Using Natural Language Processing to Automatically Identify Dysplasia in Pathology Reports for Patients With Barrett's Esophagus.

BACKGROUND & AIMS: Identifying dysplasia of Barrett's esophagus (BE) in the electronic medical record (EMR) requires manual abstraction of unstructured data. Natural language processing (NLP) creates structure to unstructured free text. We aimed to develop and validate an NLP algorithm to identify dysplasia in BE patients on histopathology reports with varying report formats in a large integrated EMR system. METHODS: We randomly selected 600 pathology reports for NLP development and 400 reports for validation from patients with suspected BE in the national Veterans Affairs databases. BE and dysplasia were verified by manual review of the pathology reports. We used NLP software (Clinical Language Annotation, Modeling, and Processing Toolkit; Melax Tech, Houston, TX) to develop an algorithm to identify dysplasia using findings. The algorithm performance characteristics were calculated as recall, precision, accuracy, and F-measure. RESULTS: In the development set of 600 patients, 457 patients had confirmed BE (60 with dysplasia). The NLP identified dysplasia with 98.0% accuracy, 91.7% recall, and 93.2% precision, with an F-measure of 92.4%. All 7 patients with confirmed high-grade dysplasia were classified by the algorithm as having dysplasia. Among the 400 patients in the validation cohort, 230 had confirmed BE (39 with dysplasia). Compared with manual review, the NLP algorithm identified dysplasia with 98.7% accuracy, 92.3% recall, and 100.0% precision, with an F-measure of 96.0%. CONCLUSIONS: NLP yielded a high degree of sensitivity and accuracy for identifying dysplasia from diverse types of pathology reports for patients with BE. The application of this algorithm would facilitate research and clinical care in an EMR system with text reports in large data repositories.

Effect of diabetes medications and glycemic control on risk of hepatocellular cancer in patients with nonalcoholic fatty liver disease.

BACKGROUND AND AIMS: In patients with NAFLD, those with type 2 diabetes mellitus (DM) have a high risk of progression to HCC. However, the determinants of HCC risk in these patients remain unclear. APPROACH AND RESULTS: We assembled a retrospective cohort of patients with NAFLD and DM diagnosed at 130 facilities in the Veterans Administration between 1/1/2004 and 12/31/2008. We followed patients from the date of NAFLD diagnosis to HCC, death, or 12/31/2018. We used landmark Cox proportional hazards models to determine the effects of anti-DM medications (metformin, insulin, sulfonylureas) and glycemic control (percent of follow-up time with hemoglobin A1c < 7%) on the risk of HCC while adjusting for demographics and other metabolic traits (hypertension, obesity, dyslipidemia). We identified 85,963 patients with NAFLD and DM. In total, 524 patients developed HCC during a mean of 10.3 years of follow-up. Most common treatments were metformin monotherapy (19.7%), metformin-sulfonylureas (19.6%), insulin (9.3%), and sulfonylureas monotherapy (13.6%). Compared with no medication, metformin was associated with 20% lower risk of HCC (HR, 0.80; 95% CI, 0.93-0.98). Insulin had no effect on HCC risk (HR, 1.02; 95% CI, 0.85-1.22; p = 0.85). Insulin in combination with other oral medications was associated with a 1.6 to 1.7-fold higher risk of HCC. Adequate glycemic control was associated with a 31% lower risk of HCC (HR, 0.69; 95% CI, 0.62-0.78). CONCLUSIONS: In this large cohort of patients with NAFLD and DM, use of metformin was associated with a reduced risk of HCC, whereas use of combination therapy was associated with increased risk. Glycemic control can serve as a biomarker for HCC risk stratification in patients with NAFLD and diabetes.

Risk of Hepatocellular Carcinoma in Patients with Various HFE Genotypes.

BACKGROUND AND AIMS: Hereditary hemochromatosis (HH) is associated with increased risk of hepatocellular carcinoma (HCC). However, HCC risk factors within this population and across various HFE genotypes remain unclear. METHODS: We conducted a retrospective cohort study of patients with ≥ 1 HFE genotype test in the Veterans Health Administration. We followed patients until HCC, death, or 6/30/19. We calculated incidence rates (IRs) and used Cox proportional hazards models to estimate HCC risk. In patients with type-1 HH genotypes (C282Y/C282Y or C282Y/H63D), we examined risk factors for HCC. RESULTS: We identified 5225 patients: 260 were C282Y/C282Y; 227 were C282Y/H63D; 436 were H63D heterozygous; 535 had other HFE mutations; 3767 without mutation. IR for C282Y/C282Y homozygotes (5.59/1000 PYs) and C282Y/H63D compound heterozygotes (4.12/1000 PYs) were significantly higher than controls (0.92/1000 PYs) with adjusted hazard ratio (adj HR), 95% CI 8.80, 4.17-18.54; and 5.25, 2.24-12.32, respectively. HCC risk was higher in H63D heterozygote than controls (adj HR = 2.82, 95% CI 1.21-6.58); cases were related to non-alcoholic fatty liver disease. Among patients with HH, age ≥ 65 (adj HR = 2.2, 95% CI 0.47-10.27), diabetes (adj HR 3.74, 95% CI 1.25-11.20) and high baseline aspartate-aminotransferase to platelet ratio-index (APRI, adj HR = 3.91, 95% CI 1.29-11.89) had higher risk. Among patients with high baseline ferritin, persistent ferritin > 250 ng/mL had higher risk. CONCLUSION: HCC risk was high in C282Y homozygous and C282Y/H63D patients. These HFE genotypes, older age, diabetes, high APRI/ferritin levels were associated with increased risk. While H63D heterozygous genotype was associated with HCC risk, this association might be due to metabolic factors.

Clinical Course and Outcomes of Patients with Nonalcoholic Fatty Liver Disease-Related Hepatocellular Cancer (NAFLD-HCC).

BACKGROUND & AIMS: Among etiologies for hepatocellular (HCC), nonalcoholic fatty liver disease (NAFLD) carries a high risk of competing non-cancer mortality. The effect of cancer and non-cancer factors on risk of death after NAFLD-HCC diagnosis remains unclear. We aimed to evaluate the role of non-cancer mortality with NAFLD-HCC. METHODS: Using a retrospective cohort of patients with NAFLD diagnosed at 130 facilities in the Veterans Administration, we identified patients with incident HCC diagnosed between January 1, 2005 and June 30, 2018. We determined cause of death as HCC-related, non-HCC liver-related, and non-liver-related after HCC diagnosis. We used Cox proportional hazards regression models to evaluate the effect of clinical factors on cause-specific mortality after NAFLD-HCC diagnosis. RESULTS: We identified 776 patients with incident HCC. Mean age at HCC diagnosis was 70.1 year, 22.2% had Barcelona Clinic Liver Cancer (BCLC) stage 0-A, and 67.0% had more than one comorbidity. 1- and 3-year mortality rates were 47.0% and 69.6%, respectively. Most deaths (72.2% at 3 years) were attributable to HCC. In HCC patients who received curative treatment, non-cancer mortality accounted for 40% of all deaths between 3 and 5 years after treatment. Poor performance status (ECOG 3/4, HR 5.03, 95% CI: 2.59-9.77) and older age (65-75, HR 1.94, 95% CI: 1.06-3.54) were strongly associated with non-cancer mortality. CONCLUSION: Although most patients with NAFLD-HCC die of HCC, non-cancer mortality represents a clinically meaningful competing event for patients receiving curative treatment, underscoring the importance of assessing and managing risk factors of non-cancer morbidity and mortality. TRIAL AND REGISTRATION: N/A.

Preparing for the NASH Epidemic: A Call to Action.

Nonalcoholic fatty liver disease (NAFLD) and nonalcoholic steatohepatitis (NASH) are common conditions with a rising burden. Yet there are significant management gaps between clinical guidelines and practice in patients with NAFLD and NASH. Further, there is no single global guiding strategy for the management of NAFLD and NASH. The American Gastroenterological Association, in collaboration with 7 professional associations, convened an international conference comprising 32 experts in gastroenterology, hepatology, endocrinology, and primary care providers from the United States, Europe, Asia, and Australia. Conference content was informed by the results of a national NASH Needs Assessment Survey. The participants reviewed and discussed published literature on global burden, screening, risk stratification, diagnosis, and management of individuals with NAFLD, including those with NASH. Participants identified promising approaches for clinical practice and prepared a comprehensive, unified strategy for primary care providers and relevant specialists encompassing the full spectrum of NAFLD/NASH care. They also identified specific high-yield targets for clinical research and called for a unified, international public health response to NAFLD and NASH.

Effect of Metabolic Traits on the Risk of Cirrhosis and Hepatocellular Cancer in Nonalcoholic Fatty Liver Disease.

BACKGROUND AND AIMS: Nonalcoholic fatty liver disease (NAFLD) is now the most common liver condition. Predicting its progression could help clinicians manage and potentially prevent complications. We evaluated the independent and joint effects of metabolic traits on the risk of cirrhosis and hepatocellular carcinoma (HCC) among patients with NAFLD. APPROACH AND RESULTS: We assembled a retrospective cohort of patients with NAFLD diagnosed at 130 facilities in the Veterans Administration between January 1, 2004, and December 31, 2008, with follow-up through December 31, 2015. We performed competing risk-adjusted cause-specific Cox models to evaluate the effects of metabolic traits (diabetes, hypertension, dyslipidemia, obesity) as additive or combined indicators on time to develop cirrhosis or HCC or a composite endpoint of both. Of the 271,906 patients, 22,794 developed cirrhosis, and 253 developed HCC during a mean of 9 years follow-up. At baseline, the mean body mass index was 31.6 (SD, 5.6), 28.7% had diabetes, 70.3% had hypertension, and 62.3% had dyslipidemia with substantial overlap among these traits. The risk of progression was the lowest in patients with only one or no metabolic trait. There was a stepwise increase in risk with each additional metabolic trait. Compared with patients with no metabolic trait, patients with both hypertension and dyslipidemia had 1.8-fold higher risk of progression to cirrhosis/HCC (hazard ratio [HR] = 1.8, 95% confidence interval [CI] = 1.59-2.06); the risk was 2.6-fold higher in patients with diabetes, obesity, dyslipidemia, and hypertension (HR = 2.6, 95% CI = 2.3-2.9). These associations were stronger for HCC. Diabetes had the strongest association with HCC in this cohort. CONCLUSIONS: Each additional metabolic trait increased the risk of cirrhosis and HCC in patients with NAFLD. Diabetes conferred the highest risk of progression to HCC. Patients with diabetes and coexisting hypertension and obesity may be important targets for secondary prevention.

Risk of Cirrhosis and Hepatocellular Cancer in Patients With NAFLD and Normal Liver Enzymes.

BACKGROUND AND AIMS: The long-term risk of disease for patients with nonalcoholic fatty liver disease (NAFLD) in the absence of elevated enzymes is unclear. We conducted a retrospective cohort study using the Corporate Data Warehouse of the Veterans Health Administration. APPROACH AND RESULTS: We classified patients into three groups: patients with steatosis/normal alanine aminotransferase (ALT), steatosis/elevated ALT, and no steatosis/normal ALT. We examined incidence rates for cirrhosis and hepatocellular carcinoma (HCC) and conducted cause-specific hazard models to evaluate the risk of cirrhosis and HCC. We identified 3,522 patients with steatosis/normal ALT, 15,419 patients with steatosis/elevated ALT, and 9,267 patients with no steatosis/normal ALT. The mean age in each group was 58.9, 54.7 and 59.3 years, respectively; over 90% were men. Compared to patients with hepatic steatosis/normal ALT, those with steatosis/elevated ALT were younger and more likely to be obese (both P < 0.01). In patients with steatosis/normal ALT, the incidence rates of cirrhosis and HCC were 1.22 (95% confidence interval [CI]: 0.83-1.74) and 0.20 (95% CI: 0.06-0.46) per 1,000 person-years, respectively; this was lower than in patients with steatosis/elevated ALT (cirrhosis: 3.85; 95% CI: 3.50-4.23, and HCC: 0.37; 95% CI: 0.26-0.49). Patients with steatosis/elevated ALT had a higher risk of developing cirrhosis (adjusted hazard ratio: 3.37; 95% CI:  2.34-4.86; P < 0.01) than patients with steatosis/normal ALT; they also had a higher risk of HCC, although it did not reach statistical significance (hazard ratio: 2.07; 95% CI: 0.82-5.28; P = 0.13). The risk of cirrhosis and HCC in patients with steatosis/normal ALT and those without steatosis was not significantly different. CONCLUSIONS: Patients with hepatic steatosis with persistently normal ALT are at lower risk for cirrhosis compared to those with steatosis and elevated ALT and not different from the risk in a clinical cohort without hepatic steatosis.

Incidence of Hepatocellular Carcinoma in Primary Biliary Cholangitis: A Systematic Review and Meta-Analysis.

BACKGROUND: The risk and determinants of HCC in patients with primary biliary cholangitis (PBC) are unclear. We conducted a systematic review and meta-analysis of the incidence of HCC and risk factors associated with HCC risk among patients with PBC. METHODS: We searched PubMed, EMBASE, MEDLINE, Cochrane databases and reference lists from relevant articles to identify cohort studies that examined incidence of HCC in patients with PBC from inception through November 2019. RESULTS: A total of 29 studies including 22,615 patients met the eligibility criteria. The median cohort size was 292 patients followed for an average of 76 months. The pooled incidence rate for patients with PBC was 4.17 per 1000 patient-years (95% CI 3.17-5.47). On subgroup analysis, the incidence of HCC in patients with PBC cirrhosis was 15.7 per 1000 patient-years (95% CI 8.73-28.24). The HCC incidence rate was 9.82 per 1000 person-years (95% CI 5.92-16.28) in men and 3.82 per 1000 person-years (95% CI 2.85-5.11) in women. CONCLUSIONS: Cirrhosis is the strongest risk factor for HCC in patients with PBC. Male gender was also a risk factor. Our meta-analysis supports current recommendations of HCC surveillance in patients with PBC cirrhosis. Further studies are needed to evaluate risk factors in this population.

Prevalence and short-term mortality of acute-on-chronic liver failure: A national cohort study from the USA.

BACKGROUND & AIMS: Acute-on-chronic liver failure (ACLF) is characterised by the presence of organ failure in patients with decompensated cirrhosis and is associated with high short-term mortality. However, there are limited data on the prevalence and short-term outcomes of ACLF in patients with cirrhosis seen in the US. We aimed to study the prevalence and risk factors associated with the development and short term mortality in a large cohort of patients in the US. METHODS: Using the US Department of Veterans Affairs (VA) Corporate Data Warehouse, we identified patients with ACLF during hospitalisation for decompensated cirrhosis at any of the 127 VA hospitals between January 1, 2004, and December 31, 2014. We examined the prevalence of ACLF and variables associated with 28- and 90-day mortality in ACLF, and trends in prevalence and survival over time. RESULTS: Of 72,316 patients hospitalised for decompensated cirrhosis, 19,082 (26.4%) patients met the criteria of ACLF on admission. Of these, 12.8% had 1, 10.1% had 2, and 3.5% had 3 or more organ failures. Overall, 25.5% and 40.0% of ACLF patients died within 28 days and 90 days of admission, respectively. Older age, White race, liver cancer, higher model for end-stage liver disease sodium corrected score, and non-liver transplant centre were associated with increased risk of death in ACLF. Over the study period, the prevalence of ACLF decreased, and all grades but ACLF-3 had improvement in survival. CONCLUSIONS: In a US cohort of hospitalised patients with decompensated cirrhosis, ACLF was common and associated with high short-term mortality. Over a decade, ACLF prevalence decreased but survival improvement of ACLF-3 was not seen. Early recognition and aggressive management including timely referral to transplant centres may lead to improved outcomes in ACLF. LAY SUMMARY: Acute-on-chronic liver failure (ACLF) is a condition marked by multiple organ failures in patients with cirrhosis and associated with a high risk of death. In this study of US patients hospitalised with cirrhosis, 1 in 4 patients developed ACLF. In total, 25% of patients with ACLF died within 1 month and 40% died within 3 months. Thus, early recognition of ACLF is important for the initiation of aggressive management, which is required to save these patients' lives.

Statin Use After Diagnosis of Hepatocellular Carcinoma Is Associated With Decreased Mortality.

BACKGROUND & AIMS: Statin use is associated with a lower risk of developing hepatocellular carcinoma (HCC). However, it is unclear whether postdiagnosis statin use is associated with a reduced risk of death in patients with HCC. METHODS: We performed a retrospective analysis of data from 15,422 patients with HCC in the Veterans Administration Central Cancer Registry, diagnosed from 2002 through 2016. We identified statin prescriptions that were filled before and after the cancer diagnosis and used time-dependent Cox regression models to calculate adjusted hazard ratios (HRs) and 95% CIs for risk of death. We used a time-varying exposure to avoid immortal time bias, and a 3-month lag (following up patients from 3 months after the cancer diagnosis) to reduce reverse causation. A sensitivity analysis was conducted varying the lag duration between date of cancer diagnosis and start of follow-up evaluation. RESULTS: Statin use after diagnosis was recorded for 14.9% of patients with HCC. We found that postdiagnosis statin use was associated with a decreased risk of cancer-specific death (adjusted HR, 0.85; 95% CI, 0.77-0.93) and all-cause mortality (HR, 0.89; 95% CI, 0.83-0.95). The magnitudes of these inverse associations were consistent for patients who used high or low doses of statins, and the inverse associations remained across a range of lag periods (from 0 months to 12 months after HCC diagnosis). We found no evidence for effect modification by prediagnosis statin use, or by presentation- or treatment-related factors, and no independent association with prediagnosis statin use. CONCLUSIONS: In a retrospective analysis of data from veterans with HCC, use of statins (high or low doses) after a diagnosis of HCC was associated with reduced mortality.

Risk of Hepatocellular Cancer in Patients With Non-Alcoholic Fatty Liver Disease.

BACKGROUND & AIMS: There are limited data on the risk of hepatocellular cancer (HCC) in patients with non-alcoholic fatty liver disease (NAFLD). We aimed to estimate the risk of incident HCC among patients with NAFLD. METHODS: We conducted a retrospective cohort study from a total of 130 facilities in the Veterans Health Administration. Patients with NAFLD diagnosed between January 1, 2004 and December 31, 2008 were included and followed until HCC diagnosis, death, or December 31, 2015. We also identified a sex- and age-matched control cohort without NAFLD. We ascertained all new HCC cases from the Central Cancer Registry and manual chart reviews. We calculated incidence rates for HCC by NAFLD status, as well as in subgroups of NAFLD patients. We used competing risk models to compare the risk of HCC in patients with NAFLD vs those without NAFLD. We reviewed electronic medical records of all HCC cases that developed in NAFLD patients without cirrhosis. RESULTS: We compared 296,707 NAFLD patients with 296,707 matched controls. During 2,382,289 person-years [PYs] of follow-up, 490 NAFLD patients developed HCC (0.21/1000 PYs). HCC incidence was significantly higher among NAFLD patients vs controls (0.02/1000 PYs; hazard ratio, 7.62; 95% confidence interval, 5.76-10.09). Among patients with NAFLD, those with cirrhosis had the highest annual incidence of HCC (10.6/1000 PYs). Among patients with NAFLD cirrhosis, HCC risk ranged from 1.6 to 23.7 per 1000 PYs based on other demographic characteristics; risk of HCC was the highest in older Hispanics with cirrhosis. In medical record reviews, 20% of NAFLD patients with HCC had no evidence of cirrhosis. CONCLUSIONS: Risk of HCC was higher in NAFLD patients than that observed in general clinical population. Most HCC cases in NAFLD developed in patients with cirrhosis. The absolute risk of HCC was higher than the accepted thresholds for HCC surveillance for most patients with NAFLD cirrhosis.

Role of Non-hepatic Medical Comorbidity and Functional Limitations in Predicting Mortality in Patients with HCV.

BACKGROUND: Medical comorbidities and functional status limitations are determinants of mortality in many chronic diseases. The extent to which survival in the rapidly aging cohort of patients with HCV is affected by these competing causes of mortality remains unclear. AIM: We sought to determine the effect of medical/functional comorbidities on survival after adjusting for liver disease severity in a cohort of patients with HCV infection. METHODS: We prospectively recruited consecutive patients from an HCV clinic 2009-2014. We calculated an index of survival (Schonberg Index, SI) based on age, gender, medical comorbidities, and functional status variables. We defined cirrhosis with the FibroSure test (F3/4-F4). We used multivariable Cox modeling to assess association between functional/survival measure and survival after adjustment for severity of liver disease. RESULTS: The cohort consisted of 1052 HCV patients. The average age was 56.8 years; 36 % had cirrhosis. The mean SI was 8.2 (SD = 2.7). During a mean follow-up of 5610 person-years, 102 (9.7 %) patients died. In unadjusted analysis, higher baseline SI predicted mortality (HR 1.17; 95 % CI 1.09-1.25). SI similarly predicted mortality in cirrhotic patients (HR 1.23, 95 % CI 1.13-1.34) and non-cirrhotic patients (HR 1.21, 95 % CI 1.08-1.36). This did not change after adjusting for age, drug use, or coronary artery disease. DISCUSSION: Comorbidities and functional limitations predict higher mortality in patients with HCV; this relationship is independent of cirrhosis. Use of general prognostic indices may help identify HCV patients at high risk for mortality, which could further guide clinical care in a manner not achievable with assessment of liver disease alone.

Accurate Identification of Fatty Liver Disease in Data Warehouse Utilizing Natural Language Processing.

INTRODUCTION: Natural language processing is a powerful technique of machine learning capable of maximizing data extraction from complex electronic medical records. METHODS: We utilized this technique to develop algorithms capable of "reading" full-text radiology reports to accurately identify the presence of fatty liver disease. Abdominal ultrasound, computerized tomography, and magnetic resonance imaging reports were retrieved from the Veterans Affairs Corporate Data Warehouse from a random national sample of 652 patients. Radiographic fatty liver disease was determined by manual review by two physicians and verified with an expert radiologist. A split validation method was utilized for algorithm development. RESULTS: For all three imaging modalities, the algorithms could identify fatty liver disease with >90% recall and precision, with F-measures >90%. DISCUSSION: These algorithms could be used to rapidly screen patient records to establish a large cohort to facilitate epidemiological and clinical studies and examine the clinic course and outcomes of patients with radiographic hepatic steatosis.

Pay for Performance in Chronic Liver Disease.

With the advent of the Affordable Care Act, pay-for-performance programs have become widespread in the United States and are here to stay. The Centers for Medicare and Medicaid Services started its pay-for-performance program, the Physician Quality Reporting Initiative, in 2007, and made it a permanent system, the Physician Quality Reporting System, in 2011. Although it started off as a pay-for-performance initiative, in which physicians and other health care professionals were rewarded for satisfactorily reporting on selected quality measures, it now has evolved into a penalty-based program. The Physician Quality Reporting System includes measures that target hepatitis C virus infection. It is important for gastroenterologists to be aware of these measures and the submission process to avoid penalties or other difficulties with reimbursement. This review describes the current measures in chronic liver disease, rates of submission, as well as the submission process and associated challenges.

Magnetic Resonance Elastography for the Clinical Risk Assessment of Fibrosis, Cirrhosis, and Portal Hypertension in Patients With NAFLD.

Nonalcoholic fatty liver disease (NAFLD) is rapidly becoming one of the most common causes of liver disease. The progressive subtype of NAFLD, nonalcoholic steatohepatitis (NASH), leads to cirrhosis, hepatocellular carcinoma, and mortality. Fibrosis is the strongest predictor for complications. Due to the invasive nature of liver biopsy, noninvasive testing methods have emerged to detect fibrosis and predict outcomes. Of these modalities, magnetic resonance elastography (MRE) has demonstrated the highest accuracy to detect fibrosis. In this review, we will focus on the emerging data regarding MRE and liver fibrosis, cirrhosis, and portal hypertension in NAFLD.

Risk Factors for Hepatocellular Carcinoma: A Historical Perspective.

Content available: Author Audio Recording.

What's in Your Drink? Poster Educates Families About Sugar Content and Fatty Liver Disease.

OBJECTIVE: Drinking sugar-sweetened beverages is a risk factor for developing childhood obesity and nonalcoholic fatty liver disease (NAFLD). This study investigated the impact of an educational poster in pediatric offices on family's knowledge of sugar content in beverages and assessed awareness of NAFLD. DESIGN: Preclinic visit surveys asked patients' caregivers about the sugar content in beverages and awareness of NAFLD. Postclinic visit surveys assessed improvement in knowledge of sugar content and willingness to change dietary habits. SETTING: Outpatient visits in a single center in Houston between September and November 2019. PARTICIPANTS: One hundred and forty-nine caregivers were surveyed, and patients' median age was 5.5 years (range, 0-18 years) with 57% males. INTERVENTION: Educational posters displayed the sugar content of common beverages in each clinic room. MAIN OUTCOME MEASURES: Outcomes measured included pre-post clinic visit change and predictors of change in (1) knowledge of sugar content in beverages and (2) intent to change beverage consumption. Baseline awareness of NAFLD and associated predictors were also assessed. ANALYSIS: Logistic regression identified factors associated with an intended change in beverage consumption, change in survey score, and NAFLD awareness. RESULTS: Increased knowledge of sugar content with median scores of 25% preclinic to 50% postclinic (P < 0.001). Eighty-eight percent of caregivers were very/moderately likely to provide their children fewer sugar-sweetened beverages. Sixty percent of caregivers were aware of NAFLD, but only 32.8% were concerned. CONCLUSIONS AND IMPLICATIONS: Posters in clinics increased awareness of the sugar content in beverages, and most caregivers reported intent to decrease children's sugary beverage consumption.