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.

Nationwide estimate of emergency department visits in the United States related to caustic ingestion.

INTRODUCTION: Caustic ingestion, whether intentional or unintentional, may result in significant morbidity. Our aim was to provide an estimate of the incidence and outcomes of caustic ingestion among emergency department (ED) visits across the United States. METHODS: The Nationwide Emergency Department Sample (NEDS) is part of the family of databases developed for the Healthcare Cost and Utilization Project. We analyzed NEDS for the period 2010-2014. Adults (≥18 years of age) with a diagnosis of caustic ingestion were identified by ICD-9 codes. The weighted frequencies and proportions of caustic ingestion-related ED visits by demographic characteristics and disposition status were examined. A weighted multivariable logistic regression model was performed to examine factors associated with inpatient admission for caustic ingestion-related visits. RESULTS: From 2010 to 2014, there were 40,844 weighted adult ED visits related to caustic ingestion among 533.8 million visits (7.65/100,000, 95% CI 7.58/100,000-7.73/100,000), resulting in over $47 million in annual cost. Among ED visits related to caustic ingestion, 28% had comorbid mental and substance use disorders. Local and systemic complications were rare. There was significant regional, gender, and insurance variability in the decision as to perform endoscopy. Males, insured patients, patients domiciled in the Southeast region of the United States, and patients with mental or substance use disorders had significantly higher percentages of receiving endoscopic procedures. Overall, 6,664 (16.27%) visits resulted in admission to the same hospital and 1,063 (2.60%) visits resulted in transfer to another hospital or facility. The risk factors for admission were increasing in age, male gender, local or systemic complications related to caustic ingestion, and comorbid mental and substance use disorders. A total of 161 (0.39%) patients died related to caustic ingestion. CONCLUSION: Our results from NEDS provide national estimates on the incidence of caustic ingestions involving adults seen in US EDs. Further studies are needed to examine the standard management of caustic ingestion and investigate the factors causing variability of esophagogastroduodenoscopy performance and caustic ingestion care.

Emerging strategies for the treatment of gastroparesis.

Gastroparesis is a syndrome of delayed gastric emptying in the absence of mechanical obstruction. Symptoms can be debilitating, affect nutritional states, and significantly impact patients' quality of life. The management of these patients can prove quite difficult to many providers. This article will review the current management recommendations of gastroparesis, discuss investigational medications and interventions, and summarize future directions of therapies targeting the underlying disease process. Current therapies are subdivided into those improving gastric motility and those directly targeting symptoms. Non-pharmacologic interventions, including gastric stimulator implantation and intra-pyloric botulinum toxic injection are reviewed. A discussion of expert opinion in the field, a look into the future of gastroparesis management, and a key point summary conclude the article.

Comprehensive Health Enhancement Support System (CHESS) for people with HIV infection.

We investigated the utility and the pattern of use of the Comprehensive Health Enhancement Support System (CHESS), an Internet based consumer health informatics system for people living with HIV/AIDS. Eight patients utilized CHESS for 4 months. The total number of log-ins ranged between 1 and 93 (median 21), with a median of 4.6 per month (0.2-21.8). Discussions Group was the service most frequently accessed; the Referral Directory and Fat Assessment services were requested the least. The barriers to using CHESS were difficulty in using the laptop, being too busy, and the discussion group size being too small. Most participants agreed that CHESS was easy to use and helped them cope with and understand more about their disease. They also felt comfortable asking questions and felt more involved in their health care.