Contemporary use of elastography in liver fibrosis and portal hypertension

Development of Cost-Effective Fatty Liver Disease Prediction Models in a Chinese Population: Statistical and Machine Learning Approaches

BACKGROUND

The increasing prevalence of nonalcoholic fatty liver disease (NAFLD) in China presents a significant public health concern. Traditional ultrasound, commonly used for fatty liver screening, often lacks the ability to accurately quantify steatosis, leading to insufficient follow-up for patients with moderate-to-severe steatosis. Transient elastography (TE) provides a more quantitative diagnosis of steatosis and fibrosis, closely aligning with biopsy results. Moreover, machine learning (ML) technology holds promise for developing more precise diagnostic models for NAFLD using a variety of laboratory indicators.

OBJECTIVE

This study aims to develop a novel ML-based diagnostic model leveraging TE results for staging hepatic steatosis. The objective was to streamline the model's input features, creating a cost-effective and user-friendly tool to distinguish patients with NAFLD requiring follow-up. This innovative approach merges TE and ML to enhance diagnostic accuracy and efficiency in NAFLD assessment.

METHODS

The study involved a comprehensive analysis of health examination records from Suzhou Municipal Hospital, spanning from March to May 2023. Patient data and questionnaire responses were meticulously inputted into Microsoft Excel 2019, followed by thorough data cleaning and model development using Python 3.7, with libraries scikit-learn and numpy to ensure data accuracy. A cohort comprising 978 residents with complete medical records and TE results was included for analysis. Various classification models, including logistic regression (LR), k-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), light gradient boosting machine (LightGBM), and extreme gradient boosting (XGBoost), were constructed and evaluated based on the area under the receiver operating characteristic curve (AUROC).

RESULTS

Among the 916 patients included in the study, 273 were diagnosed with moderate-to-severe NAFLD. The concordance rate between traditional ultrasound and TE for detecting moderate-to-severe NAFLD was 84.6% (231/273). The AUROC values for the RF, LightGBM, XGBoost, SVM, KNN, and LR models were 0.91, 0.86, 0.83, 0.88, 0.77, and 0.81, respectively. These models achieved accuracy rates of 84%, 81%, 78%, 81%, 76%, and 77%, respectively. Notably, the RF model exhibited the best performance. A simplified RF model was developed with an AUROC of 0.88, featuring 62% sensitivity and 90% specificity. This simplified model used 6 key features: waist circumference, BMI, fasting plasma glucose, uric acid, total bilirubin, and high-sensitivity C-reactive protein. This approach offers a cost-effective and user-friendly tool while streamlining feature acquisition for training purposes.

CONCLUSIONS

The study introduces a groundbreaking, cost-effective ML algorithm that leverages health examination data for identifying moderate-to-severe NAFLD. This model has the potential to significantly impact public health by enabling targeted investigations and interventions for NAFLD. By integrating TE and ML technologies, the study showcases innovative approaches to advancing NAFLD diagnostics.

Suboptimal reliability of FIB-4 and NAFLD-fibrosis scores for staging of liver fibrosis in general population

Background and Aim

The burden and incidence of liver cirrhosis are increasing worldwide. Early detection of liver fibrosis would help in early interventions and preventing the progression of fibrosis and cirrhosis. The accepted noninvasive markers for liver fibrosis staging, namely fibrosis-4 (FIB-4) and nonalcoholic fatty liver disease fibrosis score (NFS), have shown inconsistent performance for detecting the fibrosis stage. We aimed to evaluate the efficacy of FIB-4 score and NFS for the detection of liver fibrosis in the general population.

Methods

From a general population referred from a single, community-based family-physician clinic, we included study participants between the ages of 45 and 65 years, with no knowledge of liver disease and no record of alcohol consumption. Liver fibrosis was evaluated by the FIB-4 score and NFS using shear wave elastography (SWE) or transient elastography (TE) measurements as a reference.

Results

A total of 76 participants (aged 61.5 ± 0.37 years, 33% females) were included in the study cohort. We observed a nonsignificant correlation between liver stiffness measurement (LSM) and FIB-4 and NFS (r = 0.1, P = 0.37; r = 0.16, P = 0.15, respectively). Our results showed that only 5.2% with FIB-4 >3.25 and 9.7% with NFS >0.675 had LSM >12 kPa. The compatibility of fibrosis staging was 55% between FIB-4 score and LSM and only 18% between NFS and LSM.

Conclusion

We found that FIB-4 and NFS are unreliable tools for liver fibrosis estimation in the general population. There is a need for more reliable noninvasive methods for the early detection of liver fibrosis.

The non-invasive evaluation of liver involvement in patients with cystic fibrosis: A prospective study

BACKGROUND AND AIMS

Porto-sinusoidal vascular disease (PSVD) has been described as the prominent pathology in liver explants of patients with cystic fibrosis (CF), but data outside the transplant setting are lacking. We aimed to investigate the prevalence of portal hypertension (PH) in CF-associated liver disease (CFLD) and develop an algorithm to classify liver involvement in CF patients.

METHODS

This is a cross-sectional study of consecutive paediatric and adult patients in a tertiary centre between 2018 and 2019, who underwent ultrasound, liver (LSM) and spleen stiffness (SSM) measurement. CFLD was defined according to physical examination, liver tests and ultrasound findings. PSVD was likely if there were PH signs in the absence of advanced chronic liver disease (CF-ACLD, LSM <10 kPa). A historical cohort was used to validate the prognostic significance of the new definitions.

RESULTS

Fifty (27.5%) patients met CFLD criteria. At least one sign of PH was found in 47 (26%) patients, but most (81%) had LSM <10 kPa and were likely to have PSVD; only 9 (5%) had CF-ACLD. PSVD and CFLD (LSM <10 kPa) co-existed in most (23/36) cases. In the historical cohort (n = 599 patients), likely PSVD and CFLD+PH were independently associated with a 2-fold and 3.5-fold increase in mortality compared to patients without PH, respectively. In 34 patients with SSM, values <21 and >50 kPa accurately diagnosed specific signs of PH.

CONCLUSIONS

PSVD is the prevailing cause of PH in CF patients. We developed a new diagnostic algorithm based on clinical and elastosonography criteria to classify liver involvement in patients with CF.

Spleen and Liver Stiffness Evaluation by ARFI Imaging: A Reliable Tool for a Short-Term Monitoring of Portal Hypertension?

BACKGROUND

Assessment of hepatic venous pressure gradient (HVPG) is the most reliable, though invasive method for evaluation of portal hypertension. Non-invasive, elastography-based techniques are well established in diagnosis, but not in monitoring of portal hypertension. The aim of our prospective study was to determine the value of acoustic radiation force impulse (ARFI) elastography technique of the liver and spleen in diagnosis and monitoring of portal hypertension.

METHODS

We prospectively assessed portal hypertension by HVPG and corresponding elastography of the liver and spleen in 31 patients with liver cirrhosis and an indication for primary prophylaxis by non-cardio selective beta-blockers. Investigations were performed at baseline and a follow-up visit after 6-8 weeks. To address the known large variability of values for spleen elastography, well-defined corresponding areas in the spleen were used for baseline and follow-up elastography. Sensitivity, specificity, and AUC-ROC values for both spleen and liver elastography monitoring of portal hypertension were calculated.

RESULTS

Liver but not spleen elastography significantly correlated with HVPG results and was suitable for initial evaluation of portal hypertension. However, changes in HVPG results did not show any correlation with alterations of ARFI values from baseline to follow-up visits both for liver and spleen elastography. Spleen stiffness results were not homogeneous across the whole organ differing significantly between the upper, hilar, and bottom placed investigation areas.

CONCLUSIONS

In this prospective study ARFI-based assessment of liver elastography showed itself suitable for initial assessment but not for monitoring of portal hypertension. Spleen elastography was not appropriate for both, evaluation and monitoring of portal hypertension. A possible explanation for this new data that are in some contrast to previously published results is the degree of portal hypertension in our study, a comparatively short follow-up period, and well-defined investigation areas for spleen elastography in repetitive ARFI investigations. This trial is registered with NCT03315767.

Nonalcoholic Fatty Liver Disease and Cardiovascular Disease: Overlapping Mechanisms

Nonalcoholic fatty liver disease (NAFLD) denotes a condition with excess fat in the liver. The prevalence of NAFLD is increasing, averaging > 25% of the Western population. In 25% of the patients, NAFLD progresses to its more severe form: nonalcoholic steatohepatitis and >25% of these progress to cirrhosis following activation of inflammatory and fibrotic processes. NAFLD is associated with obesity, type 2 diabetes, and the metabolic syndrome and represents a considerable and increasing health burden. In the near future, NAFLD cirrhosis is expected to be the most common cause for liver transplantation. NAFLD patients have an increased risk of developing cardiovascular disease as well as liver-related morbidity. In addition, hepatic steatosis itself appears to represent an independent cardiovascular risk factor. In the present review, we provide an overview of the overlapping mechanisms and prevalence of NAFLD and cardiovascular disease.

High-dimensional hepatopath data analysis by machine learning for predicting HBV-related fibrosis

Chronic HBV infection, the main cause of liver cirrhosis and hepatocellular carcinoma, has become a global health concern. Machine learning algorithms are particularly adept at analyzing medical phenomenon by capturing complex and nonlinear relationships in clinical data. Our study proposed a predictive model on the basis of 55 routine laboratory and clinical parameters by machine learning algorithms as a novel non-invasive method for liver fibrosis diagnosis. The model was further evaluated on the accuracy and rationality and proved to be highly accurate and efficient for the prediction of HBV-related fibrosis. In conclusion, we suggested a potential combination of high-dimensional clinical data and machine learning predictive algorithms for the liver fibrosis diagnosis.

Endogenous motion of liver correlates to the severity of portal hypertension

BACKGROUND

Degree of portal hypertension (PH) is the most important prognostic factor for the decompensation of liver cirrhosis and death, therefore adequate care for patients with liver cirrhosis requires timely detection and evaluation of the presence of clinically significant PH (CSPH) and severe PH (SPH). As the most accurate method for the assessment of PH is an invasive direct measurement of hepatic venous pressure gradient (HVPG), the search for non-invasive methods to diagnose these conditions is actively ongoing.

AIM

To evaluate the feasibility of parameters of endogenously induced displacements and strain of liver to assess degree of PH.

METHODS

Of 36 patients with liver cirrhosis and measured HVPG were included in the case-control study. Endogenous motion of the liver was characterized by derived parameters of region average tissue displacement signal (d_antero, d_retro, d_RMS) and results of endogenous tissue strain imaging using specific radiofrequency signal processing algorithm. Average endogenous strain µ and standard deviation σ of strain were assessed in the regions of interest (ROI) (1 cm × 1 cm and 2 cm × 2 cm in size) and different frequency subbands of endogenous motion (0-10 Hz and 10-20 Hz).

RESULTS

Four parameters showed statistically significant (P < 0.05) correlation with HVPG measurement. The strongest correlation was obtained for the standard deviation of strain (estimated at 0-10 Hz and 2 cm × 2 cm ROI size). Three parameters showed statistically significant differences between patient groups with CSPH, but only d_retro showed significant results in SPH analysis. According to ROC analysis area under the curve (AUC) of the σ_{ROI[0…10Hz, 2 cm × 2 cm]} parameter reached 0.71 (P = 0.036) for the diagnosis of CSPH; with a cut-off value of 1.28 μm/cm providing 73% sensitivity and 70% specificity. AUC for the diagnosis of CSPH for µ_{ROI[0…10Hz, 1 cm × 1 cm]} was 0.78 (P = 0.0024); with a cut-off value of 3.92 μm/cm providing 73% sensitivity and 80% specificity. D_retro parameter had an AUC of 0.86 (P = 0.0001) for the diagnosis of CSPH and 0.84 (P = 0.0001) for the diagnosis of SPH. A cut-off value of -132.34 μm yielded 100% sensitivity for both conditions, whereas specificity was 80% and 72% for CSPH and SPH respectively.

CONCLUSION

The parameters of endogenously induced displacements and strain of the liver correlated with HVPG and might be used for non-invasive diagnosis of PH.

cis-4-[18F]fluoro-L-proline Molecular Imaging Experimental Liver Fibrosis

Introduction: Early-stage liver fibrosis is potentially reversible, but difficult to diagnose. Clinical management would be enhanced by the development of a non-invasive imaging technique able to identify hepatic injury early, before end-stage fibrosis ensues. The analog of the amino acid proline, cis-4-[¹⁸F]fluoro-L-proline ([¹⁸F]fluoro-proline), which targets collagenogenesis in hepatic stellate cells (HSC), was used to detect fibrosis.

Methods: Acute steatohepatitis was induced in experimental animals by liquid ethanol diet for 8 weeks, intra-gastric binge feedings every 10th day along with lipopolysaccharide (LPS) injection. The control animals received control diet for 8 weeks and an equivalent volume of saline on the same schedule as the acute steatohepatitis model. First, in vitro cellular experiments were carried out to assess [³H]proline uptake by HSC, hepatocytes and Kupffer cells derived from rats with acute steatohepatitis (n = 14) and controls (n = 14). Next, ex vivo liver experiments were done to investigate unlabeled proline-mediated collagen synthesis and its associated proline transporter expression in acute steatohepatitis (n = 5) and controls (n = 5). Last, in vivo dynamic and static [¹⁸F]fluoro-proline micro-PET/CT imaging was performed in animal models of acute steatohepatitis (n = 7) and control (n = 7) mice.

Results: [³H]proline uptake was 5-fold higher in the HSCs of steatohepatitis rats than controls after incubation of up to 60 min. There was an excellent correlation between [³H]proline uptake and liver collagen expression (r-value > 0.90, p < 0.05). Subsequent liver tissue studies demonstrated 2–3-fold higher proline transporter expression in acute steatohepatitis animals than in controls, and proline-related collagen synthesis was blocked by this transporter inhibitor. In vivo micro-PET/CT studies with [¹⁸F]fluoro-proline showed 2–3-fold higher uptake in the livers of acute steatohepatitis mice than in controls. There was an excellent correlation between [¹⁸F]fluoro-proline uptake and liver collagen expression in the livers of acute steatohepatitis mice (r-value = 0.97, p < 0.001).

Conclusion: [¹⁸F]fluoro-proline localizes in the liver and correlates with collagenogenesis in acute steatohepatitis with a signal intensity that is sufficiently high to allow imaging with micro-PET/CT. Thus, [¹⁸F]fluoro-proline could serve as a PET imaging biomarker for detecting early-stage liver fibrosis.

Liver stiffness in chronic hepatitis C virus infection

INTRODUCTION

The severity of liver fibrosis can be assessed noninvasively today by liver stiffness measurements. Vibration-controlled transient elastography, shear wave elastography or magnetic resonance elastography are techniques increasingly used for this purpose.

METHODS

This article presents the recent advances in the use of new techniques for liver fibrosis assessment in chronic hepatitis C: the correlation between liver stiffness values and liver fibrosis estimated by liver biopsies, the prognosis role of liver stiffness values, their usefulness in monitoring the treatment response, in assessing the severity of portal hypertension and in estimating the presence of esophageal varices. Scientific articles from January 2017 to January 2018 were searched in PubMed and PubMed Central databases, using the terms "liver stiffness" and "hepatitis C".

RESULTS

The median liver stiffness values measured with different techniques are not identical, so that FibroScan thresholds cannot be used on any other elastographic machine. The higher the liver's stiffness measurement, the higher the liver-related events in patients with chronic hepatitis C. A liver stiffness measurement over 17 kPa could be an independent predictor for the presence of esophageal varices as well as a spleen with a longitudinal span ≥ 15 cm for patients with a value of liver stiffness < 17 kPa. A progressive and persistent decrease in liver stiffness is dependent on sustained virological response achievement. The lack of liver stiffness decrease has been associated with relapsers and a low value of liver stiffness at baseline.

CONCLUSION

Liver stiffness provides clues about the severity and evolution of liver disease.

Impact of DARC rs12075 Variants on Liver Fibrosis Progression in Patients with Chronic Hepatitis C: A Retrospective Study

: The Duffy antigen receptor for chemokines (DARC) rs12075 polymorphism regulates leukocyte trafficking and proinflammatory chemokine homeostasis. Hepatitis C virus (HCV)-mediated liver fibrosis is associated with an uncontrolled inflammatory response. In this study, we evaluate the association between the DARC rs12075 polymorphism and liver stiffness progression in HCV-infected patients. We carried out a retrospective cohort study (repeated measures design) in 208 noncirrhotic patients with chronic hepatitis C (CHC) who had at least two liver stiffness measurements (LSM) with a separation of at least 12 months. We used generalized linear models to analyze the association between DARC rs12075 polymorphism and outcome variables. During a follow-up of 46.6 months, the percentage of patients with stages of fibrosis F0/F1 decreased (p < 0.001), while LSM values and the percentage of patients with cirrhosis increased (p < 0.001). This pattern of changes was maintained in each of the groups of patients analyzed according to their rs12075 genotypes (AA or AG/GG). However, the variations in liver stiffness characteristics were lower in patients with the rs12075 AG/GG genotype (AG/GG versus AA). Thereby, in the adjusted analysis, patients with the rs12075 AG/GG genotype had a lower risk of an increased value of LSM2/LSM1 arithmetic mean ratio (AMR = 0.83; p = 0.001) and of an increase in LSM ≥ 5 kPa (odds ratio (OR) = 0.28; p = 0.009). Besides, patients with rs12075 AG/GG had a lower risk of cirrhosis progression (OR = 0.24; p = 0.009). No significant associations were found for an increase in LSM ≥ 10 kPa. We found an association between the DARC rs12075 single nucleotide polymorphism (SNP) and CHC progression. Specifically, patients with the DARC rs12075 AG/GG genotype had a lower risk of liver fibrosis progression and development of cirrhosis.

Prognostic Role of Liver Stiffness Measurements Using Magnetic Resonance Elastography in Patients with Compensated Chronic Liver Disease

PURPOSE

To retrospectively evaluate the prognostic role of liver stiffness (LS) measurement using magnetic resonance elastography (MRE) in patients with compensated chronic liver disease (cCLD).

METHODS

We enrolled 217 patients with cCLD who underwent MRE. After mean follow-up of 45.0 ± 17.6 months, cumulative incidence (CI) of hepatocellular carcinoma (HCC) occurrence, development of decompensation and overall survival (OS) were estimated using the Kaplan-Meier method. Prognostic factors were evaluated using the Cox proportional hazard regression model.

RESULTS

During the follow-up period, HCC occurred in 33 patients, and 1-, 3- and 5-year CIs of HCC occurrence were 3.8%, 14.8% and 18.9%, respectively. The LS value was a significant predictive factor for HCC occurrence [p < 0.001, hazard ratio (HR) = 1.59 per unit (1.25-2.03)]. Eighteen patients experienced hepatic decompensation, and 1-, 3- and 5-year CIs of decompensation were 2.8%, 7.3% and 11.3%, respectively. The LS value was also significantly associated with decompensation development [p < 0.001, HR = 2.02 per unit (1.37-2.98)]. Fourteen patients died, and 1-, 3- and 5-year OSs were 99.1%, 98.0% and 89.8%, respectively. The LS value was demonstrated to be a significant affecting factor for OS [p = 0.008, HR = 1.39 per unit (1.10-1.78)].

CONCLUSIONS

LS obtained from MRE was a significant predictive factor for the development of decompensation, HCC occurrence and OS in cCLD patients.

KEY POINTS

• Liver stiffness (LS) values obtained from MRE can provide prognostic information. • The LS value was a significant predictive factor for occurrence of hepatocellular carcinoma. • The LS value was significantly associated with development of hepatic decompensation. • Survival of compensated chronic liver disease patients was affected by the LS value.

Time-Harmonic Elastography of the Liver is Sensitive to Intrahepatic Pressure Gradient and Liver Decompression after Transjugular Intrahepatic Portosystemic Shunt (TIPS) Implantation

We investigated the correlation between hepatic venous pressure gradient (HVPG) and liver shear wave speed (SWS) measured by multi-frequency time-harmonic ultrasound elastography (THE) before and after transjugular intrahepatic portosystemic shunt (TIPS) implantation. Ten patients with ascites, cirrhotic liver disease and portal hypertension were prospectively examined with invasive HVPG measurement and THE before and after TIPS implantation. HVPG and SWS decreased after TIPS placement from 20.4 ± 2.2 mmHg to 9.8 ± 4.1 mmHg (mean ± standard deviation) and from 3.87 ± 0.54 m/s to 3.27 ± 0.44 m/s. Mean reduction HVPG was -10.6 ± 3.7 mmHg, p < 0.001; mean reduction SWS was -0.60 ± 0.29 m/s, p < 0.001. A linear correlation was observed between HVPG and SWS (R = 0.59, p = 0.0061). THE-measured SWS is a first potential direct ultrasound marker for liver decompression following TIPS in ascites-associated cirrhotic liver disease and therefore might be suitable to non-invasively detect portal hypertension.

Shear wave elastography (SWE) of the spleen in patients with hepatitis B and C but without significant liver fibrosis

OBJECTIVE

The aim of the study was to compare the elasticity of the spleen in patients with hepatitis B and C but without liver fibrosis with that of healthy subjects using a shear wave elastography (SWE) examination.

METHODS

Between December 2014 and December 2015, 35 patients with hepatitis B virus (HBV) infections and 45 patients with (hepatitis C virus) HCV infections and liver stiffness below 7.1 kPa were included in the study. The control group was composed of 53 healthy volunteers without any chronic liver disease, with no abnormal findings in their ultrasound examinations and with an SWE of the liver below 6.5 kPa. The SWE measurements were a part of routine ultrasound abdominal examinations. The examinations were performed using an Aixplorer device by two radiologists with at least 6 years' experience. To compare spleen stiffness between the groups, the Mann-Whitney U-test was applied. To analyze the dependency between liver and spleen elasticity, Spearman's rank correlation coefficient was calculated.

RESULTS

A total of 133 SWE findings were analyzed. Stiffness of the spleen was significantly higher in patients with HBV and HCV but without significant liver fibrosis than it was in the healthy controls (p = 0.0018 and 0.0000, respectively). This correlation was also present in patients with liver stiffness below 6.5 kPa (p = 0.0041 and 0.0000, respectively). Analysis revealed no significant correlation between liver and spleen stiffness in patients with hepatitis B and C and without significant fibrosis (p = 0.3216 and 0.0626, respectively).

CONCLUSION

Patients with hepatitis B and C but without significant liver fibrosis have stiffer spleens than healthy controls. There is no dependency between liver and spleen elasticity in patients without significant fibrosis.

ADVANCES IN KNOWLEDGE

The SWE examination might be an important tool and could be used in addition to conventional imaging. Our study may become a starting point in further investigations into the role of the spleen in HCV and HBV infections and perhaps into introducing spleen elastography into diagnostic and follow-up procedures.

Non-invasive Markers of Liver Fibrosis: Adjuncts or Alternatives to Liver Biopsy?

Liver fibrosis reflects sustained liver injury often from multiple, simultaneous factors. Whilst the presence of mild fibrosis on biopsy can be a reassuring finding, the identification of advanced fibrosis is critical to the management of patients with chronic liver disease. This necessity has lead to a reliance on liver biopsy which itself is an imperfect test and poorly accepted by patients. The development of robust tools to non-invasively assess liver fibrosis has dramatically enhanced clinical decision making in patients with chronic liver disease, allowing a rapid and informed judgment of disease stage and prognosis. Should a liver biopsy be required, the appropriateness is clearer and the diagnostic yield is greater with the use of these adjuncts. While a number of non-invasive liver fibrosis markers are now used in routine practice, a steady stream of innovative approaches exists. With improvement in the reliability, reproducibility and feasibility of these markers, their potential role in disease management is increasing. Moreover, their adoption into clinical trials as outcome measures reflects their validity and dynamic nature. This review will summarize and appraise the current and novel non-invasive markers of liver fibrosis, both blood and imaging based, and look at their prospective application in everyday clinical care.