Long-term impact of artificial intelligence on colorectal adenoma detection in high-risk colonoscopy.

BACKGROUND: Improved adenoma detection rate (ADR) has been demonstrated with artificial intelligence (AI)-assisted colonoscopy. However, data on the real-world application of AI and its effect on colorectal cancer (CRC) screening outcomes is limited. AIM: To analyze the long-term impact of AI on a diverse at-risk patient population undergoing diagnostic colonoscopy for positive CRC screening tests or symptoms. METHODS: AI software (GI Genius, Medtronic) was implemented into the standard procedure protocol in November 2022. Data was collected on patient demographics, procedure indication, polyp size, location, and pathology. CRC screening outcomes were evaluated before and at different intervals after AI introduction with one year of follow-up. RESULTS: We evaluated 1008 colonoscopies (278 pre-AI, 255 early post-AI, 285 established post-AI, and 190 late post-AI). The ADR was 38.1% pre-AI, 42.0% early post-AI (P = 0.77), 40.0% established post-AI (P = 0.44), and 39.5% late post-AI (P = 0.77). There were no significant differences in polyp detection rate (PDR, baseline 59.7%), advanced ADR (baseline 16.2%), and non-neoplastic PDR (baseline 30.0%) before and after AI introduction. CONCLUSION: In patients with an increased pre-test probability of having an abnormal colonoscopy, the current generation of AI did not yield enhanced CRC screening metrics over high-quality colonoscopy. Although the potential of AI in colonoscopy is undisputed, current AI technology may not universally elevate screening metrics across all situations and patient populations. Future studies that analyze different AI systems across various patient populations are needed to determine the most effective role of AI in optimizing CRC screening in clinical practice.

Epidemiology and outcomes of non-alcoholic fatty liver disease in African Americans.

1_bxolhs28Kaltura.

Comparison of Guidelines for the Screening, Diagnosis, and Noninvasive Assessment of Nonalcoholic Fatty Liver Disease.

Background: Nonalcoholic fatty liver disease (NAFLD) is the most common cause of chronic liver disease worldwide. However, there is no clear consensus on optimal screening strategies and risk stratification. We conducted a systematic review of society guidelines to identify differences in recommendations regarding the screening, diagnosis, and assessment of NAFLD. Methods: We searched PubMed, Web of Science, and Embase databases from January 1, 2015, to August 2, 2022. Two researchers independently extracted information from the guidelines about screening strategies, risk stratification, use of noninvasive tests (NITs) to assess hepatic fibrosis, and indications for liver biopsy. Results: Twenty clinical practice guidelines and consensus statements were identified in our search. No guidelines recommended routine screening for NAFLD, while 14 guidelines recommended case finding in high-risk groups. Of the simple risk stratification models to assess for fibrosis, the fibrosis-4 score was the most frequently recommended, followed by the NAFLD fibrosis score. However, guidelines differed on which cutoffs to use and the interpretation of "high-risk" results. Conclusion: Multiple guidelines exist with varying recommendations on the benefits of screening and interpretation of NIT results. Despite their differences, all guidelines recognize the utility of NITs and recommend their incorporation into the clinical assessment of NAFLD.

Diffuse-Type Pancreatic Ductal Adenocarcinoma Mimicking Autoimmune Pancreatitis.

Pancreatic ductal adenocarcinoma (PDAC) classically presents as a solitary mass on cross-sectional imaging. Diffuse-type PDAC is an unusual variant that accounts for 1%-5% of PDACs. Owing to its rarity, there are no established radiographic or endosonographic definitions. We report a unique case of diffuse-type PDAC presenting with imaging findings of 2 distinct masses in the pancreatic head and tail and with endoscopic ultrasound findings of diffuse gland enlargement mimicking autoimmune pancreatitis. The case illustrates the importance of sampling several areas of the pancreas when diffuse enlargement is present on endoscopic ultrasound and multiple masses are seen on cross-sectional imaging.

Barriers to Lactulose Adherence in Patients with Cirrhosis and Hepatic Encephalopathy.

BACKGROUND: Hepatic encephalopathy (HE) is a major cause of mortality and morbidity in patients with cirrhosis. Lactulose non-adherence is one of the most frequently reported precipitants of hospital admission for HE. AIMS: We aimed to identify which factors contribute most to lactulose non-adherence and propose strategies to promote greater adherence and utilization of lactulose. METHODS: Participants in this study consisted of patients with cirrhosis who were taking lactulose for prevention of HE. Subjects were administered the Morisky Adherence Scale 8 (MAS-8) and a customized 16-question survey that assessed barriers to lactulose adherence. Results from the MAS-8 were used to stratify subjects into "adherent" and "non-adherent" groups. Survey responses were compared between groups. RESULTS: We enrolled 129 patients in our study, of whom 45 were categorized as "adherent and 72 were categorized as "non-adherent." Barriers to adherence included large volumes of lactulose, high frequency of dosing, difficulty remembering to take the medication, unpleasant taste, and medication side-effects. Most patients (97%) expressed understanding of the importance of lactulose, and 71% of patients felt that lactulose was working to manage their HE. Hospital admission rates for HE was higher in non-adherent patients, although this difference was not statistically significant. CONCLUSION: We identified several factors that contribute to lactulose non-adherence among patients treated for HE. Many of these factors are potentially modifiable. Patient and care-giver education are critical to assure adherence. Pharmacists and nurses are an essential but underutilized aspect of education regarding proper medication use.

Autoimmune Hepatitis-Like Syndrome Following COVID-19 Vaccination: A Systematic Review of the Literature.

OBJECTIVES: During the summer of 2021, case reports began to emerge documenting a small number of individuals who developed autoimmune hepatitis (AIH) following COVID-19 vaccination. These cases are rare and novel, and very little is known. In our systematic review, we analyzed every published case of AIH and reviewed their characteristic findings, treatment, and outcomes. METHODS: We searched PubMed, Embase, and Web of Science from December 1, 2019, to November 1, 2021. Two researchers independently extracted information from the articles about vaccine type, patient history, laboratory values, histology results, treatment regimens, and disease course. RESULTS: Thirty-two patients developed AIH-like syndromes after receiving a COVID-19 vaccine. Jaundice was the most frequently reported symptom (81%), and 19% of patients were initially asymptomatic and presented with elevated liver enzymes found during routine bloodwork. Mean alanine transaminase, aspartate transaminase, and total bilirubin were 1231 U/L, 921 U/L, and 14 mg/dL, respectively. Anti-nuclear antibody was positive in 56%, and anti-smooth muscle antibody in 28% of patients. Steroids were used in 75% of patients. Improvement or complete resolution was seen in 97% of patients. One patient died despite aggressive steroid treatment. CONCLUSION: COVID-19 vaccine-induced AIH is an uncommon association with just 32 documented cases in the literature. Clinicians should be vigilant for AIH in patients who present with liver injury following vaccination. These new findings should under not deter individuals from getting vaccinated, as the benefits of vaccination far outweigh the risks. Fortunately, COVID-19 vaccine-induced AIH appears amendable to corticosteroid therapy and appears to have a favorable outcome.

Outcomes and Healthcare Provider Perceptions of Real-Time Continuous Glucose Monitoring (rtCGM) in Patients With Diabetes and COVID-19 Admitted to the ICU.

OBJECTIVE: We assessed the clinical utility and accuracy of real-time continuous glucose monitoring (rtCGM) (Dexcom G6) in managing diabetes patients with severe COVID-19 infection following admission to the intensive care unit (ICU). METHODS: We present retrospective analysis of masked rtCGM in 30 patients with severe COVID-19. rtCGM was used during the first 24 hours for comparison with arterial-line point of care (POC) values, where clinicians utilized rtCGM data to adjust insulin therapy in patients if rtCGM values were within 20% of point-of-care (POC) values during the masked period. An investigator-developed survey was administered to assess nursing staff (n = 66) perceptions regarding the use of rtCGM in the ICU. RESULTS: rtCGM data were used to adjust insulin therapy in 30 patients. Discordance between rtCGM and POC glucose values were observed in 11 patients but the differences were not considered clinically significant. Mean sensor glucose decreased from 235.7 ± 42.1 mg/dL (13.1 ± 2.1 mmol/L) to 202.7 ± 37.6 mg/dL (11.1 ± 2.1 mmol/L) with rtCGM management. Improvements in mean sensor glucose were observed in 77% of patients (n = 23) with concomitant reductions in daily POC measurements in 50% of patients (n = 15) with rtCGM management. The majority (63%) of nurses reported that rtCGM was helpful for improving care for patients with diabetes patients during the COVID-19 pandemic, and 49% indicated that rtCGM reduced their use of personal protective equipment (PPE). CONCLUSIONS: Our findings provide a strong rationale to increase clinician awareness for the adoption and implementation of rtCGM systems in the ICU. Additional studies are needed to further understand the utility of rtCGM in critically ill patients and other clinical care settings.

Use of Continuous Glucose Monitoring to Assess Parenteral Nutrition-Induced Hyperglycemia in an Adult Patient With Severe COVID-19.

Many patients admitted to the intensive care unit (ICU) are acutely malnourished and often require aggressive and early nutrition support with parenteral nutrition (PN). However, PN-induced hyperglycemia is a predictor of hospital mortality and is associated with increased length of stay. Elevated blood glucose in hospitalized patients with coronavirus disease 2019 (COVID-19) is also associated with increased mortality. Real-time continuous glucose monitoring (rtCGM) is primarily used in the outpatient setting, but there is rapidly growing interest in its applicability to help treat dysglycemia in critically ill patients, especially during the ongoing COVID-19 pandemic. We assessed the use of rtCGM data (Dexcom G6) in a 58-year-old male admitted to the ICU for severe COVID-19 infection, who developed PN-induced hyperglycemia with markedly elevated total daily insulin requirements as high as 128 units. rtCGM was used to safely titrate insulin infusion and monitor glucose levels. No episodes of hypoglycemia were observed, despite an extremely aggressive insulin regimen. This case demonstrates the potential utility of rtCGM in the critical care setting and highlights its potential to help conserve personal protective equipment and minimize unnecessary staff exposure in the setting of COVID-19.

Continued In-Hospital Angiotensin-Converting Enzyme Inhibitor and Angiotensin II Receptor Blocker Use in Hypertensive COVID-19 Patients Is Associated With Positive Clinical Outcome.

BACKGROUND: This study investigated continued and discontinued use of angiotensin-converting enzyme inhibitors (ACEi) or angiotensin II receptor blockers (ARB) during hospitalization of 614 hypertensive laboratory-confirmed COVID-19 patients. METHODS: Demographics, comorbidities, vital signs, laboratory data, and ACEi/ARB usage were analyzed. To account for confounders, patients were substratified by whether they developed hypotension and acute kidney injury (AKI) during the index hospitalization. RESULTS: Mortality (22% vs 17%, P > .05) and intensive care unit (ICU) admission (26% vs 12%, P > .05) rates were not significantly different between non-ACEi/ARB and ACEi/ARB groups. However, patients who continued ACEi/ARBs in the hospital had a markedly lower ICU admission rate (12% vs 26%; P = .001; odds ratio [OR] = 0.347; 95% confidence interval [CI], .187-.643) and mortality rate (6% vs 28%; P = .001; OR = 0.215; 95% CI, .101-.455) compared to patients who discontinued ACEi/ARB. The odds ratio for mortality remained significantly lower after accounting for development of hypotension or AKI. CONCLUSIONS: These findings suggest that continued ACEi/ARB use in hypertensive COVID-19 patients yields better clinical outcomes.