Faculty Bibliography

Artificial intelligence (AI) has potential to significantly impact clinical research when it comes to research preparation and data interpretation. Development of AI tools that can help in performing literature searches, synthesizing and streamlining data collection and analysis, and formatting of study could make the clinical research process more efficient. Several of these tools have been developed and trialed and many more are being rapidly developed. This article highlights the AI applications in clinical research in gastroenterology including its impact on drug discovery and explores areas where further guidance is needed to supplement the current understanding and enhance its use.

Colorectal cancer screening plays a vital role in early detection and removal of precancerous adenomas, contributing to decreased mortality rates. Most polyps found during colonoscopies are small and unlikely to harbor advanced neoplasia or invasive cancer, leading to the development of "leave-in-situ" and "resect-and-discard" approaches. These strategies could lead to significant cost savings and efficiencies, but their implementation has been hampered by concerns around financial incentives, medical-legal risks, and local rules for tissue handling. This article reviews the potential of artificial intelligence to enhance the accuracy of polyp diagnosis through computer-aided diagnosis (CADx). While the adoption of CADx in optical biopsy has shown mixed results, it has the potential to significantly improve the management of colorectal polyps. Several studies reviewed in this article highlight the varied results of CADx in optical biopsy for colorectal polyps. Although artificial intelligence does not consistently outperform expert endoscopists, it has the potential to serve as a beneficial secondary reader, aiding in accurate optical diagnosis and increasing the confidence of the endoscopist. These studies indicate that although CADx holds great potential, it is yet to fully meet the performance thresholds necessary for clinical implementation.

Colorectal cancer (CRC) is the 2(nd) most common cancer in women and 3(rd) most common cancer in men worldwide. Most CRCs develop from adenomatous polyps arising from glandular epithelium. Tumor growth is initiated by mutation of the tumor suppressor gene APC and involves other genetic mutations in a stepwise process over years. Both hereditary and environmental factors contribute to the development of CRC. Screening has been proven to reduce the incidence of CRC. Screening has also contributed to the decrease in CRC mortality in the United States. However, CRC incidence and/or mortality remain on the rise in some parts of the world (Eastern Europe, Asia, and South America), likely due to factors including westernized diet, lifestyle, and lack of healthcare infrastructure. Multiple screening options are available, ranging from direct radiologic or endoscopic visualization tests that primarily detect premalignant or malignant lesions such as flexible sigmoidoscopy, optical colonoscopy, colon capsule endoscopy, computed tomographic colonography, and double contrast barium enema - to stool based tests which primarily detect cancers, including fecal DNA, fecal immunochemical test, and fecal occult blood test. The availability of some of these tests is limited to areas with high economic resources. This article will discuss CRC epidemiology, pathogenesis, risk factors, and screening modalities with a particular focus on new technologies.

BACKGROUND:Clostridium difficile infection (CDI) has recently markedly increased, incurring greater health care-associated costs and hospitalizations especially in vitamin D deficient patients. Accordingly, the aim of this study was to evaluate the relationship between low vitamin D levels and the severity and recurrence of CDI. METHODS:A retrospective case-control study evaluated patients hospitalized between 2007 and 2013 with CDI and a positive C. difficile toxin assay. Severe complicated CDI was defined based on (1) laboratory or radiological criteria correlated clinically and (2) sepsis requiring intensive care unit admission. Recurrent CDI (RCDI) was defined as a new episode of diarrhea occurring within 90 days of resolution of the initial episode for at least 10 days after discontinuing therapy and confirmed by positive stool C. difficile toxin assay or polymerase chain reaction. Patients were divided into 4 groups based on vitamin D level (ng/mL): severely deficient (<10), insufficient (10-19.9), predeficient (20-29.9), and control group (≥30). RESULTS:Two hundred seventy-one patients were diagnosed with CDI, of which 48 had RCDI distributed as 5 (12.5%), 15 (16.1%), 10 (15.6%), and 13 (17.5%) patients in each of the aforementioned groups, respectively (P=0.55). Severe complicated CDI was identified in 7 (17.5%), 17 (18.2%), 9 (14%), and 3 (4%) patients, respectively (P=0.04). Thirty-day mortality was 1 of 40, 1 of 93, 2 of 64, and 2 of 74 patients, respectively (P=0.43). CONCLUSIONS:Normal vitamin D level has a protective effect against severe CDI, and low vitamin D is associated with greater severity of CDI but not with an increased risk of RCDI or 30-day mortality.