Evaluation of D-dimer and prothrombin time in alcohol related liver cirrhosis with comparison of machine learning analyses

OBJECTIVES

Liver cirrhosis (LC) can be caused by obesity, alcohol consumption, viral infection, and autoimmune disease. Early diagnosis and management of LC is important for patient quality of life. Non-invasive diagnostic methods are useful for predicting the current status and mortality risk of LC. The purpose of this study is to identify relevant diagnostic factors measured in routine laboratory test of alcohol-related liver cirrhosis (ALC) patients.

METHODS

This study analyzed data from 127 patients with ALC, including their laboratory test results and clinical information, including coagulation parameters, hematologic parameters, and biochemical parameters. These data were used to compare the performance of the prediction models from three machine learning algorithms including K-nearest neighbor (KNN), support vector machine (SVM), and random forest (RF).

RESULTS

Higher Model for End-stage Liver Disease (MELD) score were associated with prothrombin time (PT) and D-dimer. Logistic and multiple linear regression analyses revealed significant factors predicting mortality in the MELD group. Machine learning approaches were used to predict death in ALC patients using some laboratory parameters associated with mortality. The prediction model based on SVM exhibited better prediction performance than others.

CONCLUSION

PT and D-dimer were the factors that were most strongly associated with 90-day mortality, and machine learning methods can create prediction models with good predictive power.

Advancements in metabolic-associated steatotic liver disease research: Diagnostics, small molecule developments, and future directions

Metabolic (dysfunction)-associated steatotic liver disease (MASLD), formerly known as nonalcoholic fatty liver disease, is a growing global health concern with no approved pharmacological treatments. At the same time, there are no standard methods to definitively screen for the presence of MASLD because of its progressive nature and symptomatic commonality with other disorders. Recent advances in molecular understanding of MASLD pathophysiology have intensified research on development of new drug molecules, repurposing of existing drugs approved for other indications, and an educated use of dietary supplements for its treatment and prophylaxis. This review focused on depicting the latest advancements in MASLD research related to small molecule development for prophylaxis or treatment and diagnosis, with emphasis on mechanistic basis at the molecular level.

Performance Evaluation of a Novel Non-Invasive Test for the Detection of Advanced Liver Fibrosis in Metabolic Dysfunction-Associated Fatty Liver Disease

Metabolic dysfunction-associated fatty liver disease (MAFLD) may progress to advanced liver fibrosis (ALF). We evaluated the diagnostic accuracy of a novel Liver Fibrosis Risk Index (LFRI) in MAFLD subjects using transient elastography (TE) as the reference method for liver fibrosis measurement and then the diagnostic performance of a new two-step non-invasive algorithm for the detection of ALF risk in MAFLD, using Fibrosis-4 (FIB-4) followed by LFRI and comparing it to the reference algorithm based on FIB-4 and TE. We conducted a prospective study on 104 MAFLD European adult subjects. All consenting subjects underwent TE and measurements of FIB-4 and LFRI. For FIB-4 and TE, validated cut-offs were used. An ROC analysis showed that LFRI diagnosed severe fibrosis with moderate accuracy in MAFLD subjects with a negative predictive value above 90%. Using the new algorithm with LFRI thresholds recommended by the manufacturer, the number of subjects classified into ALF risk groups (low, intermediate, or high) differed significantly when compared with the reference algorithm (p = 0.001), with moderate agreement between them (weighted kappa (95% CI) = 0.59 (0.41-0.77)). To improve the performance of the LFRI-based algorithm, we modified cut-off points based on ROC curves obtained by dividing the study population according to the reference algorithm and observed no difference between algorithms (p = 0.054) in categorizing ALF risk, with a slight increase in the total agreement (weighted kappa (95% CI) = 0.63 (0.44-0.82)). Our findings suggest that using the novel LFRI as a second-line test may represent a potential alternative for liver fibrosis risk stratification in MAFLD patients; however, modified cut-offs are needed to optimize its performance.

Analytical performance of the Enhanced Liver Fibrosis (ELF) Test on the Atellica IM Analyzer

BACKGROUND

The Enhanced Liver Fibrosis (ELFTM) Test comprises 3 direct serum markers of fibrosis-hyaluronic acid (HA), amino-terminal pro-peptide of type III procollagen (PIIINP), and tissue inhibitor of matrix metalloproteinase 1 (TIMP-1)-whose results are combined in an algorithm to generate the ELF score. Outside the U.S., the ELF Test and score are CE marked for assessment of liver fibrosis severity in patients with signs, symptoms, or risk factors of chronic liver disease to support diagnosis of fibrosis staging or prognosis for likelihood of progression to cirrhosis and liver-related clinical events. In the U.S., the FDA granted de novo marketing authorization to aid prognostic evaluation of disease progression (to cirrhosis and liver-related clinical events) in nonalcoholic steatohepatitis patients with advanced liver fibrosis. We describe the analytical performance of the ELF analytes and score on the Atellica® IM Analyzer.

METHODS

Clinical and Laboratory Standards Institute protocols were followed for detection capability (limits of blank [LoB], detection [LoD], and quantitation [LoQ]), precision, interference, linearity, hook effect, and ELF reference interval.

RESULTS

All parameters met predetermined requirements: HA (LoB 1.00 ng/mL, LoD 2.00 ng/mL, LoQ 3.00 ng/mL); PIIINP (LoB 0.50 ng/mL, LoD 0.75 ng/mL, LoQ 1.00 ng/mL); TIMP-1 (LoB 3.0 ng/mL, LoD 4.0 ng/mL, LoQ 5.0 ng/mL). Across the 3 assays, repeatability was ≤5.4% CV; within-lab precision was ≤8.5% CV. ELF score repeatability was ≤0.6% CV, within-lab precision ≤1.3% CV, and reproducibility ≤1.1% CV. Good correlation was obtained between the Atellica IM ELF and ADVIA Centaur ELF Tests (y = 1.01x - 0.22, r = 0.997). Assays were linear across analytical measuring ranges.

CONCLUSIONS

Analytical performance validation results for the ELF Test and ELF score were excellent making the test acceptable for routine clinical use.

Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study

BACKGROUND AND AIMS

Detecting NASH remains challenging, while at-risk NASH (steatohepatitis and F≥ 2) tends to progress and is of interest for drug development and clinical application. We developed prediction models by supervised machine learning techniques, with clinical data and biomarkers to stage and grade patients with NAFLD.

APPROACH AND RESULTS

Learning data were collected in the Liver Investigation: Testing Marker Utility in Steatohepatitis metacohort (966 biopsy-proven NAFLD adults), staged and graded according to NASH CRN. Conditions of interest were the clinical trial definition of NASH (NAS ≥ 4;53%), at-risk NASH (NASH with F ≥ 2;35%), significant (F ≥ 2;47%), and advanced fibrosis (F ≥ 3;28%). Thirty-five predictors were included. Missing data were handled by multiple imputations. Data were randomly split into training/validation (75/25) sets. A gradient boosting machine was applied to develop 2 models for each condition: clinical versus extended (clinical and biomarkers). Two variants of the NASH and at-risk NASH models were constructed: direct and composite models.Clinical gradient boosting machine models for steatosis/inflammation/ballooning had AUCs of 0.94/0.79/0.72. There were no improvements when biomarkers were included. The direct NASH model produced AUCs (clinical/extended) of 0.61/0.65. The composite NASH model performed significantly better (0.71) for both variants. The composite at-risk NASH model had an AUC of 0.83 (clinical and extended), an improvement over the direct model. Significant fibrosis models had AUCs (clinical/extended) of 0.76/0.78. The extended advanced fibrosis model (0.86) performed significantly better than the clinical version (0.82).

CONCLUSIONS

Detection of NASH and at-risk NASH can be improved by constructing independent machine learning models for each component, using only clinical predictors. Adding biomarkers only improved the accuracy of fibrosis.

NAFLD and NASH biomarker qualification in the LITMUS consortium - Lessons learned

Biomarkers have the potential to accelerate drug development, as early indicators of improved clinical response, to improve patient safety, and for personalised medicine. However, few have been approved through the biomarker qualification pathways of the regulatory agencies. This paper outlines how biomarkers can accelerate drug development, and reviews the lessons learned by the EU IMI2-funded LITMUS consortium, which has had several interactions with regulatory agencies in both the US and EU regarding biomarker qualification in patients with non-alcoholic fatty liver disease and non-alcoholic steatohepatitis. Sharing knowledge of such interactions with the scientific community is of paramount importance to increase the chances of qualification of relevant biomarkers that may accelerate drug development, and thereby help patients, across disease indications. A qualified biomarker enables a decision to be made that all understand and support in a common framework.

Fibroblast Growth Factors for Nonalcoholic Fatty Liver Disease: Opportunities and Challenges

Nonalcoholic fatty liver disease (NAFLD), a chronic condition associated with metabolic dysfunction and obesity, has reached epidemic proportions worldwide. Although early NAFLD can be treated with lifestyle changes, the treatment of advanced liver pathology, such as nonalcoholic steatohepatitis (NASH), remains a challenge. There are currently no FDA-approved drugs for NAFLD. Fibroblast growth factors (FGFs) play essential roles in lipid and carbohydrate metabolism and have recently emerged as promising therapeutic agents for metabolic diseases. Among them, endocrine members (FGF19 and FGF21) and classical members (FGF1 and FGF4) are key regulators of energy metabolism. FGF-based therapies have shown therapeutic benefits in patients with NAFLD, and substantial progress has recently been made in clinical trials. These FGF analogs are effective in alleviating steatosis, liver inflammation, and fibrosis. In this review, we describe the biology of four metabolism-related FGFs (FGF19, FGF21, FGF1, and FGF4) and their basic action mechanisms, and then summarize recent advances in the biopharmaceutical development of FGF-based therapies for patients with NAFLD.

Clinical importance of laboratory biomarkers in liver fibrosis

Hepatic cirrhosis is a major health problem across the world, causing high morbidity and mortality. This disease has many etiologies, yet the result of chronic hepatic injury is hepatic fibrosis causing cirrhosis and hepatocellular carcinoma, as the liver’s architecture is progressively destroyed. While liver biopsy is currently the gold standard for fibrosis staging, it has significant disadvantages, leading to a growing interest in non-invasive markers. Direct biomarkers – hyaluronic acid, laminin, collagen type III N-peptide, type IV collagen and cholylglycine – are new and rarely applied in routine clinical practice. This is the case primarily because there is no general consensus regarding the clinical application and effectiveness of the individual biomarkers. The usage of these markers in routine clinical practice could be advantageous for patients with liver fibrosis, requiring a simple blood test instead of a biopsy. The former option would be especially attractive for patients who are contraindicated for the latter. This review summarizes recent findings on direct biomarkers of liver fibrosis and highlights their possible applications and potential benefit for liver fibrosis diagnostics and/or staging.

Serum biomarkers for liver fibrosis

Liver fibrosis is a common pathway in most chronic liver diseases, characterized by excessive extracellular matrix accumulation. Without treatment, fibrosis will ultimately result in cirrhosis, portal hypertension, and even liver failure. It is considered that liver fibrosis is reversible while cirrhosis is not, making it significant to diagnose and evaluate liver fibrogenesis timely. As the gold standard, liver biopsy is imperfect due to its invasiveness and sampling error. Therefore, attempts at uncovering noninvasive tests have become a hot topic in liver fibrosis. Nowadays, as an important category of noninvasive tests, serum biomarkers, which are safer, convenient, repeatable, and more acceptable, are widely discussed and commonly used in clinical practice. Serum biomarkers of liver fibrosis can be divided into class I (direct) and classⅡ (indirect) markers. However, the diagnostic efficiency still varies among studies. This article summarizes the most established and newly discovered serum biomarkers for hepatic fibrogenesis.

Diagnostic value of HA, PC-III, IV-C, and LN in infants with congenital biliary atresia

Hyaluronic acid (HA), type III procollagen III (PC-III), type IV collagen IV (IV-C), and laminin (LN) have certain diagnostic value for hepatobiliary diseases. No published studies have compared the diagnostic accuracy of these 4 indicators for the diagnosis of congenital biliary atresia (CBA) in infants. This study aimed to investigate the diagnostic value of HA, PC-III, IV-C, and LN in infants with CBA. From January 2017 to December 2020, 185 infants with nonphysiological jaundice in the Second Department of General Surgery at the Children's Hospital of Hebei were enrolled in this study. Forty-six infants with CBA (CBA group) and 139 infants without CBA (noncongenital biliary atresia group) were diagnosed using ultrasonography, magnetic resonance imaging, intraoperative exploration, and intraoperative cholangiography. The levels of HA, PC-III, IV-C, and LN in the 2 groups were statistically analyzed. The diagnostic accuracy was determined using receiver operating characteristic curves and by calculating the area under the curve. Univariate and multivariate logistic regression analyses were performed to identify the independent risk factors. Compared to the noncongenital biliary atresia group, the levels of HA, PC-III, IV-C, and LN were significantly increased in the CBA group (P <.05). The receiver operating characteristic analysis showed the optimal cutoff values for HA, PC-III, IV-C, and LN were 162.7, 42.5, 199.7, and 101.2 ng/mL, and the area under the curves were 0.892, 0.762, 0.804, and 0.768, respectively. The sensitivity values for the diagnosis of CBA were 76.82%, 71.61%, 70.32%, and 72.28%, and the specificity values for the diagnosis of biliary atresia were 70.22%, 70.44%, 66.34%, and 68.71%, respectively. In the multivariate model, HA ≥162.7 ng/mL (odds ratio [OR] = 5.28, 95% confidence interval [CI]: 3.15-8.37), PC-III ≥42.5 ng/mL (OR = 4.61, 95% CI: 2.54-7.16), IV-C ≥199.7 ng/mL (OR = 5.02, 95% CI: 2.98-7.64), and LN ≥101.2 ng/mL (OR = 6.25, 95% CI: 2.41-10.07) remained associated with the occurrence of CBA. HA, PC-III, IV-C, and LN have high accuracy for the diagnosis of CBA in infants, and these factors are potential diagnostic biomarkers for CBA.

MicroRNA-15a inhibits hepatic stellate cell activation and proliferation via targeting SRY-box transcription factor 9

Accumulating research have indicated that microRNAs are associated with the progression of hepatic fibrosis (HF). Nevertheless, the biological role and function of microRNA (miR)-15a in HF are still unknown. Our data revealed that miR-15a expression was decreased in TGF-β1-treated LX-2 cells and CCl₄-induced mouse model. Additionally, miR-15a could directly target the 3’‑untranslated region of SRY-box transcription factor 9 (SOX9) to inhibit its expression. miR-15a overexpression attenuated the viability and invasion, but enhanced apoptosis in LX-2 cells. However, miR-15a knockdown had the opposite effects. Interestingly, SOX9 overexpression reversed the changes in cell viability, invasion and apoptosis mediated by miR-15a overexpression. Moreover, the miR-15a overexpression-mediated collagen I and alpha smooth muscle actin (a-SMA) downregulation were reversed by SOX9 overexpression. Overall, miR-15a could inhibit LX-2 cell viability and HF pathogenesis by targeting SOX9 in vitro and in vivo.

Fatty Liver through the Ages- Non-Alcoholic Steatohepatitis (NASH)

BACKGROUND

The global epidemic of obesity and type 2 diabetes mellitus is the main driver of the growing global prevalence of non-alcoholic fatty liver disease (NAFLD). We aimed to review the current literature on NAFLD and NASH as it impacts children and adults.

METHODS

We performed a literature search on fatty liver specifically non-alcoholic fatty liver disease (NAFLD) and non-alcoholic steatohepatitis (NASH) among children and adults.

RESULTS

The prevalence of NAFLD in children ranges from 8%-12% while the prevalence in adults ranges 25%-48%. The prevalence of NASH among children with NAFLD is 23% while it ranges from 13% to 65% in the adults. There are similar risk factors for NAFLD among children and adults. However, in children, the diagnostic tests in the studies of NAFLD are limited to elevation of ALT level or a liver biopsy. In adults, additional diagnostic modalities, including non-invasive tests (NITs), have been used. From the spectrum of NAFLD, those with NASH are predominantly at risk of progressive liver disease to cirrhosis and liver-related mortality. NAFLD is associated with impairment of health-related quality of life and substantial economic burden.

CONCLUSION

The comprehensive burden (clinical, HRQL and economic) of NAFLD is high and increasing.

Soluble biomarkers for diagnosis, monitoring, and therapeutic response assessment in psoriasis

BACKGROUND

Psoriasis is an inflammatory disease associated with multiple comorbidities. Biomarkers for the assessment of psoriasis, its associated comorbidities, and the therapeutic response are not well characterized. A number of possible biomarkers for the diagnosis and monitoring of psoriasis have been proposed.

PURPOSE

To assess potential biomarkers for diagnosis of psoriasis, its associated comorbidities and response to treatment.

METHODS

We investigated medical databases from 2000 to 2021 and assessed relevant research. In this review, we evaluated the important biomarkers to help predict potential risk of psoriasis and disease activity (Beta-defensin-2, VEGF, Lipocalin-2, and YKL-40) and its possible inflammatory-related comorbidities like cardiovascular diseases (hs-CRP, GlycA, Psoriasin, IL-18, NT-proBNP, and Adipokines). In addition, we described the potential biomarkers for psoriatic arthritis (CXCL10, S100A8 and S100A9, and MicroRNA) and related manifestations such as enthesitis. Finally, we discussed novel markers for monitoring the response to specific treatments (HLA-C 06, PLC, TARC, NLR, and PLR) as well as potentially useful biomarkers for evaluation of therapy-associated adverse events (liver fibrosis-related markers).

CONCLUSION

A wide range of genetic, tissue and serum markers have been investigated in psoriasis; however, most of them are not used in routine clinical practice; and thorough physical examination along with the appropriate application of clinical scoring systems like Psoriasis Area and Severity Index (PASI) score are still of particular importance.

The Enhanced Liver Fibrosis Index Predicts Hepatic Fibrosis Superior to FIB4 and APRI in HIV/HCV Infected Patients

BACKGROUND

Accurate noninvasive biomarkers of fibrotic progression are important for hepatitis C virus (HCV) management, but commonly used modalities may have decreased efficacy in human immunodeficiency virus (HIV)/HCV-coinfected persons. The enhanced liver fibrosis (ELF) index is a highly sensitive noninvasive marker of hepatic fibrosis that has had limited assessment in the HIV/HCV population. We compared ELF index performance to FIB4 and aspartate to platelet ratio index (APRI) at different stages of liver fibrosis as determined by liver histology, and validated the efficacy of the three noninvasive biomarkers in HIV/HCV-coinfected versus HCV-monoinfected.

METHODS

The ELF index was determined in 147 HIV/HCV-coinfected and 98 HCV-monoinfected persons using commercial ELISA assays for the component elements of the index. Area under the receiver-operator curve was used to validate ELF and to compare its performance to liver histology as well as to other noninvasive biomarkers of liver fibrosis, FIB4, and APRI.

RESULTS

The ELF index increased with histological stage of liver fibrosis and exhibited a linear relationship with Metavir score in all subjects. ELF performance was comparable between HIV/HCV and HCV with advanced liver fibrosis/cirrhosis. In the HIV/HCV cohort ELF cutoffs of 8.45 and 9.23 predicted mild and moderate fibrosis with 85% sensitivity, whereas the ELF cutoff of 9.8 had the highest specificity for advanced fibrosis and the cutoff of 10.4 was 99% specific for cirrhosis. ELF performance was superior to FIB4 and APRI in all subjects regardless of HIV status.

CONCLUSIONS

ELF index demonstrated excellent characteristics toward accurate prediction of liver fibrosis and cirrhosis with superior performance to APRI and FIB4 in HIV/HCV coinfection. Applying this noninvasive biomarker index for diagnosis of liver fibrosis and progression in HIV/HCV is warranted.

Prostate cancer survivors with symptoms of radiation cystitis have elevated fibrotic and vascular proteins in urine

Radiation for pelvic cancers can result in severe bladder damage and radiation cystitis (RC), which is characterized by chronic inflammation, fibrosis, and vascular damage. RC development is poorly understood because bladder biopsies are difficult to obtain. The goal of this study is to gain understanding of molecular changes that drive radiation-induced cystitis in cancer survivors using urine samples from prostate cancer survivors with history of radiation therapy. 94 urine samples were collected from prostate cancer survivors with (n = 85) and without (n = 9) history of radiation therapy. 15 patients with radiation history were officially diagnosed with radiation cystitis. Levels of 47 different proteins were measured using Multiplex Luminex. Comparisons were made between non-irradiated and irradiated samples, and within irradiated samples based on radiation cystitis diagnosis, symptom scores or hematuria. Statistical analysis was performed using Welch’s t-test. In prostate cancer survivors with history of radiation therapy, elevated levels of PAI 1, TIMP1, TIMP2, HGF and VEGF-A were detected in patients that received a radiation cystitis diagnosis. These proteins were also increased in patients suffering from hematuria or high symptom scores. No inflammatory proteins were detected in the urine, except in patients with gross hematuria and end stage radiation cystitis. Active fibrosis and vascular distress is detectable in the urine through elevated levels of associated proteins. Inflammation is only detected in urine of patients with end-stage radiation cystitis disease. These results suggest that fibrosis and vascular damage drive the development of radiation cystitis and could lead to the development of more targeted treatments.

Intelligent Liver Function Testing: Working Smarter to Improve Patient Outcomes in Liver Disease

Chronic liver disease (CLD) is a significant health problem affecting millions of people worldwide. In Scotland, CLD is a major cause of premature mortality. Liver function tests (LFTs) are a panel of frequently requested blood tests which may indicate liver disease. However, LFTs commonly contain at least one abnormal result, and abnormalities are rarely investigated to the extent recommended by national guidelines. The intelligent Liver Function Testing (iLFT) pathway is a novel, automated system designed to improve early diagnosis of liver disease. Initial abnormal LFT results trigger a cascade of reflexive testing to help identify the cause of any liver dysfunction. Algorithms combine these results with demographic and clinical data (such as patient age, body mass index, and alcohol intake) and fibrosis estimates to produce an electronic diagnosis and management plan. The pilot trial demonstrated that iLFT increased diagnosis of liver disease whilst remaining cost-effective. As such, iLFT has been fully operational across our region (NHS Tayside, Scotland) since August 2018. In the first year, iLFT generated over 2000 diagnoses from 1824 patient samples with an abnormality in the initial LFTs. The majority of these patients could be safely managed in primary care. iLFT allows maximal value to be obtained from liver blood tests across biochemistry, virology, immunology, and hematology with only minor changes to working practices. ‘Intelligent’, algorithm-led testing pathways break down the barrier between clinical and laboratory medicine and offer solutions to many of the challenges experienced in modern healthcare systems.