Large-scale identification of undiagnosed hepatic steatosis using natural language processing.

Background: Nonalcoholic fatty liver disease (NAFLD) is a major cause of liver-related morbidity in people with and without diabetes, but it is underdiagnosed, posing challenges for research and clinical management. Here, we determine if natural language processing (NLP) of data in the electronic health record (EHR) could identify undiagnosed patients with hepatic steatosis based on pathology and radiology reports. Methods: A rule-based NLP algorithm was built using a Linguamatics literature text mining tool to search 2.15 million pathology report and 2.7 million imaging reports in the Penn Medicine EHR from November 2014, through December 2020, for evidence of hepatic steatosis. For quality control, two independent physicians manually reviewed randomly chosen biopsy and imaging reports (n = 353, PPV 99.7%). Findings: After exclusion of individuals with other causes of hepatic steatosis, 3007 patients with biopsy-proven NAFLD and 42,083 patients with imaging-proven NAFLD were identified. Interestingly, elevated ALT was not a sensitive predictor of the presence of steatosis, and only half of the biopsied patients with steatosis ever received an ICD diagnosis code for the presence of NAFLD/NASH. There was a robust association for PNPLA3 and TM6SF2 risk alleles and steatosis identified by NLP. We identified 234 disorders that were significantly over- or underrepresented in all subjects with steatosis and identified changes in serum markers (e.g., GGT) associated with presence of steatosis. Interpretation: This study demonstrates clear feasibility of NLP-based approaches to identify patients whose steatosis was indicated in imaging and pathology reports within a large healthcare system and uncovers undercoding of NAFLD in the general population. Identification of patients at risk could link them to improved care and outcomes. Funding: The study was funded by US and German funding sources that did provide financial support only and had no influence or control over the research process.

A comparison of 9-min colonoscopy withdrawal time and 6-min colonoscopy withdrawal time: A systematic review and meta-analysis.

INTRODUCTION: The optimal colonoscopy withdrawal time is still a controversial topic. While several studies demonstrate that longer withdrawal time improves adenoma detection rate, others have contradicted these findings. METHODS: Three independent reviewers performed a comprehensive review of all original articles published from inception to January 2021 and included studies reporting comparison of the two cohorts-(i) ≥ 6 but less than 9 min of colonoscopy withdrawal time (CWT) and (ii) ≥ 9 min of CWT. The outcome measures were the following: (i) adenoma detection rate (ADR), (ii) advanced ADR, and (iii) sessile serrated adenoma detection rate (SDR). The meta-analysis was performed, and the statistics were two-tailed. RESULTS: A total of seven studies met the inclusion criteria after a thorough search of the literature was completed. The analysis revealed that ≥ 9 min of CWT had significantly higher odds of adenoma detection as compared with 6-9 min of CWT (odds ratio [OR] 1.54, 95% confidence interval [CI] 1.30-1.82; I2  = 93.7). Additionally, a significantly higher odds of sessile serrated adenoma detection (OR 1.68, 95% CI 1.28-2.22; I2  = 0) and a trend towards higher odds of advanced adenoma detection (OR 1.38, 95% CI 0.98-1.95, I2  = 90) were seen with CWT of at least 9 min when compared with 6-9 min of CWT. CONCLUSION: This systematic review and meta-analysis analysis provides further evidence that at least 9 min of CWT cohort had significantly higher ADR and SDR as compared with the at least 6 min but less than 9 min of cohort.

Inverse Association of Coffee with Liver Cancer Development: An Updated Systematic Review and Meta-analysis.

BACKGROUND AND AIMS: Coffee consumption has been suggested to reduce the risk for hepatocellular carcinoma (HCC). While several studies report inverse correlation with coffee drinking, others have suggested more than 2 cups of coffee every day decrease the risk of liver cancer or HCC. However, controversy exists about the exact dose that would provide protective benefit. Therefore, we aimed to carry out a systematic review and meta-analysis of all studies that investigated the association of coffee consumption and risk of HCC and/or liver cancer. Our outcomes were the evaluation of the association of coffee with HCC or liver cancer development along with the amount of coffee needed to prevent HCC or liver cancer. METHODS: We performed a PubMed/MEDLINE/EMBASE/Ovid/Google Scholar search of original articles published in English from 1996 to June 2019, on case-control or cohort or prospective studies that associated coffee with liver cancer or HCC. We calculated the relative risk (RR) of the two conditions for coffee drinking and then stratified this into increments of one cup of coffee per day. Twenty studies were identified. The analysis was performed using random effects models from the methods of DerSimonian and Laird with inverse variance weighting. The Cochrane Q and the I 2 statistics were calculated to assess heterogeneity between studies. A p<0.10 value for chi-square test and I 2 <20% were interpreted as low-level heterogeneity. Probability of publication bias was assessed using funnel plots and with the Egger's test. RESULTS: The overall RR was 0.69 (95%CI 0.56-0.85; p<0.001) with significant heterogeneity between the studies. We performed subgroup analysis over the increments of 1 cup of coffee. Higher doses of coffee consumption were associated with a significant decrease in the risk of developing HCC or liver cancer. The funnel plot did not show significant publication bias. CONCLUSIONS: Our systematic review and meta-analysis suggests that drinking coffee provides benefits with a reduction in the risk of HCC or liver cancer. Higher doses of coffee have higher benefits in terms of risk reduction. However, further biological and epidemiological studies are required to determine the exact mechanism and to study specific subgroups such as viral hepatitis B or C related HCC.

The Microbiome and Hepatocellular Carcinoma.

The human microbiome is a vast and complex system encompassing all of the microbes and their genes that occupy the environmentally exposed surfaces of the human body. The gut microbiota and its associated microbiome play an integral role in mammalian metabolism and immune tolerance as well as in immunocompetence. Disruptions in the human gut microbiome are associated with a cycle of hepatocyte injury and regeneration characteristic of chronic liver disease. The persistence of this inflammation has been shown to induce the accumulation of genetic and epigenetic changes leading to hepatocellular carcinoma (HCC). Therefore, the importance and prognostic influence of the gut microbiome on hepatocarcinogenesis has been increasingly studied in recent years. This review discusses the mechanisms by which imbalances in the gut microbiome disturb the gut-liver axis to impact hepatocarcinogenesis, including disruption of the intestinal barrier, changes in bile acid metabolism, and reduction in tumor-suppressing microRNA. Furthermore, this review summarizes recent advances in potential microbiome-based therapeutic opportunities in HCC.