Machine learning improves the prediction of significant fibrosis in Asian patients with metabolic dysfunction-associated steatotic liver disease - The Gut and Obesity in Asia (GO-ASIA) Study.

BACKGROUND: The precise estimation of cases with significant fibrosis (SF) is an unmet goal in non-alcoholic fatty liver disease (NAFLD/MASLD). AIMS: We evaluated the performance of machine learning (ML) and non-patented scores for ruling out SF among NAFLD/MASLD patients. METHODS: Twenty-one ML models were trained (N = 1153), tested (N = 283), and validated (N = 220) on clinical and biochemical parameters of histologically-proven NAFLD/MASLD patients (N = 1656) collected across 14 centres in 8 Asian countries. Their performance for detecting histological-SF (≥F2fibrosis) were evaluated with APRI, FIB4, NFS, BARD, and SAFE (NPV/F1-score as model-selection criteria). RESULTS: Patients aged 47 years (median), 54.6% males, 73.7% with metabolic syndrome, and 32.9% with histological-SF were included in the study. Patients with SFvs.no-SF had higher age, aminotransferases, fasting plasma glucose, metabolic syndrome, uncontrolled diabetes, and NAFLD activity score (p < 0.001, each). ML models showed 7%-12% better discrimination than FIB-4 to detect SF. Optimised random forest (RF) yielded best NPV/F1 in overall set (0.947/0.754), test set (0.798/0.588) and validation set (0.852/0.559), as compared to FIB4 in overall set (0.744/0.499), test set (0.722/0.456), and validation set (0.806/0.507). Compared to FIB-4, RF could pick 10 times more patients with SF, reduce unnecessary referrals by 28%, and prevent missed referrals by 78%. Age, AST, ALT fasting plasma glucose, and platelet count were top features determining the SF. Sequential use of SAFE < 140 and FIB4 < 1.2 (when SAFE > 140) was next best in ruling out SF (NPV of 0.757, 0.724 and 0.827 in overall, test and validation set). CONCLUSIONS: ML with clinical, anthropometric data and simple blood investigations perform better than FIB-4 for ruling out SF in biopsy-proven Asian NAFLD/MASLD patients.

Rising global burden of cancer attributable to high BMI from 2010 to 2019.

BACKGROUND: High body mass index (BMI) is a major risk factor for cancer development, but its impact on the global burden of cancer remains unclear. METHODS: We estimated global and regional temporal trends in the burden of cancer attributable to high BMI, and the contributions of various cancer types using the framework of the Global Burden of Disease Study. RESULTS: From 2010 to 2019, there was a 35 % increase in deaths and a 34 % increase in disability-adjusted life-years from cancers attributable to high BMI. The age-standardized death rates for cancer attributable to high BMI increased over the study period (annual percentage change [APC] +0.48 %, 95 % CI 0.22 to 0.74 %). The greatest number of deaths from cancer attributable to high BMI occurred in Europe, but the fastest-growing age-standardized death rates and disability-adjusted life-years occurred in Southeast Asia. Liver cancer was the fastest-growing cause of cancer mortality (APC: 1.37 %, 95 % CI 1.25 to 1.49 %) attributable to high BMI. CONCLUSION: The global burden of cancer-related deaths attributable to high BMI has increased substantially from 2010 to 2019. The greatest increase in age-standardized death rates occurred in Southeast Asia, and liver cancer is the fastest-growing cause of cancer mortality attributable to high BMI. Urgent and sustained measures are required at a global and regional level to reverse these trends and slow the growing burden of cancer attributed to high BMI.

Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD): A State-of-the-Art Review.

Metabolic dysfunction-associated steatotic liver disease (MASLD) is the latest term for steatotic liver disease associated with metabolic syndrome. MASLD is the most common cause of chronic liver disease and is the leading cause of liver-related morbidity and mortality. It is important that all stakeholders be involved in tackling the public health threat of obesity and obesity-related diseases, including MASLD. A simple and clear assessment and referral pathway using non-invasive tests is essential to ensure that patients with severe MASLD are identified and referred to specialist care, while patients with less severe disease remain in primary care, where they are best managed. While lifestyle intervention is the cornerstone of the management of patients with MASLD, cardiovascular disease risk must be properly assessed and managed because cardiovascular disease is the leading cause of mortality. No pharmacological agent has been approved for the treatment of MASLD, but novel anti-hyperglycemic drugs appear to have benefit. Medications used for the treatment of diabetes and other metabolic conditions may need to be adjusted as liver disease progresses to cirrhosis, especially decompensated cirrhosis. Based on non-invasive tests, the concepts of compensated advanced chronic liver disease and clinically significant portal hypertension provide a practical approach to stratifying patients according to the risk of liver-related complications and can help manage such patients. Finally, prevention and management of sarcopenia should be considered in the management of patients with MASLD.

Frequency of significant steatosis and compensated advanced chronic liver disease among adults with chronic liver disease.

BACKGROUND: With changes in the epidemiology and treatment of chronic liver disease (CLD), the impact of various etiologies of liver disease on steatosis and advanced fibrosis are uncertain. METHODS: A retrospective study was conducted among liver disease patients of various etiologies undergoing transient elastography (TE) over a 9-year duration. RESULTS: Data for 2886 patients were analyzed and had the following demographics: The median age was 60 (IQR: 45-69) years, 51% were males, and ethnicity was predominantly Chinese (52.5%), followed by Malays (34%) and Indians (12.3%). The median CAP score was 272 (IQR: 219-319) dB/m and the median liver stiffness measurement (LSM) score was 6.5 (IQR: 4.9-9.7) kPa. Hepatic steatosis occurred across the spectrum of etiologies of CLD. Among patients with steatosis, the most common etiologies were nonalcoholic fatty liver disease (NAFLD) at 62% and chronic hepatitis B (CHB) at 26.3%. TE findings suggestive of cACLD (10.1-15 kPa) and highly suggestive of cACLD (>15 kPa) were observed in 11.3% and 12.4% of patients, respectively. NAFLD was found to be the most common etiology for cases with suggestive of cACLD (47.2%) and highly suggestive of cACLD (41.5%). CONCLUSION: Hepatic steatosis is common in CLD, regardless of etiology. Compared with other etiologies, NAFLD is now the leading cause of cACLD.

Epidemiological trends of gastrointestinal and liver diseases in Malaysia: A single-center observational study.

BACKGROUND AND AIM: The spectrum of gastrointestinal (GI) and liver diseases is recognized to have a geographical variation, which may be due to environmental or genetic differences. We aimed to explore this further in a specialist clinic serving a multi-ethnic Asian urban population. METHODS: A retrospective analysis of outpatient data from this institution's electronic medical records was conducted between January and June 2019. Clinical diagnoses of GI and liver diseases and associated demographic information were collected. RESULTS: Data from 3676 adult patients (median age 62 years, female 51.1%) were available for analysis. The frequency of luminal GI, liver and pancreato-biliary diseases were 34.2%, 63.2%, and 2.6%, respectively. Among luminal GI diseases, 38.6% were functional gastrointestinal disorders and 61.4% had an organic cause. A higher proportion of patients of Indian ethnicity were diagnosed with IBD compared with other ethnic groups (India 21.9%, Malay 16.5%, Chinese 12.2%, P = 0.001). Among liver diseases, the most common etiologies were HBV (44.4%) and NAFLD (39.3%). Cirrhosis and/or hepatocellular carcinoma were present in 18% of liver diseases, with NAFLD as the most frequent etiology. Among patients with NAFLD, a higher proportion of ethnic Malays and Indians were evident (Malay 53.8% vs Chinese 28.7% vs Indian 61.1%, P < 0.001). In contrast, a greater proportion of ethnic Chinese were diagnosed with HBV compared with other ethnic groups (Malay 30.9% vs Chinese 57.5% vs Indian 8.4%, P < 0.001). CONCLUSION: The spectrum of GI and liver diseases has a peculiar epidemiology, particularly with reference to the ethnic predilection of certain diseases.

Hydroxyurea associated ileocecal valve ulcer: evidence for causality.

Hydroxyurea is an antimetabolite drug that is commonly used in many hematological disorders. Ulcer formation in the gastrointestinal tract is a rare phenomenon associated with this drug. We report a case of a 73-year-old woman who was found to have an isolated ileocecal valve ulcer while on hydroxyurea 1 g daily for essential thrombocythemia. A comprehensive evaluation ruled out all other causes. The cytoreductive therapy was switched to anagrelide and the endoscopic evaluation 6 months later showed complete healing of the ulcer. However, the hydroxyurea was resumed due to increasing platelet counts and intolerance to dose increments of the anagrelide. Subsequently, the patient was found to have a recurrence of the ulcer. Apart from oral ulcers, there have also been reports of ulcers involving the small bowel and the colon associated with the use of hydroxyurea. The pathophysiology of the non-oral gastrointestinal ulceration in relation to this drug is unclear. Withdrawal of the drug typically leads to complete resolution. Increasing awareness of the rare association between the use of hydroxyurea and nonoral gastrointestinal ulcers is essential for early detection to prevent related complications.