Artificial Intelligence for Real-Time Prediction of the Histology of Colorectal Polyps by General Endoscopists.

BACKGROUND: Real-time prediction of histologic features of small colorectal polyps may prevent resection and/or pathologic evaluation and therefore decrease colonoscopy costs. Previous studies showed that computer-aided diagnosis (CADx) was highly accurate, though it did not outperform expert endoscopists. OBJECTIVE: To assess the diagnostic performance of histologic predictions by general endoscopists before and after assistance from CADx in a real-life setting. DESIGN: Prospective, multicenter, single-group study. (ClinicalTrials.gov: NCT04437615). SETTING: 6 centers across the United States. PARTICIPANTS: 1252 consecutive patients undergoing colonoscopy and 49 general endoscopists with variable experience in real-time prediction of polyp histologic features. INTERVENTION: Real-time use of CADx during routine colonoscopy. MEASUREMENTS: The primary end points were the sensitivity and specificity of CADx-unassisted and CADx-assisted histologic predictions for adenomas measuring 5 mm or less. For clinical purposes, additional estimates according to location and confidence level were provided. RESULTS: The CADx device made a diagnosis for 2695 polyps measuring 5 mm or less (96%) in 1252 patients. There was no difference in sensitivity between the unassisted and assisted groups (90.7% vs. 90.8%; P = 0.52). Specificity was higher in the CADx-assisted group (59.5% vs. 64.7%; P < 0.001). Among all 2695 polyps measuring 5 mm or less, 88.2% and 86.1% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be resected and discarded without pathologic evaluation. Among 743 rectosigmoid polyps measuring 5 mm or less, 49.5% and 47.9% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be left in situ without resection. LIMITATION: Decision making based on CADx might differ outside a clinical trial. CONCLUSION: CADx assistance did not result in increased sensitivity of optical diagnosis. Despite a slight increase, the specificity of CADx-assisted diagnosis remained suboptimal. PRIMARY FUNDING SOURCE: Olympus America Corporation served as the clinical study sponsor.

Treatment of functional bowel disorders in an integrative medicine clinic resulting in improved digestive tract symptoms.

Background and Aim: Functional bowel disorders (FBDs), including irritable bowel syndrome (IBS) and others, are conditions without a physically identifiable etiology that, as a result, are difficult to treat. Alternatives to traditional medical interventions are needed because IBS patients require more of physician time and higher healthcare spending. The goal of this study was to determine the efficacy of alternative lifestyle interventions for patients with FBDs seen in an integrative medicine (IM) clinic at an academic medical center. Methods: We performed a retrospective chart review to determine whether patients with FBDs had improvement in symptoms following predominantly nutrition-based IM interventions that included recommendations for dietary supplements and elimination diets. We measured symptoms before and after intervention (average time between measurements 8.75 months) using a medical symptoms questionnaire (MSQ) commonly used to quantify symptom change in IM clinics. Results: Digestive tract symptoms, as measured by the MSQ, improved significantly in patients (n = 57) with FBDs following IM intervention. The MSQ Digestive Tract subtotal for FBD patients decreased from 10.2 (SD, 5.4) to 7.2 (SD, 5.2) (P < 0.001) after IM intervention. Conclusions: Patients in an IM clinic had improved digestive tract symptoms scores following IM intervention. Because nutrition-based interventions were the primary intervention recommended by IM providers, primary care physicians and gastroenterologists may wish to consider referring FBD patients to registered dietitian-nutritionists (RDNs) skilled in implementing elimination diets.

Translating Molecular Biology Discoveries to Develop Targeted Cancer Interception in Barrett's Esophagus.

Esophageal adenocarcinoma (EAC) is a rapidly increasing lethal tumor. It commonly arises from a metaplastic segment known as Barrett's esophagus (BE), which delineates the at-risk population. Ample research has elucidated the pathogenesis of BE and its progression from metaplasia to invasive carcinoma; and multiple molecular pathways have been implicated in this process, presenting several points of cancer interception. Here, we explore the mechanisms of action of various agents, including proton pump inhibitors, non-steroidal anti-inflammatory drugs, metformin, and statins, and explain their roles in cancer interception. Data from the recent AspECT trial are discussed to determine how viable a multipronged approach to cancer chemoprevention would be. Further, novel concepts, such as the repurposing of chemotherapeutic drugs like dasatinib and the prevention of post-ablation BE recurrence using itraconazole, are discussed.

Preoperative Screening of Colorectal Cancers Is As Accurate As Postoperative Screening for Detection of Lynch Syndrome.

Lynch syndrome (LS) is the most common inherited colorectal cancer (CRC) syndrome with lifetime CRC risks of up to 70%.1 Conventionally, CRC specimens are screened for LS postoperatively but preoperative diagnosis of LS could impact decisions, such as the extent of resection and the need for additional risk-reducing surgeries for uterine and ovarian cancers. Few studies have addressed this issue2-5 and surveys indicate that most gastroenterologists are unsure that LS can be screened for preoperatively.6 We compared the yield of preoperative versus postoperative screening of LS by immunohistochemistry (IHC) and microsatellite instability (MSI) in unselected patients with newly diagnosed CRC who underwent testing under real-life laboratory conditions to mimic clinical practice.

Relating Stool Microbial Metabolite Levels, Inflammatory Markers and Dietary Behaviors to Screening Colonoscopy Findings in a Racially/Ethnically Diverse Patient Population.

Colorectal cancer (CRC) is the third leading cause of cancer death for both men and women in the United States, yet it is treatable and preventable. African Americans have higher incidence of CRC than other racial/ethnic groups, however, it is unclear whether this disparity is primarily due to environmental or biological factors. Short chain fatty acids (SCFAs) are metabolites produced by bacteria in the colon and are known to be inversely related to CRC progression. The aim of this study is to investigate how stool SCFA levels, markers of inflammation in stool and dietary intake relate to colonoscopy findings in a diverse patient population. Stool samples from forty-eight participants were analyzed for SCFA levels and inflammatory markers (lysozyme, secretory IgA, lactoferrin). Additionally, participants completed the National Cancer Institute's Diet History Questionnaire II (DHQ II) to report dietary intake over the past year. Subsequently, the majority of participants underwent screening colonoscopy. Our results showed that African Americans had higher total levels of SCFAs in stool than other racial/ethnic groups, significantly lower intake of non-starchy vegetables and similar inflammatory marker expression and colonoscopy outcomes, compared to others. This work is an initial exploration into the biological and clinical factors that may ultimately inform personalized screening approaches and clinical decision-making to improve colorectal cancer disparities for African Americans.

Effectiveness of focal vs. balloon radiofrequency ablation devices in the treatment of Barrett's esophagus.

BACKGROUND AND AIMS: The safety and efficacy of radiofrequency ablation (RFA) in treatment of Barrett's esophagus (BE)-associated dysplasia has been well established. The effectiveness of focal and balloon RFA devices has not been compared. Therefore, the aim of our study was to assess the effectiveness of focal and balloon RFA devices in the treatment of BE by calculating absolute and percentage change in BE length with RFA therapy by comparing pre- and post-treatment BE length. PATIENTS AND METHODS: This is a retrospective cross-sectional study of patients who underwent at least one treatment with either focal and/or balloon RFA devices who were identified from two tertiary centers. Patients' demographics, hiatal hernia, pre- and post-treatment BE length, prior use of endoscopic therapies and number of sessions were recorded. RESULTS: Sixty-one patients who had undergone 161 RFA treatment sessions met inclusion criteria. There was no significant difference in percentage change in BE length with greater number of RFA sessions. RFA with a focal device resulted in greater percentage reduction in BE length compared to the balloon system (73% vs. 39%, p < 0.01). After adjusting for initial BE length, pre-treatment BE length, hernia status, prior endoscopic mucosal resection (EMR), prior RFA, and prior EMR/RFA sessions, RFA with a focal device at each session remained an independent predictor for a significant reduction in BE extent as compared to the balloon system. CONCLUSION: The focal RFA device alone was more effective in treatment of BE compared to the balloon system, with a greater reduction in extent of BE. The focal RFA device for endoscopic eradication therapy of BE should be considered the preferred technique.

Implementation intentions and colorectal screening: a randomized trial in safety-net clinics.

CONTEXT: Low-income and racial/ethnic minority populations experience disproportionate colorectal cancer (CRC) burden and poorer survival. Novel behavioral strategies are needed to improve screening rates in these groups. BACKGROUND: The study aimed to test a theoretically based "implementation intentions" intervention for improving CRC screening among unscreened adults in urban safety-net clinics. DESIGN: Randomized controlled trial. SETTING/PARTICIPANTS: Adults (N=470) aged ≥50 years, due for CRC screening, from urban safety-net clinics were recruited. INTERVENTION: The intervention (conducted in 2009-2011) was delivered via touchscreen computers that tailored informational messages to decisional stage and screening barriers. The computer then randomized participants to generic health information on diet and exercise (Comparison group) or "implementation intentions" questions and planning (Experimental group) specific to the CRC screening test chosen (fecal immunochemical test or colonoscopy). MAIN OUTCOME MEASURES: The primary study outcome was completion of CRC screening at 26 weeks based on test reports (analysis conducted in 2012-2013). RESULTS: The study population had a mean age of 57 years and was 42% non-Hispanic African American, 28% non-Hispanic white, and 27% Hispanic. Those receiving the implementation intentions-based intervention had higher odds (AOR=1.83, 95% CI=1.23, 2.73) of completing CRC screening than the Comparison group. Those with higher self-efficacy for screening (AOR=1.57, 95% CI=1.03, 2.39), history of asthma (AOR=2.20, 95% CI=1.26, 3.84), no history of diabetes (AOR=1.86, 95% CI=1.21, 2.86), and reporting they had never heard that "cutting on cancer" makes it spread (AOR=1.78, 95% CI=1.16, 2.72) were more likely to complete CRC screening. CONCLUSIONS: The results of this study suggest that programs incorporating an implementation intentions approach can contribute to successful completion of CRC screening even among very low-income and diverse primary care populations. Future initiatives to reduce CRC incidence and mortality disparities may be able to employ implementation intentions in large-scale efforts to encourage screening and prevention behaviors.

Impact of a computer-based teaching module on characterization of diminutive colon polyps by using narrow-band imaging by non-experts in academic and community practice: a video-based study.

BACKGROUND: Experts can accurately characterize the histology of diminutive polyps with narrow-band imaging (NBI). There are limited data on the performance of non-experts. OBJECTIVE: To assess the impact of a computer-based teaching module on the accuracy of predicting polyp histology with NBI by non-experts (in academics and community practice) by using video clips. DESIGN: Prospective, observational study. SETTING: Academic and community practice. PARTICIPANTS: A total of 15 gastroenterologists participated-5 experts in NBI, 5 non-experts in academic practice, and 5 non-experts in community practice. INTERVENTION: Participants reviewed a 20-minute, computer-based teaching module outlining the different NBI features for hyperplastic and adenomatous polyps. MAIN OUTCOME MEASUREMENTS: Performance characteristics in characterizing the histology of diminutive polyps with NBI by using short video clips before (pretest) and after (posttest) reviewing the teaching module. RESULTS: Non-experts in academic practice showed a significant improvement in the sensitivity (54% vs 79%; P < .001), accuracy (64% vs 81%; P < .001), and proportion of high-confidence diagnoses (49% vs 69%; P < .001) in the posttest. Non-experts in community practice had significantly higher sensitivity (58% vs 75%; P = .004), specificity (76% vs 90%; P = .04), accuracy (64% vs 81%; P < .001), and proportion of high-confidence diagnoses (49% vs 72%; P < .001) in the posttest. Performance of experts in NBI was significantly better than non-experts in both academic and community practice. LIMITATIONS: Selection bias in selecting good quality videos. Performance not assessed during live colonoscopy. CONCLUSION: Academic and community gastroenterologists without prior experience in NBI can achieve significant improvements in characterizing diminutive polyp histology after a brief computer-based training. The durability of these results and applicability in everyday practice are uncertain.

Are endoscopic ultrasonography imaging characteristics reliable for the diagnosis of small upper gastrointestinal subepithelial lesions?

PURPOSE OF THE STUDY: To compare the accuracy of endoscopic ultrasonography (EUS) imaging with histopathology in the diagnosis of upper gastrointestinal subepithelial lesions. METHODS: Thirty-seven patients (21 female; mean age: 55 y) underwent endoscopic submucosal resection (ESMR) of upper gastro intestinal subepithelial lesions at a tertiary care facility. All patients underwent EUS before ESMR of the lesion. Information regarding location, size, echogenecity, layer of origin, presumptive diagnosis based on EUS imaging, and histopathology diagnosis after ESMR of the subepithelial lesion was recorded. RESULTS: Twenty-seven subepithelial lesions were resected from the stomach, 5 from the esophagus, and 5 from the duodenum. The mean size of the lesions was 9 mm (range, 6-18 mm). Thirty-six lesions originated from the submucosa, and 1 from the muscularis propria. Using histopathology as the gold standard, the overall diagnostic accuracy of EUS imaging was 49% (18 out of 37). The accuracy of EUS imaging for the diagnosis of esophageal, gastric, and duodenal subepithelial lesions was 20%, 56%, and 40%, respectively. One patient developed a microperforation, and 1 developed bleeding during the ESMR procedure. No complications were reported with the EUS procedure. CONCLUSIONS: The diagnostic accuracy of EUS imaging is inferior to histopathology in the diagnosis of small upper gastrointestinal subepithelial lesions. Endoluminal resection is a relatively safe and noninvasive modality that not only provides tissue sample for accurate diagnostic interpretation, but also aids in the complete removal of small subepithelial lesions of the upper gastrointestinal tract.

Defining patients at high risk for gastrointestinal hemorrhage after drug-eluting stent placement: a cost utility analysis.

INTRODUCTION: The study goal was to evaluate the cost-effectiveness of drug-eluting stent (DES) placement with consideration of gastrointestinal (GI) bleeding risk. DES reduce the need for future coronary revascularization, but require prolonged dual anti-platelet (DAT) therapy, which may increase the risk for GI bleeding. While DES have been found to be cost-effective in patients at average risk for GI bleeding, they may not be the most cost-effective strategy in higher risk patients. METHODS: A Markov model was created to compare DES with bare metal stents (BMS). Patients were a hypothetical cohort of 60-year-old individuals with coronary artery stenosis that required nonemergent percutaneous coronary revascularization (PCI). The primary outcomes were the threshold incremental risks of GI bleeding from DAT based on willingness to pay (WTP) of $50,000, $100,000, and $150,000 per quality adjusted life year (QALY) gained. RESULTS: For a WTP of $100,000, the relative risk of GI bleeding from DAT could be as high as 10.8 (when compared to aspirin alone) before DES would no longer be cost-effective. In patients with two risk factors for GI bleeding, the threshold relative risk could be as low as 1.6. CONCLUSION: In average-risk patients, the risk of GI bleeding from DAT can be substantial without affecting the cost-effectiveness of DES. However, DES are unlikely to be cost-effective in patients with two or more risk factors for GI bleeding.

Treatment of Barrett's esophagus with high-grade dysplasia.

The incidence of esophageal adenocarcinoma is increasing in the USA, now accounting for at least 4% of US cancer-related deaths. Barrett's esophagus is the main risk factor for the development of esophageal adenocarcinoma. The annual incidence of development of adenocarcinoma in Barrett's esophagus is approximately 0.5% per year, representing at least a 30-40-fold increase in risk from the general population. High-grade dysplasia is known to be the most important risk factor for progression to adenocarcinoma. Traditionally, esophagectomy has been the standard treatment for Barrett's esophagus with high-grade dysplasia. This practice is supported by studies revealing unexpected adenocarcinoma in 29-50% of esophageal resection specimens for high-grade dysplasia. In addition, esophagectomy employed prior to tumor invasion of the muscularis mucosa results in 5-year survival rates in excess of 80%. Although esophagectomy can result in improved survival rates for early-stage cancer, it is accompanied by significant morbidity and mortality. Recently, more accurate methods of surveillance and advances in endoscopic therapies have allowed scientists and clinicians to develop treatment strategies with lower morbidity for high-grade dysplasia. Early data suggests that carefully selected patients with high-grade dysplasia can be managed safely with endoscopic therapy, with outcomes comparable to surgery, but with less morbidity. This is an especially attractive approach for patients that either cannot tolerate or decline surgical esophagectomy. For patients that are surgical candidates, high-volume centers have demonstrated improved morbidity and mortality rates for esophagectomy. The addition of laparoscopic esophagectomy adds a less invasive surgical resection to the treatment armanentarium. Esophagectomy will remain the gold-standard treatment of Barrett's esophagus with high-grade dysplasia until clinical research validates the role of endoscopic therapies. Current treatment strategies for Barrett's esophagus with high-grade dysplasia will be reviewed.

Treatment of Gastroparesis.

Gastroparesis is a condition of impaired gastric motility that can be chronic and result in decreased quality of life and complete disability. Once the diagnosis of gastroparesis is established, the clinician's attention should immediately focus on restoring nutritional status, providing symptomatic relief from nausea and vomiting, and improving gastric motility. Combination therapy is the rule rather than the exception, and most patients require multiple prokinetic and antiemetic modalities for adequate symptom relief. Currently available medications are often inadequate to achieve therapeutic goals, and newer modalities, such as gastric electrical stimulation, which has been shown to decrease symptoms and improve quality of life, should be employed at a low threshold. Several novel therapeutic options are under investigation and may also become part of the routine treatment of gastroparesis.

Delayed gastric emptying in gastroesophageal reflux disease: reassessment with new methods and symptomatic correlations.

BACKGROUND: Previous studies have shown that patients with gastroesophageal reflux disease (GERD) have slower rates of gastric emptying than control subjects, but the prevalence has differed because of variations in methodology. The recent establishment of international control values for scintigraphic gastric emptying assessment makes standardization of this technique possible. It would also be useful to determine whether specific gastrointestinal symptoms predicted delayed gastric emptying in GERD. METHODS: Forty-nine patients (mean age, 42.9 years; range, 24-65 years; 35 women, 14 men) who were diagnosed with GERD in the previous 12 months were given a standardized 280-kcal 99Tc-labeled low fat meal (egg beater). Percentage of intragastric residual content was recorded at baseline and at hourly intervals for 240 minutes by scintigraphy. Patients were also asked about the presence of dyspepsia (bloating, postprandial discomfort or belching, or early satiety), dysphagia, or regurgitation. RESULTS: Sixteen patients (33%) had intragastric residual contents greater than the 95th percentile (>40%) at 120 minutes, and 13 (26%) had abnormal results at 240 minutes (>6%). Dyspepsia was present in all patients. Regurgitation and dysphagia were common (present in approximately 80% and 40% of patients, respectively) and the prevalence of these symptoms did not differ between patients with normal versus delayed gastric emptying. CONCLUSIONS: Using standardized techniques: 1) delayed gastric emptying is common in patients presenting with GERD at both 120 and 240 minutes after ingestion of a solid meal and 2) symptoms alone are not a useful predictor of this pathophysiology. Awareness of this subgroup of patients can be important in treatment strategies and long-term therapy.

The treatment of gastroparesis in the age of the gastric pacemaker: a review.

Gastroparesis is a chronic disabling condition of impaired gastric motility that results in decreased quality of life. Currently available medical therapy consists of prokinetic medication combined with antiemetic therapy, dietary modifications, and nutritional supplementation. Many patients continue to have a suboptimal clinical response despite maximal use of these modalities. Instead of surgery, which involves irreversible stomach-modifying procedures, gastric electrical stimulation (GES) with a high-frequency/low-energy stimulus was approved by the US Food and Drug Administration (FDA) and can now be used in this setting. This approach has been shown to decrease symptom frequency and severity, reduce hospitalizations and medical costs, and improve quality of life. Occurrence of complications with this device are uncommon (< 5% of patients). Preliminary studies of new gastric stimulators that restore gastric contractility are promising, but additional investigation is needed. This article reviews the pathophysiology and epidemiology of gastroparesis and the role of conventional medical therapies, and discusses GES therapy with respect to its mechanisms of action, appropriate application, results and benefits, and future directions.

In primary sclerosing cholangitis, gallbladder polyps are frequently malignant.

OBJECTIVE: The management of gallbladder polyps/masses in patients with primary sclerosing cholangitis (PSC) (i.e., cholecystectomy vs observation) remains problematic. Given the risk of biliary tract cancer in PSC in the face of the benign nature of most gallbladder polyps in the general population, our aim was to determine the prevalence of gallbladder cancer in PSC patients with a gallbladder mass who had undergone cholecystectomy. METHODS: The case records of all patients with PSC undergoing a cholecystectomy at the Mayo Clinic between 1977-1999 were reviewed. RESULTS: Of the 102 patients with PSC who underwent a cholecystectomy, 14 of 102 (13.7%) had a gallbladder mass. In the subset of patients with gallbladder masses, eight of 14 (57%) had adenocarcinomas (seven primary adenocarcinomas and one metastatic cholangiocarcinoma); the other six had benign masses (five adenomas and one cholesterol polyp). In those patients with benign masses, 33% had associated epithelial cell dysplasia; in patients with primary gallbladder cancers, 57% had associated dysplasia. The patients with primary gallbladder adenocarcinoma had a favorable outcome after cholecystectomy, with a 36-month survival of 66%. CONCLUSIONS: In conclusion, gallbladder neoplasms in PSC patients are malignant in approximately 40-60% of the cases. The presence of gallbladder epithelial cell dysplasia suggests a dysplasia-carcinoma sequence in PSC similar to that observed in ulcerative colitis. Consideration should be given to performing a cholecystectomy in PSC patients with gallbladder polyps. If a cholecystectomy is not performed, careful interval follow-up is warranted.