Machine Learning for Short-Term Mortality in Acute Decompensation of Liver Cirrhosis: Better than MELD Score.

Prediction of short-term mortality in patients with acute decompensation of liver cirrhosis could be improved. We aimed to develop and validate two machine learning (ML) models for predicting 28-day and 90-day mortality in patients hospitalized with acute decompensated liver cirrhosis. We trained two artificial neural network (ANN)-based ML models using a training sample of 165 out of 290 (56.9%) patients, and then tested their predictive performance against Model of End-stage Liver Disease-Sodium (MELD-Na) and MELD 3.0 scores using a different validation sample of 125 out of 290 (43.1%) patients. The area under the ROC curve (AUC) for predicting 28-day mortality for the ML model was 0.811 (95%CI: 0.714- 0.907; p < 0.001), while the AUC for the MELD-Na score was 0.577 (95%CI: 0.435-0.720; p = 0.226) and for MELD 3.0 was 0.600 (95%CI: 0.462-0.739; p = 0.117). The area under the ROC curve (AUC) for predicting 90-day mortality for the ML model was 0.839 (95%CI: 0.776- 0.884; p < 0.001), while the AUC for the MELD-Na score was 0.682 (95%CI: 0.575-0.790; p = 0.002) and for MELD 3.0 was 0.703 (95%CI: 0.590-0.816; p < 0.001). Our study demonstrates that ML-based models for predicting short-term mortality in patients with acute decompensation of liver cirrhosis perform significantly better than MELD-Na and MELD 3.0 scores in a validation cohort.

Improved Applicability and Diagnostic Accuracy of the Novel Spleen-Dedicated Transient Elastography Device for High-Risk Esophageal Varices.

Spleen stiffness measurement (SSM) by transient elastography (TE) has been repeatedly demonstrated as the reliable way to rule out the presence of high-risk esophageal varices (HRV). We aimed to evaluate and compare novel vs. standard TE-SSM module performance in diagnosing HRV in patients with compensated advanced chronic liver disease (cACLD). This retrospective study included patients with cACLD; blood data, upper digestive endoscopy performed within 3 months of TE, SSM@50Hz and SSM@100Hz were collected. Overall, 112 patients with cACLD were analyzed (75.9% males, average age of 66, 43.7% alcohol-related chronic liver disease, 22.3% metabolic-associated steatotic liver disease, 6.2% viral hepatitis). Reliable SSM was possible in 80.3% and 93.8% of patients by using SSM@50Hz and SSM@100Hz probe, respectively. At the cut-off 41.8 kPa and 40.9 kPa (Youden), SSM@50Hz and SSM@100Hz had AUROCs of 0.746 and 0.752, respectively, for diagnosing HRV (p = 0.71). At the respective cut-offs, sensitivities for HRV were 92.9% and 100%, resulting in misclassification rates of 7.1% and 0% by using SSM@50Hz and SSM@100Hz. SSM reliably excludes HRV in cACLD patients, with measurements below 41 kPa potentially avoiding EGD in around 50% of cases, with minimal risk of HRV omission. SSM@100Hz demonstrated less measurement failures and no HRV misclassification.

Compensated Advanced Chronic Liver Disease and Steatosis in Patients with Type 2 Diabetes as Assessed through Shear Wave Measurements and Attenuation Measurements.

Patients with type 2 diabetes (T2D) are at risk of developing metabolic dysfunction-associated steatotic liver disease (MASLD). We investigated the prevalence of compensated advanced chronic liver disease (cACLD) and steatosis in patients with T2D using the new non-invasive diagnostic methods of shear wave measurements (SWMs) and attenuation (ATT) measurements in comparison with those of vibration-controlled transient elastography (VCTE) and the controlled attenuation parameter (CAP), which served as the reference methods. Among 214 T2D patients, steatosis at any grade and cACLD were revealed in 134 (62.6%) and 19 (8.9%) patients, respectively. SWMs showed a high correlation with VCTE (Spearman's ρ = 0.641), whereas SWMs produced lower (mean of -0.7 kPa) liver stiffness measurements (LSMs) overall. At a LSM of >11.0 kPa (Youden), SWMs had an AUROC of 0.951 that was used to diagnose cACLD (defined as a LSM of >15 kPa through VCTE) with 84.2% sensitivity and 96.4% specificity. The performance of ATT measurements in diagnosing liver steatosis at any grade (defined as the CAP of ≥274 dB/m) was suboptimal (AUROC of 0.744 at the ATT measurement cut-off of >0.63 dB/cm/MHz (Youden) with 59% sensitivity and 81.2% specificity). In conclusion, the prevalence of liver steatosis and previously unrecognized cACLD in patients with T2D is high and SWMs appear to be a reliable diagnostic method for this purpose, whereas further investigation is needed to optimize the diagnostic performance of ATT measurements.

Proton pump inhibitors use prior to COVID-19 hospitalization is associated with higher Clostridioides difficile infection rate.

BACKGROUND: There are uncertainties regarding associations of prior proton pump inhibitor (PPI) use with susceptibility for COVID-19 and risks associated with SARS-CoV-2 infection. We aimed to evaluate the associations of prior PPI use with outcomes in hospitalized patients with COVID-19. RESEARCH DESIGN AND METHODS: We have retrospectively evaluated a total of 5959 consecutively hospitalized patients with COVID-19 from a tertiary-level institution in the period 3/2020-6/2021. Associations of prior PPI use with outcomes of in-hospital mortality, mechanical ventilation, intensive care unit stay, venous thromboembolism, arterial thrombosis, major bleeding, bacteremia, and Clostridioides difficile infection (C. diff.) were evaluated in entire and case-matched cohorts. RESULTS: Among 5959 evaluated patients, there were 1967 (33%) PPI users. In an entire cohort, prior PPI use was associated with higher in-hospital mortality and higher occurrence of C. diff. Association of prior PPI use with mortality diminished, whereas association with C. diff. persisted after multivariable adjustments. In a matched cohort, prior PPI use was associated only with higher risk of C. diff. but not other outcomes in line with multivariable analysis. CONCLUSIONS: Although prior PPI use might not have a significant impact on clinical course and mortality of SARS-CoV-2 infection, it may predispose patients to the development of complications like higher occurrence of C. diff. and thus substantially impact the course of treatment.

Porto-sinusoidal vascular disease: a new definition of an old clinical entity.

Porto-sinusoidal vascular disease (PSVD) is defined as a vascular liver disease characterized by the absence of cirrhosis and the presence of characteristic histological features, with or without the presence of portal hypertension (PH). Half of the patients with PSVD also have associated disease that may contribute to the development of PSVD. Patients usually remain asymptomatic until complications of PH arise. Variceal bleeding and portal vein thrombosis are major complications associated with PSVD. The treatment is focused on managing complications of PH, mainly through primary prophylaxis of variceal bleeding and treatment of portal vein thrombosis. Currently, there is insufficient evidence to support the use of anticoagulants for thrombosis prevention in these patients. Despite the increase of recognition of PSVD, further research is needed to enable early disease diagnosis, establish optimal screening methods, and develop strategies to slow down disease progression.

Survival after hospital discharge in patients hospitalized for acute coronavirus disease 2019: data on 2586 patients from a tertiary center registry.

AIM: To assess the long-term survival after hospital discharge of patients hospitalized due to coronavirus disease 2019 (COVID-19). METHODS: We retrospectively reviewed data on post-discharge survival of 2586 COVID-19 patients hospitalized in our tertiary hospital from March 2020 to March 2021. RESULTS: Among 2586 patients, 1446 (55.9%) were men. The median age was 70 years, interquartile range (IQR, 60-80). The median Charlson comorbidity index was 4 points, IQR (2-5). The median length of hospital stay was 10 days, IQR (7-16). During a median follow-up of 4 months, 192 (7.4%) patients died. The median survival time after hospital discharge was not reached, and 3-month, 6-month, and 12-month survival rates were 93%, 92%, and 91%, respectively. In a multivariate analysis, mutually independent predictors of worse mortality after hospital discharge were age >75 years, Eastern Cooperative Oncology Group status 4, white blood cell count >7 ×109/L, red cell distribution width >14%, urea on admission >10.5 mmol/L, mechanical ventilation during hospital stay, readmission after discharge, absence of obesity, presence of chronic obstructive pulmonary disease, dementia, and metastatic malignancy (P<0.05 for all). CONCLUSION: Substantial risk of death persists after hospital admission due to COVID-19. Factors related to an increased risk are older age, higher functional impairment, need for mechanical ventilation during hospital admission, parameters indicating more pronounced inflammation, impaired renal function, and particular comorbidities. Interventions aimed at improving patients' functional capacity may be needed.

Short-term outcomes of patients with chronic liver disease hospitalised with COVID-19.

BACKGROUND: Patients with chronic liver disease (CLD) might have an aggravated course after acquisition of coronavirus disease 2019 (COVID-19). AIMS: To analyse the outcomes of patients with CLD who were hospitalised due to COVID-19. METHODS: The medical records of 4014 patients hospitalised because of COVID-19 in a regional referral hospital over a 12-month period were analysed. Patients with CLD were identified based on discharge diagnoses according to the International Classification of Diseases-10th Revision. Patients were followed for 30 days from admission and their outcomes (intensive care unit (ICU) admission, mechanical ventilation (MV) or death) were analysed. RESULTS: Of the 4014 patients, 110 (2.7%) had CLD and 49 (1.2%) had cirrhosis. The median age of CLD patients was 67.5 years, 79 (71.8%) were males, 224 (23.5%) were obese, 56 (50.9%) reported alcohol abuse, 24 (21.8%) had non-alcoholic fatty liver disease, 11 (10%) had viral hepatitis and 98 (89.1%) had pneumonia. The median length of hospitalisation was 12 days; 32 (29.1%) patients required ICU admission and 23 (20.9%) patients required MV, while 43 (39.1%) died. In univariate analysis, patients with cirrhosis (45% vs 73%, hazard ratio (HR) = 2.95; P < 0.001), but not those with non-cirrhotic CLD (74% vs 73%; P > 0.05), experienced worse 30-day survival when compared with age, sex and COVID-19 duration-matched cohorts. In a logistic regression analysis conducted on the overall and matched cohorts, liver cirrhosis, but not CLD, predicted inferior survival independently of age, comorbidities and severity of COVID-19, with a fourfold higher adjusted risk of 30-day mortality. CONCLUSION: Cirrhosis is independently associated with higher 30-day mortality of hospitalised patients with COVID-19.

Clinical and prognostic significance of C-reactive protein to albumin ratio in hospitalized coronavirus disease 2019 (COVID-19) patients : Data on 2309 patients from a tertiary center and validation in an independent cohort.

C­reactive protein (CRP) and albumin are inflammation sensitive parameters that are regulated by interleukin­6 inflammatory pathways. The CRP to albumin ratio (CAR) integrates these two into a potent clinical parameter whose clinical and prognostic association in the context of coronavirus disease 2019 (COVID-19) have not been well defined. We aimed to investigate the clinical and prognostic significance of CAR in the context of COVID-19 infection.We retrospectively analyzed 2309 consecutive COVID-19 patients hospitalized at a tertiary level hospital in the period from March 2020 to March 2021 who had baseline data for a CAR assessment. Findings were validated in an independent cohort of 1155 patients hospitalized from March 2021 to June 2021.The majority of patients (85.8%) had severe or critical COVID-19 on admission. Median CRP, albumin and CAR levels were 91 mg/L, 32 g/L and 2.92, respectively. Higher CAR was associated with a tendency for respiratory deterioration during hospitalization, increased requirement of high-flow oxygen treatment and mechanical ventilation, higher occurrence of bacteriemia, higher occurrence of deep venous thrombosis, lower occurrence of myocardial infarction, higher 30-day mortality and higher postdischarge mortality rates. We defined and validated four CAR prognostic categories (< 1.0, 1.0-2.9, 3.0-5.9 and ≥ 6.0) with distinct 30-day survival. In the series of multivariate Cox regression models we could demonstrate robust prognostic properties of CAR that was associated with inferior 30-day survival independently of COVID-19 severity, age and comorbidities and additionally independently of COVID-19 severity, CURB-65 and VACO index in both development and validation cohorts.The CAR seems to have a good potential to improve prognostication of hospitalized COVID-19 patients.

FibroScan-AST Score Predicts 30-Day Mortality or Need for Mechanical Ventilation among Patients Hospitalized with COVID-19.

BACKGROUND: Liver involvement in Coronavirus disease 2019 (COVID-19) has been recognised. We aimed to investigate the correlation of non-invasive surrogates of liver steatosis, fibrosis and inflammation using transient elastography (TE) and FibroScan-AST (FAST) score with (a) clinical severity and (b) 30-day composite outcome of mechanical ventilation (MV) or death among patients hospitalized due to COVID-19. METHOD: Patients with non-critical COVID-19 at admission were included. Liver stiffness measurement (LSM) and controlled attenuation parameter (CAP) were assessed by TE. Clinical severity of COVID-19 was assessed by 4C Mortality Score (4CMS) and need for high-flow nasal cannula (HFNC) oxygen supplementation. RESULTS: 217 patients were included (66.5% males, median age 65 years, 4.6% with history of chronic liver disease). Twenty-four (11.1%) patients met the 30-day composite outcome. Median LSM, CAP and FAST score were 5.2 kPa, 274 dB/m and 0.31, respectively, and neither was associated with clinical severity of COVID-19 at admission. In multivariate analysis FAST > 0.36 (OR 3.19, p = 0.036), 4CMS (OR 1.68, p = 0.002) and HFNC (OR 7.03, p = 0.001) were independent predictors of adverse composite outcome. CONCLUSION: Whereas LSM and CAP failed to show correlation with COVID-19 severity and outcomes, FAST score was an independent risk factor for 30-day mortality or need for MV.

Prevalence and Prognostic Impact of Deranged Liver Blood Tests in COVID-19: Experience from the Regional COVID-19 Center over the Cohort of 3812 Hospitalized Patients.

BACKGROUND: Derangement of liver blood tests (LBT) is frequent in patients with Coronavirus disease 2019 (COVID-19). We aimed to evaluate (a) the prevalence of deranged LBT as well as their association with (b) clinical severity at admission and (c) 30-day outcomes among the hospitalized patients with COVID-19. METHODS: Consecutive patients with COVID-19 hospitalized in the regional referral center over the 12-month period were included. Clinical severity of COVID-19 at hospital admission and 30-day outcomes (need for intensive care, mechanical ventilation, or death) were analyzed. RESULTS: Derangement of LBT occurred in 2854/3812 (74.9%) of patients, most frequently due to elevation of AST (61.6%), GGT (46.1%) and ALT (33.4%). Elevated AST, ALT, GGT and low albumin were associated with more severe disease at admission. However, in multivariate Cox regression analysis, when adjusted for age, sex, obesity and presence of chronic liver disease, only AST remained associated with the risk of dying (HR 1.5081 and 2.1315, for elevations 1-3 × ULN and >3 × ULN, respectively) independently of comorbidity burden and COVID-19 severity at admission. Patients with more severe liver injury more frequently experienced defined adverse outcomes. CONCLUSIONS: Deranged LBTs are common among patients hospitalized with COVID-19 and might be used as predictors of adverse clinical outcomes.