Search

The integration of human and artificial intelligence (AI) in medicine has only recently begun but it has already become obvious that intelligent systems can dramatically improve the management of liver diseases. Big data made it possible to envisage transformative developments of the use of AI for diagnosing, predicting prognosis and treating liver diseases, but there is still a lot of work to do. If we want to achieve the 21 st century digital revolution, there is an urgent need for specific national and international rules, and to adhere to bioethical parameters when collecting data. Avoiding misleading results is essential for the effective use of AI. A crucial question is whether it is possible to sustain, technically and morally, the process of integration between man and machine. We present a systematic review on the applications of AI to hepatology, highlighting the current challenges and crucial issues related to the use of such technologies., Competing Interests: Conflict of interest The research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021. Published by Elsevier Ltd.)

Whereas the doubling time of overall biomedical knowledge bases has been estimated at about 19 years, the body of indexed information related to HBV has doubled in the last 8 years; the one related to HBV and antivirals has doubled in the last 5 years and the one related to Interferon and contraindications has doubled in less than 48 months. In Hepatology, as well as in other fast changing areas of medicine, the demand that clinical decision should always be based on the best verified knowledge available, is becoming more and more difficult to comply with. The Italian network of competence for hepatic diseases (Liver Unit Networks Association or LUNA) was established in 2003 with the patronage of the Italian Ministry of Health, with the primary goal of promoting advanced clinical research and real-time information exchange among the participating centres, facilitating knowledge sharing and identification of best practices. The ICT infrastructure designed for this purpose includes four sets of online accessible software tools:

Hepatitis B "e" antigen (HBeAg) negative chronic hepatitis B (CHB), 40 years since discovery in the Mediterranean area, has become the most prevalent form of HBV-induced liver disease worldwide and a major health care burden caused by HBV infection. A great deal of knowledge accumulated over the last decades provides consistent evidence on the bimodal dynamics of the expression of structural and non-structural forms of the viral core proteins which associate with different virologic and clinic–pathologic outcomes of HBV infection. In absence of serum HBeAg, the presence and persistence of HBV replication causes and maintains virus-related liver injury. Thus, in clinical practice it is mandatory to screen HBV carriers with HBeAg-negative infection for the early diagnosis of HBeAg-negative CHB since antiviral therapy can cure HBV-induced liver disease when started at early stages. [ABSTRACT FROM AUTHOR]

Objectives: Optimized diagnostic algorithms to detect active infections are crucial to achieving HCV elimination. We evaluated the cost effectiveness and sustainability of different algorithms for HCV active infection diagnosis, in a context of a high endemic country for HCV infection. Methods: A Markov disease progression model, simulating six diagnostic algorithms in the birth cohort 1969‐1989 over a 10‐year horizon from a healthcare perspective was used. Conventionally diagnosis of active HCV infection is through detection of antibodies (HCV‐Ab) detection followed by HCV‐RNA or HCV core antigen (HCV‐Ag) confirmatory testing either on a second sample or by same sample reflex testing. The undiagnosed and unconfirmed rates were evaluated by assays false negative estimates and each algorithm patients' drop‐off. Age, liver disease stages distribution, liver disease stage costs, treatment effectiveness and costs were used to evaluate the quality‐adjusted life‐years (QALYs) and the incremental cost‐effectiveness ratios (ICER). Results: The reference option was Rapid HCV‐Ab followed by second sample HCV‐Ag testing which produced the lowest QALYs (866,835 QALYs). The highest gains in health (QALYs=974,458) was obtained by HCV‐RNA reflex testing which produced a high cost‐effective ICER (€891/QALY). Reflex testing (same sample‐single visit) vs two patients' visits algorithms, yielded the highest QALYs and high cost‐effective ICERs (€566 and €635/QALY for HCV‐Ag and HCV‐RNA, respectively), confirmed in 99.9% of the 5,000 probabilistic simulations. Conclusions: Our data confirm, by a cost effectiveness point of view, the EASL and WHO clinical practice guidelines recommending HCV reflex testing as most cost effective diagnostic option vs other diagnostic pathways. [ABSTRACT FROM AUTHOR]

Summary: Background: An accurate, single‐point differential diagnosis between HBeAg‐negative infection (ENI) and chronic hepatitis B (CHB) is an unmet need. Aims: To assess the diagnostic value of the new hepatitis B core‐related antigen (HBcrAg) assay. Methods: A retrospective anonymised data analysis was performed in a multicentre European (nine centres and six countries) cohort of 1582 consecutive HBsAg‐positive/HBeAg‐negative subjects classified according to EASL guidelines as: 550‐CHB, 710‐ENI and 322‐GZ (grey‐zone, HBV‐DNA <20 000 IU/mL). Results: Mean age was 44 (±13.2 y), 59% were men; HBV genotypes were 15% A, 2% B, 2% C, 45% D, 9% E, 1% F and 26% unknown. Median HBV‐DNA serum levels were 2.2 (1.5‐2.7), 3.5 (3.2‐3.8) and 5.6 (4.8‐6.6) logIU/mL in ENI, GZ and CHB, P < 0.0001. HBsAg serum levels (HBsAgsl) were comparable in CHB and GZ, but lower in ENI (2.9 [2.1‐3.6] logIU/mL), P < 0.0001. HBcrAg serum levels (HBcrAgsl) were <3 logU/mL in 90.7% (644/710) ENI, 75.2% (242/322) GZ and 4.7% (26/550) CHB (P < 0.0001). Median HBcrAgsl were 4.8 (3.9‐5.7), 2.5 (2.0‐2.9) and 2.0 (2.0‐2.5) logU/mL in CHB, GZ and ENI, (P < 0.0001). ROC‐AUCs for HBcrAg and HBsAg were 0.968 (95% CI, 0.958‐0.977) and 0.732 (95% CI, 0.704‐0.760) respectively. The optimal HBcrAgsl cut‐off to distinguish CHB from ENI was 3.14 logU/mL (95% CI, 3.02‐3.25, 91% SE, 93% SP and 92.4% DA). HBcrAgsl were associated with HBV genotypes (P < 0.001, one‐way ANOVA) but using genotype‐specific cut‐offs, HBcrAg DA remained unchanged with overlapping 95% CI. Conclusion: The HBcrAg assay showed high diagnostic performance in the accurate single‐point identification of patients with HBeAg‐negative CHB, independently of HBV genotype. This should prompt future prospective studies to confirm its diagnostic role in clinical practice. [ABSTRACT FROM AUTHOR]

Background & aims: It has yet to be firmly established whether host IFNL3 (IL28B) genotype influences interferon responsiveness in patients with chronic hepatitis B. We investigated associations between single-nucleotide polymorphisms (SNPs) in the IFNL3 region and response to peginterferon alfa-2a in 701 patients enrolled in three large, randomized, international studies. Methods: Responses were defined as hepatitis B surface antigen (HBsAg) loss and/or hepatitis B e antigen (HBeAg) seroconversion plus hepatitis B virus (HBV) DNA <2000 IU/ml in HBeAg-positive patients, and HBsAg loss and/or HBV DNA <2000 IU/ml in HBeAg-negative patients (24 weeks after end of treatment). Associations between treatment response and the number of copies of the poor-response allele at three SNPs (rs8099917, rs12980275, rs12979860) were explored with logistic regression models in Asian and white patients. Results: The HBeAg-positive and -negative populations comprised 465 (92% Asian, 50% HBV genotype C) and 236 (79% Asian, 41% HBV genotype C) patients, respectively, and had respective response rates of 26% and 47%. The IFNL3 genotype was strongly associated with ethnicity. There was no association between IFNL3 genotype and treatment response in HBeAg-positive or -negative patients. Independent predictors of treatment response were: sex, HBV DNA level and alanine aminotransferase level in HBeAg-positive Asian patients; age in HBeAg-negative Asian patients; and HBV DNA in HBeAg-negative white patients. Conclusions: This is the largest analysis to date of associations between IFNL3 genotype and peginterferon response in patients with chronic hepatitis B. The data suggest that IFNL3 polymorphism is not a major determinant of the response to peginterferon alfa-2a in either HBeAg-positive or HBeAg-negative patients. [ABSTRACT FROM AUTHOR]

Background & Aims Methods Results Conclusions There is an unmet need for a reliable and reproducible non‐invasive measure of fatty liver content (FLC) for monitoring steatotic liver disease in clinical practice. Sonographic FLC assessment is qualitative and operator‐dependent, and the dynamic quantification range of algorithms based on a single ultrasound (US) parameter is unsatisfactory.This study aims to develop and validate a new multiparametric algorithm based on B‐mode images to quantify FLC using Magnetic Resonance (MR) values as standard reference.Patients with elevated liver enzymes and/or bright liver at US (N = 195) underwent FLC evaluation by MR and by US. Five US‐derived quantitative features [attenuation rate(AR), hepatic renal‐ratio(HR), diaphragm visualization(DV), hepatic‐portal‐vein‐ratio(HPV), portal‐vein‐wall(PVW)] were combined by mixed linear/exponential regression in a multiparametric model (Steatoscore2.0). One hundred and thirty‐four subjects were used for training and 61 for independent validations; score‐computation underwent an inter‐operator reproducibility analysis.The model is based on a mixed linear/exponential combination of 3 US parameters (AR, HR, DV), modelled by 2 equations according to AR values. The computation of FLC by Steatoscore2.0 (mean ± std, 7.91% ± 8.69) and MR (mean ± std, 8.10% ± 10.31) is highly correlated with a low root mean square error in both training/validation cohorts, respectively (R = 0.92/0.86 and RMSE = 5.15/4.62, p < .001). Steatoscore2.0 identified patients with MR‐FLC≥5%/≥10% with sensitivity = 93.2%/89.4%, specificity = 86.1%/95.8%, AUROC = 0.958/0.975, respectively and correlated with MR (R = 0.92) significantly (p < .001) better than CAP (R = 0.73).Multiparametric Steatoscore2.0 measures FLC providing values highly comparable with MR. It is reliable, inexpensive, easy to use with any US equipment and qualifies to be tested in larger, prospective studies as new tool for the non‐invasive screening and monitoring of FLC. [ABSTRACT FROM AUTHOR]

The relationship between hepatitis B viraemia and intrahepatic HBV nucleocapsid proteins (HBcAg and HBeAg) was studied in 18 patients with chronic hepatitis B. Monoclonal antibodies (MoABs) were obtained in BALB/c mice primed with recombinant HBV nucleocapsid proteins. Four MoABs reacting with recombinant proteins gave positive results in competitive assays. Two reacted as anti-HBc and two as anti-HBe. One of them showed a strong affinity for the cytoplasmic, membrane bound antigen (P23e) of infected hepatocytes while the latter showed a higher specificity for serum HBeAg than for the intraheptic antigen. Anti-HBeMoA Bs had a staining capacity for liver cell nuclei comparable with that of polyclonal antibodies. Overall the anti-HBc MoABs stained the liver cell nuclei in 86% of cases, while anti-HBc MoABs stained in 58% of cases. The hepatoeytc cytoplasm was stained by anti-HBc MoABs and anti-HBe MoABs in 64% and 72% of cases respectively. Not one of 12 control liver biopsies was stained. Viraemia (HBV-DNA) was measured by dot blot hybridization and was correlated with the number of hepatocytes containing the nucleocapsid antigen. The highest levels of HBV-DNA (>108 genomes/ml) were detected in patients with prevalent nuclear staining while the lowest ones were observed in those with prevalent eytoplasmic expression of this antigen. The application of anti-HBV-nueleocapsid MoABs in diagnostics requires careful scrutiny since some are specific for the circulating antigen while others show a higher afffinity for the intrahepatic antigen. [ABSTRACT FROM AUTHOR]

Non-alcoholic fatty liver disease is becoming a global epidemic. The aim of this study was to develop a system for assessing liver fat content based on ultrasound images. Magnetic resonance spectroscopy measurements were obtained in 61 patients and the controlled attenuation parameter in 54. Ultrasound images were acquired for all 115 participants and used to calculate the hepatic/renal ratio, hepatic/portal vein ratio, attenuation rate, diaphragm visualization and portal vein wall visualization. The Steato-score was obtained by combining these five parameters. Magnetic resonance spectroscopy measurements were significantly correlated with hepatic/renal ratio, hepatic/portal vein ratio, attenuation rate, diaphragm visualization and portal vein wall visualization; Steato-score was dependent on hepatic/renal ratio, attenuation rate and diaphragm visualization. Area under the receiver operating characteristic curve was equal to 0.98, with 89% sensitivity and 94% specificity. Controlled attenuation parameter values were significantly correlated with hepatic/renal ratio, attenuation rate, diaphragm visualization and Steato-score; the area under the curve was 0.79. This system could be a valid alternative as a non-invasive, simple and inexpensive assessment of intrahepatic fat. [ABSTRACT FROM AUTHOR]