Telomere length and mortality in lean MAFLD: the other face of metabolic adaptation.

BACKGROUND AND AIMS: Healthy weight (lean) patients with metabolic dysfunction-associated fatty liver disease (MAFLD) have a more favorable metabolic and histological profile in cross-sectional studies compared with their non-lean counterparts. Paradoxically, they also have higher overall mortality. The underpinning pathophysiology of this paradox is not understood. Telomere attrition is associated with increased mortality in various diseases. METHODS: We investigated the role of telomere length in the pathogenesis of lean MAFLD in cohorts with biopsy-proven MAFLD (n = 303). We measured serum malondialdehyde (MDA) levels and hepatic 8-hydroxydeoxyguanosine (8-OHdG) and 4-hydroxy-2-nonenal (4-HNE) expression (reactive oxygen species (ROS) markers), growth/differentiation factor-15 (GDF-15) and tested the effect of H2O2 on telomere length and activity in hepatocyte cell lines. The association between leukocyte telomere length and mortality was examined. RESULTS: Telomere length was significantly lower in patients with lean MAFLD (p < 0.001). They also demonstrated an increase in ROS levels and decreases in GDF-15. H2O2 induced telomere shortening and reducing telomere activity in hepatocyte cell lines. We subsequently confirmed that telomere length shortening at baseline is associated with increased hazards of all-cause mortality; the deleterious effect was more profound in lean people. CONCLUSION: Differences in telomere length in part explain the increased mortality of lean compared to non-lean patients with MAFLD. The effect is in part mediated through ROS activation and provide opportunities for therapy.

Evaluation of Google Search Trends for Liver Diseases in Europe.

BACKGROUND AND AIMS: Chronic liver diseases belong to the most common diseases worldwide and are associated with increased morbidity and mortality. Although more than one in three adults are estimated to have metabolic dysfunction-associated steatotic liver disease (MASLD), awareness of this condition is low amongst the general public, health care professionals and policy makers. However, meaningful knowledge transfer is essential for raising awareness and improving prevention and treatment. This study set out to investigate the use of the major internet search engine to understand how knowledge transfer has evolved by analyzing liver-related searches trends. METHODS: We investigated Google search trends by measuring the number of hits relating to liver diseases between 2004 and 2021 in seven languages and European countries but also worldwide. All analyses were performed in R using the R Google trends package gtrendsR. RESULTS: We found that interest in MASLD [formerly non-alcoholic fatty liver disease (NAFLD)] has generally increased over time, but that interest in metabolic associated steatohepatitis (MASH) - the most severe form of MASLD - has decreased. Interest in viral hepatitis C has decreased, whereas the number of queries regarding viral hepatitis B have been stable but dominated by interest in vaccination for it. Recent medical developments (in viral hepatitis) did not lead to a noticeable change in overall search behavior. Users preferred searching using their native language and less complex medical terms and acronyms (e.g., fatty liver instead of NAFLD). CONCLUSIONS: In the last two decades, Google search trends have followed the general development in the field of hepatology. Searches were dominated by non-experts and are not being rapidly influenced by novel scientific developments. Also, users preferred search terms in their native languages rather than English and tended to avoid complex medical search terms. Awareness and communication strategies around MASLD should consider these preferences when addressing the general public.

Fibroblast growth factor 21 is a hepatokine involved in MASLD progression.

AIM: We aimed to assess the role of FGF21 in metabolic dysfunction-associated steatotic liver disease (MASLD) at a multi-scale level. METHODS: We used human MASLD pathology samples for FGF21 gene expression analyses (qPCR and RNAseq), serum to measure circulating FGF21 levels and DNA for genotyping the FGF21 rs838133 variant in both estimation and validation cohorts. A hepatocyte-derived cell line was exposed to free fatty acids at different timepoints. Finally, C57BL/6J mice were fed a high-fat and choline-deficient diet (CDA-HFD) for 16 weeks to assess hepatic FGF21 protein expression and FGF21 levels by ELISA. RESULTS: A significant upregulation in FGF21 mRNA expression was observed in the liver analysed by both qPCR (fold change 5.32 ± 5.25 vs. 0.59 ± 0.66; p = 0.017) and RNA-Seq (3.5 fold; FDR: 0.006; p < 0.0001) in MASLD patients vs. controls. Circulating levels of FGF21 were increased in patients with steatohepatitis vs. bland steatosis (386.6 ± 328.9 vs. 297.9 ± 231.5 pg/mL; p = 0.009). Besides, sex, age, A-allele from FGF21, GG genotype from PNPLA3, ALT, type 2 diabetes mellitus and BMI were independently associated with MASH and significant fibrosis in both estimation and validation cohorts. In vitro exposure of Huh7.5 cells to high concentrations of free fatty acids (FFAs) resulted in overexpression of FGF21 (p < 0.001). Finally, Circulating FGF21 levels and hepatic FGF21 expression were found to be significantly increased (p < 0.001) in animals under CDA-HFD. CONCLUSIONS: Hepatic and circulating FGF21 expression was increased in MASH patients, in Huh7.5 cells under FFAs and in CDA-HFD animals. The A-allele from the rs838133 variant was also associated with an increased risk of steatohepatitis and significant and advanced fibrosis in MASLD patients.

Health-related quality of life in non-alcoholic fatty liver disease: A cross-cultural study between Spain and the United Kingdom.

BACKGROUND: It is unclear what biopsychosocial factors influence the impact of NAFLD on health-related quality of life (HRQoL), and if these factors are equally important predictors between different nationalities. METHODS: HRQoL (CLDQ) was measured in both Southern European (Spain, n = 513) and Northern European (United Kingdom -UK-, n = 224) cohorts of patients with NAFLD in this cross-sectional study. For each cohort, participant data were recorded on histological grade of steatohepatitis, stage of fibrosis and biopsychosocial variables. Regression analysis was used to explore which of these variables predicted HRQoL. Moderated mediation models were conducted using SPSS PROCESS v3.5 macro. RESULTS: Participants with severe fibrosis reported more fatigue, systemic symptoms and worry, and lower HRQoL than those with none/mild fibrosis, regardless of place of origin. In addition, body mass index (BMI) and gender were found to be significant predictors of HRQoL in both Spanish and UK participants. Female gender was associated with worse emotional function, higher BMI and more fatigue, which predicted lower participants' HRQoL. UK participants showed more systemic symptoms and worry than Spanish participants, regardless of liver severity. The negative effects of gender on HRQoL through emotional function, BMI and fatigue were reported to a greater degree in UK than in Spanish participants. CONCLUSIONS: UK participants showed a greater impairment in HRQoL as compared to Spanish participants. Higher fibrosis stage predicted lower HRQoL, mainly in the Spanish cohort. Factors such as female gender or higher BMI contributed to the impact on HRQoL in both cohorts of patients and should be considered in future multinational intervention studies in NAFLD.

Novel approaches in the medical management of compensated cirrhosis.

INTRODUCTION: Classically, clinical practice guidelines and expert recommendations have focused on the management of decompensated cirrhotic patients, so we focused this review on improving care for compensated cirrhotic patients who are followed up in outpatient clinics. AREAS COVERED: We reviewed the current methods for establishing liver function, the diagnosis and management of advanced chronic liver disease and clinically significant portal hypertension as well as the prevention of its complications, with special attention to covert hepatic encephalopathy, we also paid attention to the extrahepatic complications of cirrhosis and the palliative care. All this from the perspective of evidence-based medicine and trying to empower precision medicine. The literature search was undertaken by PubMed with 'cirrhosis,' 'advanced chronic liver disease,' 'liver function,' 'portal hypertension,' 'covert hepatic encephalopathy,' 'minimal hepatic encephalopathy,' 'palliative care' as MeSH terms. EXPERT OPINION: We must offer compensated cirrhotic patients specific care and measures to prevent the progression of the disease and the appearance of its complications beyond the calculation of liver function and imaging screening for hepatocellular carcinoma that we perform every six months. Entities that have typically received little attention, such as covert hepatic encephalopathy, extrahepatic complications and symptoms of cirrhosis, and palliative care, must come to the spotlight.

FIB-4 score as predictor of COVID-19-related severity in hospitalized patients.

AIM: To determine the impact of liver fibrosis on the prognosis of COVID and the liver injury associated with the infection. METHODS: Retrospective multicenter study including 575 patients requiring admission for COVID-19 between January and June 2020. FIB-4 was calculated within 6 months prior to infection and at 6 months post-infection. RESULTS: Baseline FIB-4 was increased in patients who died (1.91±0.95 vs. 1.43±0.85; p<0.001). In addition, the 17.1% (32/187) of patients with baseline FIB-4<1.45 died versus 52.9% (9/17) if FIB-4>3.25 (p<0.001). In the adjusted multivariate analysis, baseline FIB-4 (OR 1.61 (95%CI 1.19-2.18); p=0.002) was independently associated with mortality. Parameters associated with liver injury, including AST (28±10 vs. 45±56IU/L; p<0.001) and ALT (20±12 vs. 38±48IU/L; p<0.001) were significantly higher at admission compared to baseline. Also, FIB-4 was increased from baseline to the time of admission (1.53±0.88 vs. 2.55±1.91; p<0.001), and up to 6.9% (10/145) of patients with FIB-4<1.45 at admission died versus 47.5% if FIB-4>3.25 (58/122) (p<0.001). In the adjusted multivariate analysis, FIB-4 at admission (OR 1.14 (95%CI 1.03-1.27); p=0.015) was independently associated with mortality. Also, AST (42±38 vs. 22±17IU/L; p<0.001) and ALT (40±50 vs. 20±19 IU/L; p<0.001) were significantly reduced at 6 months after the resolution of infection. Accordingly, FIB-4 decreased significantly (2.12±1.25 vs. 1.32±0.57; p<0.001) six months after the infection. CONCLUSION: Increased FIB-4, either at baseline or at the time of admission, was related to the severity and mortality related to SARS-CoV-2 infection. However, the liver damage expressed by elevated transaminases and FIB-4 was reversible in most of patients.

Navigating the Link Between Non-alcoholic Fatty Liver Disease/Non-alcoholic Steatohepatitis and Cardiometabolic Syndrome.

The global prevalence of non-alcoholic fatty liver disease (NAFLD) is nearly 25% and is increasing rapidly. The spectrum of liver damage in NAFLD ranges from simple steatosis to non-alcoholic steatohepatitis, characterised by the presence of lobular inflammation and hepatocyte ballooning degeneration, with or without fibrosis, which can further develop into cirrhosis and hepatocellular carcinoma. Not only is NAFLD a progressive liver disease, but numerous pieces of evidence also point to extrahepatic consequences. Accumulating evidence suggests that patients with NAFLD are also at increased risk of cardiovascular disease (CVD); in fact, CVDs are the most common cause of mortality in patients with NAFLD. Obesity, type 2 diabetes and higher levels of LDL are common risk factors in both NAFLD and CVD; however, how NAFLD affects the development and progression of CVD remains elusive. In this review, we comprehensively summarise current data on the key extrahepatic manifestations of NAFLD, emphasising the possible link between NAFLD and CVD, including the role of proprotein convertase substilisin/kenin type 9, extracellular vesicles, microbiota, and genetic factors.

The Janus of a disease: Diabetes and metabolic dysfunction-associated fatty liver disease.

Metabolic Dysfunction-Associated Fatty Liver Disease and Diabetes Mellitus are two prevalent metabolic disorders that often coexist and synergistically contribute to the progression of each other. Several pathophysiological pathways are involved in the association, including insulin resistance, inflammation, and lipotoxicity, providing a foundation for understanding the complex interrelationships between these conditions. The presence of MASLD has a significant impact on diabetes risk and the development of microvascular and macrovascular complications, and diabetes significantly contributes to an increased risk of liver fibrosis progression in MASLD and the development of hepatocellular carcinoma. Moreover, both pathologies have a synergistic effect on cardiovascular events and mortality. Therapeutic interventions targeting MASLD and diabetes are discussed, considering lifestyle modifications, pharmacological agents, and emerging treatment modalities. The review also addresses the challenges in managing these comorbidities, such as the need for personalized approaches and the potential impact on cardiovascular health. The insights gleaned from this analysis can inform clinicians, researchers, and policymakers in developing integrated strategies for preventing, diagnosing, and managing these metabolic disorders.

The biochemical pattern defines MASLD phenotypes linked to distinct histology and prognosis.

BACKGROUND: MASLD can manifest as hepatocellular damage, which can result in mild elevation of aminotransferases. However, in some patients, MASLD presents with cholestatic pattern. OBJECTIVE: To assess the impact of the biochemical pattern on the natural course of MASLD, including liver damage in histology, the accuracy of non-invasive tests(NITs), and prognosis. METHODS: Multicenter study enrolling 2156 patients with biopsy-proven MASLD, who were classified based on their[ALT/ULN)]/[(ALP/ULN)] levels at the time of biopsy: (a) hepatocellular pattern(H), > 5; (b) mixed pattern(M),2-5; (c) cholestatic pattern(C), < 2. OUTCOMES: (a) histological evaluation of the single components of NAS, MASH, and fibrosis; (b) NITs and transient elastography assessing advanced fibrosis; (c) prognosis determined by the appearance of decompensated cirrhosis and death. RESULTS: Out of the 2156 patients, 22.9% exhibited the H-pattern, whilst 31.7% exhibited the C-pattern. Severe steatosis, ballooning, lobular inflammation, and MASH (56.4% H vs. 41.9% M vs. 31.9% C) were more common in H-pattern (p = 0.0001),whilst C-pattern was linked to cirrhosis (5.8% H vs. 5.6% M vs. 10.9% C; p = 0.0001). FIB-4(0.74(95% CI 0.69-0.79) vs. 0.83 (95% CI 0.80-0.85); p = 0.005) and Hepamet Fibrosis Score(0.77 (95% CI 0.69-0.85) vs. 0.84 (95% CI 0.80-0.87); p = 0.044)exhibited lower AUROCs in the H-pattern. The C-pattern[HR 2.37 (95% CI 1.12-5.02); p = 0.024], along with age, diabetes, and cirrhosis were independently associated with mortality. Most patients maintained their initial biochemical pattern during the second evaluation. CONCLUSIONS: The H-pattern exhibited greater necro-inflammation in the histology than the C-pattern, whereas the latter showed more cirrhosis. The accuracy of NITs in detecting fibrosis was decreased in H-pattern. The occurrence of decompensated events and mortality was predominant in C-pattern. Therefore, identifying MASLD phenotypes based on the biochemical presentation could be relevant for clinical practice.

Is There a Safe Alcohol Consumption Limit for the General Population and in Patients with Liver Disease?

Excessive alcohol consumption represents an important burden for health systems worldwide and is a major cause of liver- and cancer-related deaths. Alcohol consumption is mostly assessed by self-report that often underestimates the amount of drinking. While alcohol use disorders identification test - version C is the most widely used test for alcohol use screening, in patients with liver disease the use of alcohol biomarker could help an objective assessment. The amount of alcohol that leads to significant liver disease depends on gender, genetic background, and coexistence of comorbidities (i.e., metabolic syndrome factors). All patients with alcohol-associated liver disease are recommended to follow complete abstinence and they should be treated within multidisciplinary teams. Abstinence slows down and even reverses the progression of liver fibrosis and can help recompensate patients with complicated cirrhosis. Whether there is a safe amount of alcohol in the general population is a matter of intense debate. Large epidemiological studies showed that the safe amount of alcohol to avoid overall health-related risks is lower than expected even in the general population. Even one drink per day can increase cancer-related death. In patients with any kind of chronic liver disease, especially in those with metabolic-associated steatotic liver disease, no alcohol intake is recommended. This review article discusses the current evidence supporting the deleterious effects of small-to-moderate amounts of alcohol in the general population and in patients with underlying chronic liver disease.

Vibration-Controlled Transient Elastography Scores to Predict Liver-Related Events in Steatotic Liver Disease.

Importance: Metabolic dysfunction-associated steatotic liver disease (MASLD) is currently the most common chronic liver disease worldwide. It is important to develop noninvasive tests to assess the disease severity and prognosis. Objective: To study the prognostic implications of baseline levels and dynamic changes of the vibration-controlled transient elastography (VCTE)-based scores developed for the diagnosis of advanced fibrosis (Agile 3+) and cirrhosis (Agile 4) in patients with MASLD. Design, Setting, and Participants: This cohort study included data from a natural history cohort of patients with MASLD who underwent VCTE examination at 16 tertiary referral centers in the US, Europe, and Asia from February 2004 to January 2023, of which the data were collected prospectively at 14 centers. Eligible patients were adults aged at least 18 years with hepatic steatosis diagnosed by histologic methods (steatosis in ≥5% of hepatocytes) or imaging studies (ultrasonography, computed tomography or magnetic resonance imaging, or controlled attenuation parameter ≥248 dB/m by VCTE). Main Outcomes and Measures: The primary outcome was liver-related events (LREs), defined as hepatocellular carcinoma or hepatic decompensation (ascites, variceal hemorrhage, hepatic encephalopathy, or hepatorenal syndrome), liver transplant, and liver-related deaths. The Agile scores were compared with histologic and 8 other noninvasive tests. Results: A total of 16 603 patients underwent VCTE examination at baseline (mean [SD] age, 52.5 [13.7] years; 9600 [57.8%] were male). At a median follow-up of 51.7 (IQR, 25.2-85.2) months, 316 patients (1.9%) developed LREs. Both Agile 3+ and Agile 4 scores classified fewer patients between the low and high cutoffs than most fibrosis scores and achieved the highest discriminatory power in predicting LREs (integrated area under the time-dependent receiver-operating characteristic curve, 0.89). A total of 10 920 patients (65.8%) had repeated VCTE examination at a median interval of 15 (IQR, 11.3-27.7) months and were included in the serial analysis. A total of 81.9% of patients (7208 of 8810) had stable Agile 3+ scores and 92.6% of patients (8163 of 8810) had stable Agile 4 scores (same risk categories at both assessments). The incidence of LREs was 0.6 per 1000 person-years in patients with persistently low Agile 3+ scores and 30.1 per 1000 person-years in patients with persistently high Agile 3+ scores. In patients with high Agile 3+ score at baseline, a decrease in the score by more than 20% was associated with substantial reduction in the risk of LREs. A similar trend was observed for the Agile 4 score, although it missed more LREs in the low-risk group. Conclusions and Relevance: Findings of this study suggest that single or serial Agile scores are highly accurate in predicting LREs in patients with MASLD, making them suitable alternatives to liver biopsy in routine clinical practice and in phase 2b and 3 clinical trials for steatohepatitis.

A genome-wide association study for survival from a multi-centre European study identified variants associated with COVID-19 risk of death.

The clinical manifestations of SARS-CoV-2 infection vary widely among patients, from asymptomatic to life-threatening. Host genetics is one of the factors that contributes to this variability as previously reported by the COVID-19 Host Genetics Initiative (HGI), which identified sixteen loci associated with COVID-19 severity. Herein, we investigated the genetic determinants of COVID-19 mortality, by performing a case-only genome-wide survival analysis, 60 days after infection, of 3904 COVID-19 patients from the GEN-COVID and other European series (EGAS00001005304 study of the COVID-19 HGI). Using imputed genotype data, we carried out a survival analysis using the Cox model adjusted for age, age2, sex, series, time of infection, and the first ten principal components. We observed a genome-wide significant (P-value < 5.0 × 10-8) association of the rs117011822 variant, on chromosome 11, of rs7208524 on chromosome 17, approaching the genome-wide threshold (P-value = 5.19 × 10-8). A total of 113 variants were associated with survival at P-value < 1.0 × 10-5 and most of them regulated the expression of genes involved in immune response (e.g., CD300 and KLR genes), or in lung repair and function (e.g., FGF19 and CDH13). Overall, our results suggest that germline variants may modulate COVID-19 risk of death, possibly through the regulation of gene expression in immune response and lung function pathways.

Machine learning approaches to enhance diagnosis and staging of patients with MASLD using routinely available clinical information.

AIMS: Metabolic dysfunction Associated Steatotic Liver Disease (MASLD) outcomes such as MASH (metabolic dysfunction associated steatohepatitis), fibrosis and cirrhosis are ordinarily determined by resource-intensive and invasive biopsies. We aim to show that routine clinical tests offer sufficient information to predict these endpoints. METHODS: Using the LITMUS Metacohort derived from the European NAFLD Registry, the largest MASLD dataset in Europe, we create three combinations of features which vary in degree of procurement including a 19-variable feature set that are attained through a routine clinical appointment or blood test. This data was used to train predictive models using supervised machine learning (ML) algorithm XGBoost, alongside missing imputation technique MICE and class balancing algorithm SMOTE. Shapley Additive exPlanations (SHAP) were added to determine relative importance for each clinical variable. RESULTS: Analysing nine biopsy-derived MASLD outcomes of cohort size ranging between 5385 and 6673 subjects, we were able to predict individuals at training set AUCs ranging from 0.719-0.994, including classifying individuals who are At-Risk MASH at an AUC = 0.899. Using two further feature combinations of 26-variables and 35-variables, which included composite scores known to be good indicators for MASLD endpoints and advanced specialist tests, we found predictive performance did not sufficiently improve. We are also able to present local and global explanations for each ML model, offering clinicians interpretability without the expense of worsening predictive performance. CONCLUSIONS: This study developed a series of ML models of accuracy ranging from 71.9-99.4% using only easily extractable and readily available information in predicting MASLD outcomes which are usually determined through highly invasive means.

Novel insights into metabolic-associated steatotic liver disease preclinical models.

Metabolic-associated steatotic liver disease (MASLD) encompasses a wide spectrum of metabolic conditions associated with an excess of fat accumulation in the liver, ranging from simple hepatic steatosis to cirrhosis and hepatocellular carcinoma. Finding appropriate tools to study its development and progression is essential to address essential unmet therapeutic and staging needs. This review discusses advantages and shortcomings of different dietary, chemical and genetic factors that can be used to mimic this disease and its progression in mice from a hepatic and metabolic point of view. Also, this review will highlight some additional factors and considerations that could have a strong impact on the outcomes of our model to end up providing recommendations and a checklist to facilitate the selection of the appropriate MASLD preclinical model based on clinical aims.

Serum ferritin levels can predict long-term outcomes in patients with metabolic dysfunction-associated steatotic liver disease.

OBJECTIVE: Hyperferritinaemia is associated with liver fibrosis severity in patients with metabolic dysfunction-associated steatotic liver disease (MASLD), but the longitudinal implications have not been thoroughly investigated. We assessed the role of serum ferritin in predicting long-term outcomes or death. DESIGN: We evaluated the relationship between baseline serum ferritin and longitudinal events in a multicentre cohort of 1342 patients. Four survival models considering ferritin with confounders or non-invasive scoring systems were applied with repeated five-fold cross-validation schema. Prediction performance was evaluated in terms of Harrell's C-index and its improvement by including ferritin as a covariate. RESULTS: Median follow-up time was 96 months. Liver-related events occurred in 7.7%, hepatocellular carcinoma in 1.9%, cardiovascular events in 10.9%, extrahepatic cancers in 8.3% and all-cause mortality in 5.8%. Hyperferritinaemia was associated with a 50% increased risk of liver-related events and 27% of all-cause mortality. A stepwise increase in baseline ferritin thresholds was associated with a statistical increase in C-index, ranging between 0.02 (lasso-penalised Cox regression) and 0.03 (ridge-penalised Cox regression); the risk of developing liver-related events mainly increased from threshold 215.5 µg/L (median HR=1.71 and C-index=0.71) and the risk of overall mortality from threshold 272 µg/L (median HR=1.49 and C-index=0.70). The inclusion of serum ferritin thresholds (215.5 µg/L and 272 µg/L) in predictive models increased the performance of Fibrosis-4 and Non-Alcoholic Fatty Liver Disease Fibrosis Score in the longitudinal risk assessment of liver-related events (C-indices>0.71) and overall mortality (C-indices>0.65). CONCLUSIONS: This study supports the potential use of serum ferritin values for predicting the long-term prognosis of patients with MASLD.

Accuracy, Reliability, and Comprehensibility of ChatGPT-Generated Medical Responses for Patients With Nonalcoholic Fatty Liver Disease.

Nonalcoholic fatty liver disease (NAFLD) is an increasing global health problem and is expected to become the leading indication for liver transplantation.1 There are no approved NAFLD-specific pharmacotherapies, and lifestyle modification is the primary recommended therapy.2 Innovative approaches to facilitate the implementation and long-term maintenance of lifestyle changes are needed to address the challenging and complex nature of the management of NAFLD, which recently was renamed as metabolic dysfunction-associated steatotic liver disease, to overcome the limitations and stigma of the previous name.3,4 Artificial intelligence (AI)-powered chatbots have been shown to provide effective personalized support and education to patients, with the potential to complement health care resources. The OpenAI Foundation's AI chatbot, Chat Generative Pretrained Transformer (ChatGPT), has attracted worldwide attention for its remarkable performance in question-answer tasks.5-7 This study evaluated the accuracy, completeness, and comprehensiveness of chatGPT's responses to NAFLD-related questions, with the aim of assessing its performance in addressing patients' queries about the disease and lifestyle behaviors.

Chronic liver disease-associated severe thrombocytopenia in Spain: Results from a retrospective study using machine learning and natural language processing.

BACKGROUND: Patients with chronic liver disease (CLD) often develop thrombocytopenia (TCP) as a complication. Severe TCP (platelet count<50×109/L) can increase morbidity and complicate CLD management, increasing bleeding risk during invasive procedures. OBJECTIVES: To describe the real-world scenario of CLD-associated severe TCP patients' clinical characteristics. To evaluate the association between invasive procedures, prophylactic treatments, and bleeding events in this group of patients. To describe their need of medical resource use in Spain. METHODS: This is a retrospective, multicenter study including patients who had confirmed diagnosis of CLD and severe TCP in four hospitals within the Spanish National Healthcare Network from January 2014 to December 2018. We analyzed the free-text information from Electronic Health Records (EHRs) of patients using Natural Language Processing (NLP), machine learning techniques, and SNOMED-CT terminology. Demographics, comorbidities, analytical parameters and characteristics of CLD were extracted at baseline and need for invasive procedures, prophylactic treatments, bleeding events and medical resources used in the follow up period. Frequency tables were generated for categorical variables, whereas continuous variables were described in summary tables as mean (SD) and median (Q1-Q3). RESULTS: Out of 1,765,675 patients, 1787 had CLD and severe TCP; 65.2% were male with a mean age of 54.7 years old. Cirrhosis was detected in 46% (n=820) of patients and 9.1% (n=163) had hepatocellular carcinoma. Invasive procedures were needed in 85.6% of patients during the follow up period. Patients undergoing procedures compared to those patients without invasive procedures presented higher rates of bleeding events (33% vs 8%, p<0.0001) and higher number of bleedings. While prophylactic platelet transfusions were given to 25.6% of patients undergoing procedures, TPO receptor agonist use was only detected in 3.1% of them. Most patients (60.9%) required at least one hospital admission during the follow up and 14.4% of admissions were due to bleeding events with a hospital length of stay of 6 (3, 9) days. CONCLUSIONS: NLP and machine learning are useful tools to describe real-world data in patients with CLD and severe TCP in Spain. Bleeding events are frequent in those patients who need invasive procedures, even receiving platelet transfusions as a prophylactic treatment, increasing the further use of medical resources. Because that, new prophylactic treatments that are not yet generalized, are needed.