Artificial Intelligence-Based Opportunities in Liver Pathology-A Systematic Review.

BACKGROUND: Artificial Intelligence (AI)-based Deep Neural Networks (DNNs) can handle a wide range of applications in image analysis, ranging from automated segmentation to diagnostic and prediction. As such, they have revolutionized healthcare, including in the liver pathology field. OBJECTIVE: The present study aims to provide a systematic review of applications and performances provided by DNN algorithms in liver pathology throughout the Pubmed and Embase databases up to December 2022, for tumoral, metabolic and inflammatory fields. RESULTS: 42 articles were selected and fully reviewed. Each article was evaluated through the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool, highlighting their risks of bias. CONCLUSIONS: DNN-based models are well represented in the field of liver pathology, and their applications are diverse. Most studies, however, presented at least one domain with a high risk of bias according to the QUADAS-2 tool. Hence, DNN models in liver pathology present future opportunities and persistent limitations. To our knowledge, this review is the first one solely focused on DNN-based applications in liver pathology, and to evaluate their bias through the lens of the QUADAS2 tool.

Non-invasive diagnosis of alcohol-related steatohepatitis in patients ongoing alcohol withdrawal based on cytokeratin 18 and transient elastography.

BACKGROUND AND AIMS: The diagnosis of alcoholic steatohepatitis (ASH) is based on liver biopsy, which is costly and invasive with non-negligible morbidity. The aim of this study was to evaluate the accuracy of circulating cytokeratin 18 M65 fragment (K18-M65) alone or in association with other markers for the non-invasive diagnosis of ASH in patients ongoing alcohol withdrawal. METHODS: This study examined the serum level of K18-M65 in a test cohort of 196 patients. All patients underwent liver biopsy, transient elastography (TE) and serum collection. The diagnostic accuracy of K18-M65 alone or combined with clinico-biological data was assessed and the best defined cut-offs were validated in an independent validation cohort of 58 patients. RESULTS: K18-M65 had an area under the curve (AUC) of 0.82 (test cohort) and 0.90 (validation cohort). Using two cut-off decision points, K18-M65 was able to classify 46.9% (test cohort) and 34.5% (validation cohort) of patients with 95% sensitivity or specificity. Combining K18-M65, alpha-2-macroglobulin, TE, body mass index, and age, we created a score allowing accurate diagnosis of ASH with an AUC of 0.93 (test cohort) and 0.94 (validation cohort). This new score was able to rule out or rule in the diagnosis of steatohepatitis for probability ≤0.135 or ≥0.667 respectively in more than two-thirds of patients. CONCLUSIONS: We propose a new validated non-invasive score for the diagnosis of ASH in patients ongoing alcohol withdrawal. This score can help to identify patients that may benefit from potential therapeutics or motivate them to reduce alcohol consumption.

Consensus Statement on the definition and classification of metabolic hyperferritinaemia.

Hyperferritinaemia is a common laboratory finding that is often associated with metabolic dysfunction and fatty liver. Metabolic hyperferritinaemia reflects alterations in iron metabolism that facilitate iron accumulation in the body and is associated with an increased risk of cardiometabolic and liver diseases. Genetic variants that modulate iron homeostasis and tissue levels of iron are the main determinants of serum levels of ferritin in individuals with metabolic dysfunction, raising the hypothesis that iron accumulation might be implicated in the pathogenesis of insulin resistance and the related organ damage. However, validated criteria for the non-invasive diagnosis of metabolic hyperferritinaemia and the staging of iron overload are still lacking, and there is no clear evidence of a benefit for iron depletion therapy. Here, we provide an overview of the literature on the relationship between hyperferritinaemia and iron accumulation in individuals with metabolic dysfunction, and on the associated clinical outcomes. We propose an updated definition and a provisional staging system for metabolic hyperferritinaemia, which has been agreed on by a multidisciplinary global panel of expert researchers. The goal is to foster studies into the epidemiology, genetics, pathophysiology, clinical relevance and treatment of metabolic hyperferritinaemia, for which we provide suggestions on the main unmet needs, optimal design and clinically relevant outcomes.

Comparison of reconstruction methods used during liver transplantation in case of a graft with replaced or accessory right hepatic artery: A retrospective study.

Variations in graft arterial anatomy can increase the risk of postoperative hepatic arterial thrombosis (HAT), especially in presence of a replaced or accessory right hepatic artery (RHA). We retrospectively analyzed 223 cases of liver transplantations with the presence of an RHA on the graft. Patient outcomes were compared according to the four different reconstruction methods used: (i) the re-implantation of the RHA into the splenic or gastroduodenal artery (n = 106); (ii) the interposition of the superior mesenteric artery (SMA) (n = 83); (iii) dual anastomosis (n = 24); (iv) use of an aortic patch including the origins of both the SMA and the coeliac trunk (n = 10). A competing risk analysis and Inverse Probability Weighting (IPW) were used. We found that the interposition of the SMA method was associated with a significantly lower incidence of HAT, at 4.8% compared to the re-implantation method at 17.9%, dual anastomosis at 12.5%, and aortic patch at 20%, p = .03. In the competing risk analysis with IPW, the only risk factor for RHA thrombosis was the type of reconstruction. Taking the SMA interposition group as the reference, the sub-hazard ratio (sHR) was 5.05 (CI 95 [1.72; 14.78], p < .01) for the re-implantation group, sHR = 2.37 (CI 95 [0.51; 11.09], p = .27) for the dual anastomosis group and sHR = 2.24 (CI 95 [0.35; 14.33], p = .40) for the aortic patch group. There were no differences for intraoperative transfusion, hospitalization duration (p = .37) or incidence of severe complications (p = .1). The long-term graft (p = .69) and patient (p = .52) survival was not different. In conclusion, the SMA interposition method was associated with a lower incidence of RHA thrombosis.

Diagnosis and Outcomes of Late-Onset Wilson's Disease: A National Registry-Based Study.

BACKGROUND: Wilson's disease (WD) is usually diagnosed in children and young adults; limited data exist on late-onset forms. OBJECTIVE: The aim was to characterize the clinical and paraclinical presentations, therapeutic management, and outcomes in patients with late-onset WD. METHODS: Patients diagnosed with WD after age 40 years were identified from the French Wilson's Disease Registry (FWDR). Clinical, laboratory, and imaging findings and treatment were reported at diagnosis and last follow-up. RESULTS: Forty-five patients were identified (median age: 49, range: 40-64) and placed in three groups according to their clinical presentation: neurological (n = 20, median diagnostic delay: 20 months), hepatic (n = 13, diagnostic delay: 12 months), and family screening (n = 12), all confirmed genetically. Six neurological patients had an atypical presentation (1 torticollis, 2 writer's cramps, 2 functional movement disorders, and 1 isolated dysarthria), without T2/fluid-attenuated inversion recovery brain magnetic resonance imaging (MRI) hyperintensities; 5 of 6 had no Kayser-Fleischer ring (KFR); 5 of 6 had liver involvement. In the neurological group, 84% of patients improved clinically, and 1 developed copper deficiency. In the hepatic group, 77% had cirrhosis; 6 patients required liver transplantation. In the screened group, 43% had mild liver involvement; 3 were not treated and remained stable; 24-h urinary copper excretion was normal in 33% of patients at diagnosis. CONCLUSIONS: In the FWDR, late-onset forms of WD affect 8% of patients, mostly with neurological presentations. Thirty percent of the neurological forms were atypical (isolated long-lasting symptoms, inconspicuous brain MRI, no KFR). With personalized treatment, prognosis was good. This study emphasized that WD should be suspected at any age and even in cases of atypical presentation. © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Drug transporters are implicated in the diffusion of tacrolimus into the T lymphocyte in kidney and liver transplant recipients: Genetic, mRNA, protein expression, and functionality.

Because of a narrow therapeutic index and a wide inter- and intra-patient variability, therapeutic drug monitoring of the immunosuppressant drug tacrolimus (TAC) based on whole-blood concentrations (Cblood) is mandatory in solid organ transplant recipients. Using peripheral blood mononuclear cells concentrations (CPBMC) could improve patient outcomes. The poor correlation between Cblood and CPBMC makes hypothesize that drug transporters are implicated in the intracellular accumulation of TAC. The aim of this work was therefore to clinically study: i) the role of genetic variants and ii) the effect of mRNA and protein expression of 4 drug transporters on the TAC CPBMC/blood ratio. In addition, functional in vitro experiments were performed to mechanistically validate the clinical observations. Genetic variants of ABCB1/P-gp and SLC28A3/CNT3 did not influence TAC CPBMC in liver transplant recipients (LTR). ABCC2/MRP2 at the mRNA level; ABCB1/P-gp, SLC28A3/CNT3 and SLC29A1/ENT1 at the protein level; correlated with the CPBMC/blood in kidney and LTR. In vitro results suing transporter-expressing cells confirmed that TAC is substrate of P-gp but not MRP2, whereas experiments remained inconclusive for CNT3 and ENT1. In conclusion, the genetic-transcription-protein-functional approach presented in this work provides new insights in the understanding of TAC transport at the T lymphocyte plasma membrane.

Patient-reported outcomes and their relation with iron parameters in HFE haemochromatosis during maintenance therapy: A prospective cohort study.

BACKGROUND & AIMS: The standard of care for haemochromatosis is regular phlebotomy in order to maintain low ferritin levels. Many patients report fatigue or joint pain despite serum ferritin within the therapeutic targets. We evaluated Patient-Reported Outcomes, and their relation with iron parameters, in C282Y homozygous patients undergoing maintenance phlebotomy. METHODS: Patients were prospectively enrolled in a French referral care centre. At each phlebotomy, patients completed a numeric fatigue scale, a joint pain questionnaire and SF-36 Mental Component Score (MCS) and Physical Component Score (PCS). Haemoglobin, iron, TS and ferritin were collected concomitantly. RESULTS: About 701 visits were performed in 259 patients. The median fatigue score was 3/10; 171 (66%) patients reported joint pain. Age and worsening of joint pain were associated with fatigue (p < .0001 for both). Female gender (p < .037), age (p < .003), and a decrease of TS (p = .050) were associated with joint pain. Main features associated with PCS <50 were worsening of joint pain and age (p < .001 for both) and TS <20% (p < .02). CONCLUSIONS: Fatigue was independent from iron parameters. The main factor impacting quality of life was joint pain, which was more severe in patients with low TS values. Then, a more precise monitoring of TS should be proposed during haemochromatosis maintenance therapy; while less stringent monitoring of serum ferritin levels could be tested.

A New Pathogenic Missense Variant in a Consanguineous North-African Family Responsible for a Highly Variable Aceruloplasminemia Phenotype: A Case-Report.

Aceruloplasminemia is a rare autosomal recessive inherited disorder. Mutations in the ceruloplasmin gene cause depressed ferroxidase activity leading to iron accumulation. The clinical phenotype is highly variable: anemia, retinopathy, diabetes mellitus, psychiatric disorders, and neurological symptoms including parkinsonian disorders and dementia are the main features of this disease. Characterized by high serum ferritin with low transferrin saturation, aceruloplasminemia uniquely combines brain, liver and systemic iron overload. We report here four new cases of aceruloplasminemia in a consanguineous North-African family. Genetic sequencing revealed a homozygous missense variant c.656T>A in exon 4 of the ceruloplasmin gene, which had been described previously as of "unknown significance" in the dbSNP database and never associated with ACP in the HGMD database. Ferroxidase activity was strongly depressed. Clinical manifestations varied among cases. The proband exhibited mild microcytic anemia, diabetes mellitus, psychosis and parkinsonism, whereas the other cases were asymptomatic or mildly anemic, although high serum ferritin and brain iron deposition were documented in all of them. Therapeutic management was complex. The proband started deferoxamine treatment when already symptomatic and he rapidly declined. In the asymptomatic cases, the treatment was associated with poor tolerance and was discontinued due to anemia requiring red blood cell transfusion. Our series illustrates the need for new therapeutic approaches to aceruloplasminemia.