We described features of hospitalized Covid-19 patients and identified predictors of clinical deterioration. We included patients consecutively admitted at Humanitas Research Hospital (Rozzano, Milan, Italy); retrospectively extracted demographic; clinical; laboratory and imaging findings at admission; used survival methods to identify factors associated with clinical deterioration (defined as intensive care unit (ICU) transfer or death), and developed a prognostic index. Overall; we analyzed 239 patients (29.3% females) with a mean age of 63.9 (standard deviation [SD]; 14.0) years. Clinical deterioration occurred in 70 patients (29.3%), including 41 (17.2%) ICU transfers and 36 (15.1%) deaths. The most common symptoms and signs at admission were cough (77.8%) and elevated respiratory rate (34.1%), while 66.5% of patients had at least one coexisting medical condition. Imaging frequently revealed ground-glass opacity (68.9%) and consolidation (23.8%). Age; increased respiratory rate; abnormal blood gas parameters and imaging findings; coexisting coronary heart disease; leukocytosis; lymphocytopenia; and several laboratory parameters (elevated procalcitonin; interleukin-6; serum ferritin; C-reactive protein; aspartate aminotransferase; lactate dehydrogenase; creatinine; fibrinogen; troponin-I; and D-dimer) were significant predictors of clinical deterioration. We suggested a prognostic index to assist risk-stratification (C-statistic; 0.845; 95% CI; 0.802–0.887). These results could aid early identification and management of patients at risk, who should therefore receive additional monitoring and aggressive supportive care.

Sarcopenia and myosteatosis are common in patients with cirrhosis. This study aimed to determine the prevalence of these muscle changes, their interrelations and their prognostic impact over a 12-month period. We conducted a prospective multicentre study involving 433 patients. Sarcopenia and myosteatosis were evaluated using computed tomography scans. The 1-year cumulative incidence of relevant events was assessed by competing risk analysis. We used a Fine-Gray model adjusted for known prognostic factors, to evaluate the impact of sarcopenia and myosteatosis on mortality, hospitalization, and liver decompensation. At enrolment, 166 patients presented with isolated myosteatosis, 36 with isolated sarcopenia, 135 with combined sarcopenia and myosteatosis and 96 patients showed no muscle changes. The 1-year cumulative incidence of death in patients with either sarcopenia and myosteatosis (13.8%) or isolated myosteatosis (13.4%) was over twice that of patients without muscle changes (5.2%) or with isolated sarcopenia (5.6%). The adjusted subhazard ratio for death in patients with muscle changes was 1.36 (95% CI 0.99, 1.86) (P=0.058). The cumulative incidence of hospitalization was significantly higher in patients with combined sarcopenia and myosteatosis than in patients without muscle changes (adjusted subhazard ratio 1.18, 95% CI 1.04 to 1.35). The cumulative incidence of liver decompensation was greater in patients with combined sarcopenia and myosteatosis (p=0.018) and those with isolated sarcopenia (p=0.046) than in patients without muscle changes. Lastly, we found a strong correlation between function tests and frailty scores with the presence of muscle changes. Myosteatosis, whether alone or combined with sarcopenia, is highly prevalent in patients with cirrhosis and is associated with significantly worse outcomes. The prognostic role of sarcopenia should always be evaluated in relation to the presence of myosteatosis. This study investigates the prognostic role of muscle changes in patients with liver cirrhosis. The novelty of this study is the multicentre, prospective nature and the distinguishing impact of individual muscle changes and their combination on prognosis in cirrhosis. This study highlights the prognostic role of myosteatosis, especially when combined with sarcopenia. On the other hand, the relevance of sarcopenia could be mitigated when considered together with myosteatosis. The implication from these findings is that sarcopenia should never be evaluated individually and that myosteatosis may have a dominant role in the prognosis of patients with liver cirrhosis.

Nonalcoholic fatty liver disease (NAFLD) is a growing epidemic that encompasses three distinct clinical phenotypes: uncomplicated fatty liver, nonalcoholic steatohepatitis (NASH) and NASH‐related cirrhosis with its complications, including hepatocellular carcinoma. To date, no pharmacological treatments have been approved and lifestyle modifications including reduced caloric intake targeting a 7%‐10% weight loss from baseline assessment represent the standard approach. Mediterranean diet has been recommended as the best dietary pattern since it is easy to follow and, independently of caloric intake its nutritional components have beneficial metabolic effects that not only improve steatosis but also risk factors for cardiovascular events, the leading cause of morbidity/mortality in individuals with NAFLD. Other dietary patterns such as ketogenic diet and Dietary Approach to Stop Hypertension (DASH) diet can be used in patients with NAFLD. Recently, intermittent fasting diets have gained popularity among healthy individuals and have been proposed as a safe and effective treatment for the metabolic syndrome in experimental and in a few human studies. In this narrative review, we aim to summarize the evidence for the available dietary approaches for patients with NAFLD.

Large Language Models (LLMs) are transformer‐based neural networks with billions of parameters trained on very large text corpora from diverse sources. LLMs have the potential to improve healthcare due to their capability to parse complex concepts and generate context‐based responses. The interest in LLMs has not spared digestive disease academics, who have mainly investigated foundational LLM accuracy, which ranges from 25% to 90% and is influenced by the lack of standardized rules to report methodologies and results for LLM‐oriented research. In addition, a critical issue is the absence of a universally accepted definition of accuracy, varying from binary to scalar interpretations, often tied to grader expertise without reference to clinical guidelines. We address strategies and challenges to increase accuracy. In particular, LLMs can be infused with domain knowledge using Retrieval Augmented Generation (RAG) or Supervised Fine‐Tuning (SFT) with reinforcement learning from human feedback (RLHF). RAG faces challenges with in‐context window limits and accurate information retrieval from the provided context. SFT, a deeper adaptation method, is computationally demanding and requires specialized knowledge. LLMs may increase patient quality of care across the field of digestive diseases, where physicians are often engaged in screening, treatment and surveillance for a broad range of pathologies for which in‐context learning or SFT with RLHF could improve clinical decision‐making and patient outcomes. However, despite their potential, the safe deployment of LLMs in healthcare still needs to overcome hurdles in accuracy, suggesting a need for strategies that integrate human feedback with advanced model training.