International journal of clinical research & trials最新文献

Background: Over the past 20 years, the advancement of artificial intelligence (AI) and deep learning (DL) has allowed for fast sorting and analysis of large sets of data. In the field of gastroenterology, colorectal screening procedures produces an abundance of data through video and imaging. With AI and DL, this information can be used to create systems where automatic polyp detection and characterization is possible. Convoluted Neural Networks (CNNs) have proven to be an effective way to increase polyp detection and ultimately adenoma detection rates. Different methods of polyp characterization of being hyperplastic vs. adenomatous or non-neoplastic vs. neoplastic has also been investigated showing promising results.

Findings: The rate of missed polyps on colonoscopy can be as high as 25%. At the beginning of the 2000s, hand-crafted machine learning (ML) algorithms were created and trained retrospectively on colonoscopy images and videos, achieving high sensitivity, specificity, and accuracy of over 90% in many of the studies. Over time, the advancement of DL and CNNs has allowed algorithms to be trained on non-medical images and applied retrospectively to colonoscopy videos and images with similar results. Within the past few years, these algorithms have been applied in real-time colonoscopies and has shown mixed results, one showing no difference while others showing increased polyp detection.Various methods of polyp characterization have also been investigated. Through AI, DL, and CNNs polyps can be identified has hyperplastic/adenomatous or non-neoplastic/neoplastic with high sensitivity, specificity, and accuracy. One of the research areas in polyp characterization is how to capture the polyp image. This paper looks at different modalities of characterizing polyps such as magnifying narrow band imaging (NBI), endocytoscopy, laser-induced florescent spectroscopy, auto-florescent endoscopy, and white-light endoscopy.

Conclusions: Overall, much progress has been made in automatic detection and characterization of polyps in real time. Barring ethical or mass adoption setbacks, it is inevitable that AI will be involved in the field of GI, especially in colorectal polyp detection and identification.

Sepsis is a commonly encountered diagnosis affecting nearly 1.7 million adults in the USA annually. According to Center for Disease Control (CDC), over 270,000 Americans die of sepsis each year and 1 in 3 hospital mortalities is attributed to sepsis. The Surviving Sepsis Campaign (SSC) Guidelines for management of severe sepsis and septic shock published in 2004 provide key elements in the treatment of sepsis that are organized into two bundles of care, the "resuscitation" and "management" bundles, including interventions to be accomplished within specified timeframes. In this quality improvement study, we implemented a sepsis intervention protocol (SIP) intended to increase adherence to 3-hour and 6-hour bundles, and to examine the impact on mortality of patients presenting with severe sepsis and septic shock in our emergency department. We analyzed data from our emergency department as reported to the New York State Department of Health (NYSDOH) from 2017Q2 to 2018Q2 (April 2017 -June 2018), the period prior to implementation of SIP, compared to data from 2018Q3 to 2019Q2 (July 2018 to June 2019) after implementation of SIP. The implementation of SIP resulted in increased3-hour and 6-hour bundle adherence and showed a clinically significant reduction of the mean pre-intervention hospital percent mortality of 40.3% to a mean post-intervention hospital percent mortality of 28.7%. A t-test analysis of the pre and post intervention mean hospital percent mortality revealed a reduction in mortality outcomes that was also statistically significant (p <0.05). Our study demonstrates that a well-designed and implemented SIP can increase bundle adherence and is highly effective in reducing mortality among high-risk population.

The prevalence of obesity and its related comorbidities continues to rise in the United States and worldwide. Insulin resistance, increased inflammation and oxidative stress are the major pathogenic mechanisms involved in obesity-associated co-morbid conditions. Major efforts to curb the rising tide of obesity, including lifestyle modifications, anti-obesity medications and surgical interventions have shown minimal success. Therefore, introducing new methods to combat obesity, diabetes and associated disorders are desperately needed. Stevia rebaudiana, a natural, non-caloric sweetener has generated significant interest in the scientific community due to its effects on glucose homeostasis, blood pressure and inflammation, all known consequences of obesity. In this review, we assess the effects of Stevia on these parameters in humans as well as in animal models, highlighting its potential role as an effective intervention for the major cardiovascular risk factors associated with obesity.

Echocardiography can be a useful tool to evaluate athlete's heart in various sports. In this scoping review, we discuss some of the structural and functional changes of the right ventricle across different echocardiographic modes and techniques among individuals engaging in extreme athletic activity. We highlight the role of imaging in the evaluation of athlete's heart and describe similarities and differences between echocardiographic and cardiac MRI features related to acute and chronic athletic activity. We will also review novel echocardiographic parameters including speckle tracking and strain/strain rate imaging. Overall, we aim to present common echocardiographic parameters in elite sports population in order to facilitate better interpretation of their interpretations that may not necessarily be a distinct digression from these common features.