Computer-Assisted Classification of the Squamocolumnar Junction.

Background And Aims: An irregular z-line is characterized by a squamocolumnar junction (SCJ) that extends proximally above the gastroesophageal junction (GEJ) by < 1 centimeter (cm), while Barrett's esophagus (BE) is defined as a columnar lined esophagus (CLE) that extends proximally by ≥1 cm with the presence of specialized intestinal metaplasia (IM) on biopsy. Measurement of CLE is most accurate for lengths ≥1 cm, and as such, guidelines do not recommend biopsy of an irregular z-line when seen on endoscopy. However, a CLE is often estimated by visual inspection rather than direct measurement, making this characterization imprecise.

Optimizing Assessment of Contraction Reserve in Ineffective Esophageal Motility: A Study of Upright Multiple Rapid Swallows.

Background/aims: Multiple rapid swallows (MRS) is a provocative test during high-resolution esophageal manometry (HRM) to evaluate contraction reserve (CR). This study aims to determine the prevalence of CR in patients with ineffective esophageal motility (IEM) and MRS performed in the upright position, and to assess the ideal number of MRS sequences.

Methods: We enrolled adult patients diagnosed with IEM according to the Chicago classification version 4.

Defining methods to improve eSource site start-up practices.

Background: eSource software that transfers patient electronic health record data into a clinical trial electronic case report form holds promise for increasing data quality while reducing data collection, monitoring and source document verification costs. Integrating eSource into multicenter clinical trial start-up procedures could facilitate the use of eSource technologies in clinical trials.

Methods: We conducted a qualitative integrative analysis to identify eSource site start-up key steps, challenges that might occur in executing those steps, and potential solutions to those challenges.

Contextualized race and ethnicity annotations for clinical text from MIMIC-III.

Observational health research often relies on accurate and complete race and ethnicity (RE) patient information, such as characterizing cohorts, assessing quality/performance metrics of hospitals and health systems, and identifying health disparities. While the electronic health record contains structured data such as accessible patient-level RE data, it is often missing, inaccurate, or lacking granular details. Natural language processing models can be trained to identify RE in clinical text which can supplement missing RE data in clinical data repositories.