A natural language processing algorithm accurately classifies steatotic liver disease pathology to estimate the risk of cirrhosis.

BACKGROUND: Histopathology remains the gold standard for diagnosing and staging metabolic dysfunction-associated steatotic liver disease (MASLD). The feasibility of studying MASLD progression in electronic medical records based on histological features is limited by the free-text nature of pathology reports. Here we introduce a natural language processing (NLP) algorithm to automatically score MASLD histology features. METHODS: From the Mass General Brigham health care system electronic medical record, we identified all patients (1987-2021) with steatosis on index liver biopsy after excluding excess alcohol use and other etiologies of liver disease. An NLP algorithm was constructed in Python to detect steatosis, lobular inflammation, ballooning, and fibrosis stage from pathology free-text and manually validated in >1200 pathology reports. Patients were followed from the index biopsy to incident decompensated liver disease accounting for covariates. RESULTS: The NLP algorithm demonstrated positive and negative predictive values from 93.5% to 100% for all histologic concepts. Among 3134 patients with biopsy-confirmed MASLD followed for 20,604 person-years, rates of the composite endpoint increased monotonically with worsening index fibrosis stage (p for linear trend <0.005). Compared to simple steatosis (incidence rate, 15.06/1000 person-years), the multivariable-adjusted HRs for cirrhosis were 1.04 (0.72-1.5) for metabolic dysfunction-associated steatohepatitis (MASH)/F0, 1.19 (0.92-1.54) for MASH/F1, 1.89 (1.41-2.52) for MASH/F2, and 4.21 (3.26-5.43) for MASH/F3. CONCLUSIONS: The NLP algorithm accurately scores histological features of MASLD from pathology free-text. This algorithm enabled the construction of a large and high-quality MASLD cohort across a multihospital health care system and disclosed an accelerating risk for cirrhosis based on the index MASLD fibrosis stage.

Association of distinct microbial signatures with premalignant colorectal adenomas.

Environmental exposures are a major risk factor for developing colorectal cancer, and the gut microbiome may serve as an integrator of such environmental risk. To study the microbiome associated with premalignant colon lesions, such as tubular adenomas (TAs) and sessile serrated adenomas (SSAs), we profiled stool samples from 971 participants undergoing colonoscopy and paired these data with dietary and medication history. The microbial signatures associated with either SSA or TA are distinct. SSA associates with multiple microbial antioxidant defense systems, whereas TA associates with a depletion of microbial methanogenesis and mevalonate metabolism. Environmental factors, such as diet and medications, link with the majority of identified microbial species. Mediation analyses found that Flavonifractor plautii and Bacteroides stercoris transmit the protective or carcinogenic effects of these factors to early carcinogenesis. Our findings suggest that the unique dependencies of each premalignant lesion may be exploited therapeutically or through dietary intervention.

Clinical Characteristics and Treatment Response in Microscopic Colitis Based on Age at Diagnosis: A Multicenter Retrospective Study.

BACKGROUND: Microscopic colitis (MC) primarily affects older adults; thus, data in younger patients are scarce. AIMS: To compare clinical characteristics and treatment response by age at diagnosis. METHODS: This retrospective cohort study was performed at Mayo Clinic and Massachusetts General Hospital. Patients were chosen consecutively using established databases. Patients were 'younger' if age at diagnosis was ≤ 50 years and 'older' if age > 50 years. Treatment outcomes were captured for induction (12 ± 4 weeks), based on the total number of daily stools, and defined as remission (complete resolution), response (≥ 50% improvement), non-response (< 50% improvement), and intolerance. Patients were considered 'responders' if they had remission or response and 'non-responders' if they had non-response or intolerance. RESULTS: We included 295 patients (52 younger, 243 older). There were no differences in sex, race, MC subtype, and diarrhea severity between groups (all P > 0.05). Younger patients were more likely to have celiac disease (17.3% vs. 5.8%, P = 0.01), while older patients had higher BMI (mean 25.0 vs. 23.8 kg/m2, P = 0.04) were more likely smokers (53.9% vs. 34.6%, P = 0.01) and use NSAIDs (48.6% vs. 15.4%, P < 0.01) and statins (22.6% vs. 3.8%, P < 0.01). Overall treatment response was highest for budesonide (88.3%) and did not differ when comparing older to younger patients (90.6% vs. 77.8%, P = 0.12) or by MC subtype (LC, 81.5% vs. CC, 92.9%, P = 0.07). CONCLUSIONS: There are no significant differences in MC treatment response based on age or disease subtype. These findings support treating patients with MC based on symptom severity rather than age.

Fruit and vegetable consumption is associated with lower prevalence of asymptomatic diverticulosis: a cross-sectional colonoscopy-based study.

BACKGROUND: Previous studies of the relationship between dietary factors and risk of diverticulosis have yielded inconsistent results. We therefore sought to investigate the association between consumption of fruit and vegetables and prevalent diverticulosis. METHODS: Our study population included participants in the Gastrointestinal Disease and Endoscopy Registry (GIDER), a colonoscopy-based longitudinal cohort at the Massachusetts General Hospital, who provided comprehensive information on dietary intake and lifestyle factors using validated questionnaires prior to colonoscopy. Information on presence and location of diverticula was obtained from the endoscopist at the end of each procedure. We used Poisson regression modeling to calculate the prevalence ratios (PRs) and 95% confidence intervals (CIs). RESULTS: Among 549 participants with a mean age of 61 years enrolled in GIDER, we confirmed diverticulosis in 245 (44.6%). The prevalence of diverticulosis appeared to decrease with higher consumption of fruit and vegetables (Ptrend = 0.007 for fruit and 0.008 for vegetables, respectively). Compared to participants with less than five servings of vegetables per week, the multivariable-adjusted PRs of diverticulosis were 0.84 (95% CI, 0.60-1.17) with five to seven servings per week and 0.62 (95% CI, 0.44-0.89) with greater than one serving per day. Similarly, compared to participants with less than five servings per week of fruit, the multivariable-adjusted PR of diverticulosis was 0.60 (95% CI, 0.41-0.87) with greater than one serving per day. These associations were not modified by age, BMI, smoking, or red meat intake (All Pinteraction > 0.055). CONCLUSION: In a colonoscopy-based longitudinal cohort study, we show that higher consumption of fruit and vegetables is associated with lower risk of prevalent diverticulosis.

Microscopic Colitis Is Characterized by Intestinal Dysbiosis.

The critical role of the gut microbiome in microscopic colitis (MC) is evident by the observation that fecal diversion is associated with resolution of mucosal inflammation while restoration of fecal stream is associated with recurrence of disease.1 Characterization of the composition and function of the gut microbiome in MC therefore could provide insights into disease pathogenesis.