBJECTIVE

Histologic changes in celiac disease (CD) may be patchy or confined to the bulb. Present guidelines recommend obtaining multiple biopsies from the bulb and distal duodenum when evaluating for CD. Adherence to these recommendations among adult gastroenterologists is low. There are no such data for pediatric gastroenterologists. This study compared endoscopic biopsy practices among pediatric gastroenterologists in histologically confirmed patients with CD to those without histologically confirmed CD.

METHODS

Retrospective review of esophagogastroduodenoscopies (EGDs) during a 13-month period was performed. Children with histologically confirmed CD and a random sample of age-matched children without CD were identified. Endoscopy and histology reports were reviewed. The site and number of biopsy samples obtained was recorded. The groups were compared for number of biopsies.

RESULTS

A total of 98 children with CD were compared with 103 controls without CD. The number of biopsies obtained in the group with CD was higher than the group without CD (5.9 ± 1.6 vs 3.6 ± 1.2) (P < 0.0001). In children with CD, 80.5% had ≥5 biopsies compared with 11.7% in the group without CD (P < 0.0001). Only 10% of the children in the group with CD had bulb biopsies documented compared with none in the group without CD.

CONCLUSIONS

Pediatric gastroenterologists at our center generally obtain the recommended number of biopsies in children with histologically confirmed CD but seldom document biopsies from the bulb. In those without histologic evidence of CD, fewer biopsies are obtained with none documented from the bulb. Failure to take the recommended number of biopsies could result in some missed cases of CD.

Narrow band imaging combined with water immersion technique in the diagnosis of celiac disease

BACKGROUND

The "multiple-biopsy" approach both in duodenum and bulb is the best strategy to confirm the diagnosis of celiac disease; however, this increases the invasiveness of the procedure itself and is time-consuming.

AIM

To evaluate the diagnostic yield of a single biopsy guided by narrow-band imaging combined with water immersion technique in paediatric patients.

METHODS

Prospective assessment of the diagnostic accuracy of narrow-band imaging/water immersion technique-driven biopsy approach versus standard protocol in suspected celiac disease.

RESULTS

The experimental approach correctly diagnosed 35/40 children with celiac disease, with an overall diagnostic sensitivity of 87.5% (95% CI: 77.3-97.7). An altered pattern of narrow-band imaging/water immersion technique endoscopic visualization was significantly associated with villous atrophy at guided biopsy (Spearman Rho 0.637, p<0.001). Concordance of narrow-band imaging/water immersion technique endoscopic assessments was high between two operators (K: 0.884). The experimental protocol was highly timesaving compared to the standard protocol.

CONCLUSIONS

An altered narrow-band imaging/water immersion technique pattern coupled with high anti-transglutaminase antibodies could allow a single guided biopsy to diagnose celiac disease. When no altered mucosal pattern is visible even by narrow-band imaging/water immersion technique, multiple bulbar and duodenal biopsies should be obtained.