scholarly journals Noninvasive Evaluation of Portal Hypertension Using a Supervised Learning Technique

2017 ◽  
Vol 2017 ◽  
pp. 1-10 ◽  
Author(s):  
Mindaugas Marozas ◽  
Romanas Zykus ◽  
Andrius Sakalauskas ◽  
Limas Kupčinskas ◽  
Arūnas Lukoševičius
Keyword(s):  
Portal Hypertension ◽  
Supervised Learning ◽  
Evaluation Method ◽  
Clinical Laboratory ◽  
Transient Elastography ◽  
Venous Pressure ◽  
Noninvasive Evaluation ◽  
Noninvasive Methods ◽  
Supervised Learning Algorithms ◽  
Clinically Significant

Portal hypertension (PHT) is a key event in the evolution of different chronic liver diseases and leads to the morbidity and mortality of patients. The traditional reliable PHT evaluation method is a hepatic venous pressure gradient (HVPG) measurement, which is invasive and not always available or acceptable to patients. The HVPG measurement is relatively expensive and depends on the experience of the physician. There are many potential noninvasive methods to predict PHT, of which liver transient elastography is determined to be the most accurate; however, even transient elastography lacks the accuracy to be a perfect noninvasive diagnostic method of PHT. In this research, we are focusing on noninvasive PHT assessment methods that rely on selected best-supervised learning algorithms which use a wide set of noninvasively obtained data, including demographical, clinical, laboratory, instrumental, and transient elastography measurements. In order to build the best performing classification meta-algorithm, a set of 21 classification algorithms have been tested. The problem was expanded by selecting the best performing clinical attributes using algorithm-specific filtering methods that give the lowest error rate to predict clinically significant PHT. The suggested meta-algorithm objectively outperforms other methods found in literature and can be a good substitute for invasive PHT evaluation methods.

Noninvasive Diagnostics for Portal Hypertension: A Comprehensive Review

2020 ◽  
Vol 40 (03) ◽  
pp. 240-255 ◽  
Author(s):  
Mattias Mandorfer ◽  
Virginia Hernández-Gea ◽  
Juan Carlos García-Pagán ◽  
Thomas Reiberger
Keyword(s):  
Portal Hypertension ◽  
Beta Blockers ◽  
Venous Pressure ◽  
Target Population ◽  
Diagnostic Value ◽  
Clinical Settings ◽  
Hepatic Decompensation ◽  
Noninvasive Methods ◽  
Noninvasive Diagnostics ◽  
Clinically Significant

AbstractNoninvasive diagnostics for portal hypertension include imaging and functional tests, as well as blood-based biomarkers, and capture different features of the portal hypertensive syndrome. Definitive conclusions regarding their clinical utility require assessment of their diagnostic value in specific clinical settings (i.e., diagnosing a particular hemodynamic condition within a well-defined target population). Several noninvasive methods are predictive of clinically significant portal hypertension (CSPH; hepatic venous pressure gradient [HVPG] ≥ 10 mm Hg; the threshold for complications of portal hypertension); however, only a minority of them have been evaluated in compensated advanced chronic liver disease (i.e., the target population). Importantly, most methods correlate only weakly with HVPG at high values (i.e., in patients with CSPH). Nevertheless, selected methods show promise for diagnosing HVPG ≥ 16 mm Hg (the cut-off for increased risks of hepatic decompensation and mortality) and monitoring HVPG changes in response to nonselective beta-blockers or etiological treatments. Finally, we review established and potential future clinical applications of noninvasive methods.

Non-invasive methods in the assessment of portal hypertension severity

2021 ◽  
Vol 75 (2) ◽  
pp. 125-133
Author(s):  
Soňa Franková ◽  
Jan Šperl
Keyword(s):  
Portal Hypertension ◽  
Liver Fibrosis ◽  
Shear Wave ◽  
Transient Elastography ◽  
Venous Pressure ◽  
Liver Stiffness ◽  
Invasive Technique ◽  
Hepatic Veins ◽  
Oesophageal Varices ◽  
Non Invasive

Portal hypertension represents a wide spectrum of complications of chronic liver diseases and may present by ascites, oesophageal varices, splenomegaly, hypersplenism, hepatorenal and hepatopulmonary syndrome or portopulmonary hypertension. Portal hypertension and its severity predicts the patient‘s prognosis: as an invasive technique, the portosystemic gradient (HPVG – hepatic venous pressure gradient) measurement by hepatic veins catheterisation has remained the gold standard of its assessment. A reliable, non-invasive method to assess the severity of portal hypertension is of paramount importance; the patients with clinically significant portal hypertension have a high risk of variceal bleeding and higher mortality. Recently, non-invasive methods enabling the assessment of liver stiffness have been introduced into clinical practice in hepatology. Not only may these methods substitute for liver biopsy, but they may also be used to assess the degree of liver fibrosis and predict the severity of portal hypertension. Nowadays, we can use the quantitative elastography (transient elastography, point shear-wave elastrography, 2D-shear-wave elastography) or magnetic resonance imaging. We may also assess the severity of portal hypertension based on the non-invasive markers of liver fibrosis (i.e. ELF test) or estimate clinically signifi cant portal hypertension using composite scores (LSPS – liver spleen stiff ness score), based on liver stiffness value, spleen diameter and platelet count. Spleen stiffness measurement is a new method that needs further prospective studies. The review describes current possibilities of the non-invasive assessment of portal hypertension and its severity.

scholarly journals Insulin resistance in patients with cirrhosis and portal hypertension

2012 ◽  
Vol 302 (12) ◽  
pp. G1458-G1465 ◽  
Author(s):  
Eva Erice ◽  
Elba Llop ◽  
Annalisa Berzigotti ◽  
Juan G. Abraldes ◽  
Ignacio Conget ◽  
...  
Keyword(s):  
Insulin Resistance ◽  
Portal Hypertension ◽  
Endothelial Dysfunction ◽  
Intracellular Signaling ◽  
Venous Pressure ◽  
Portal Pressure ◽  
Model Assessment ◽  
Hepatic Hemodynamics ◽  
Clinically Significant ◽  
The Relationship

Insulin resistance (IR) is involved in the pathogenesis of endothelial dysfunction and is also present in patients with cirrhosis. Intrahepatic endothelial dysfunction plays a major role, increasing hepatic vascular resistance and promoting portal hypertension (PH). In addition, β-adrenergic agonists and insulin share several intracellular signaling pathways. Thus IR may influence the response to β-blockers. This study aimed at evaluating the relationship between IR and hepatic hemodynamics in patients with cirrhosis and with the portal pressure response to acute β-blockade. Forty-nine patients with cirrhosis and PH were included. Hepatic and systemic hemodynamics were measured, and IR was estimated by using the updated homeostasis model assessment (HOMA)-2 index. Patients with HOMA-2 > 2.4 were considered IR. In patients with hepatic venous pressure gradient (HVPG) ≥ 10 mmHg) [clinically significant PH (CSPH)], hemodynamic measurements were performed again 20 min after intravenous propranolol. Mean HOMA-2 index was 3 ± 1.4. Fifty-seven percent of patients had IR. A weak correlation between HOMA-2 index and HVPG was observed. Eighty-six percent of patients had CSPH. HOMA-2 index was an independent predictor of CSPH. However, in patients with CSPH, the correlation between HOMA-2 index and HVPG was lost. HVPG, but not IR, predicted the presence of esophageal varices. Response to propranolol was not different between patients with or without IR. In nondiabetic patients with cirrhosis, HOMA-2 index is directly associated with the presence of CSPH and indirectly with varices, but does not allow either grading HVPG or predicting its response to propranolol.

scholarly journals Noninvasive Evaluation of Liver Fibrosis in a Sample of Putative Inactive HBV Carriers in Rome, Italy

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Marco Delle Monache ◽  
Alessio Petrelli ◽  
Alessandra Rossi ◽  
Roberto Cecere ◽  
Concetta Mirisola ◽  
...  
Keyword(s):  
Liver Disease ◽  
Transient Elastography ◽  
Liver Stiffness ◽  
Demographic Variables ◽  
Hbv Dna ◽  
Noninvasive Evaluation ◽  
Noninvasive Methods ◽  
Hbsag Carriers ◽  
Risk Of Progression ◽  
Outpatient Departments

Background. Noninvasive methods are useful for investigating patients with chronic HBV infection. The severity of liver disease in inactive HBsAg carriers can be noninvasively assessed by transient elastography (TE) alone or in association with biochemical markers of fibrosis. Objectives. The study evaluates the effectiveness of the TE compared to common fibrosis scores (FSs), APRI, Forns Index, and FIB4, for identifying significant fibrosis in Italian and foreigner HBsAg carriers. To investigate the risk of progression of the liver disease, liver stiffness (LS) and HBV-DNA were monitored over time. Methods. Viral load, biochemical parameters, and LS have been retrospectively evaluated in 125 putative inactive HBV carriers, who visited two outpatient departments (Colleferro Hospital and INMP) from 01/03/2014 to 31/12/2019. Differences in clinical, biochemical, and demographic variables between Italians and foreigners were analyzed. 66 of 125 patients were followed up for 24 months by monitoring liver stiffness and HBV-DNA. Results. Mean overall LS was 5.55 ± 1.92 kPa; 18 (14.4%) patients had a LS ≥7.5 kPa. Mean of APRI, Forns, and FIB4 was 0.29 ± 0.11, 4.15 ± 1.63, and 1.16 ± 0.59, respectively. FS did not differ between the patients with LS <7.5 kPa and those with LS ≥7.5 kPa. Italians displayed a significant lower ALT (0.53 ± 0.18 vs. 0.67 ± 0.33, p < 0.05 ) and AST (0.59 ± 0.16 vs. 0.70 ± 0.21, p < 0.01 ) value than foreigners. No differences in LS and HBV-DNA levels were observed. In 66 patients followed up for 24 months, HBV-DNA increased by ≥2000 UI/ml after 12 months in 15 individuals and remained ≥2000 UI/ml after 24 months in 10/15 individuals. 7/10 patients showed LS ≥ 7.5 kPa after 24 months, and 4 of them underwent antiviral therapy for HBV. Patients with HBV-DNA <2000 IU/ml had a significantly lower LS than those with HBV-DNA ≥2000 IU/ml (5.30 ± 1.43 vs. 7.69 ± 1.07, p < 0.0001 ). Conclusions. Analysis shows lower effectiveness of FS vs. TE in the assessment of putative inactive HBV carriers. Furthermore, using FibroScan® and HBV-DNA can identify “false” inactive carriers.

scholarly journals The cut-off value of transient elastography to the value of hepatic venous pressure gradient in alcoholic cirrhosis

2021 ◽  
Vol 27 (1) ◽  
pp. 197-206
Author(s):  
Se Ri Ryu ◽  
Jeong-Ju Yoo ◽  
Seong Hee Kang ◽  
Soung Won Jeong ◽  
Moon Young Kim ◽  
...  
Keyword(s):  
Portal Hypertension ◽  
Pressure Gradient ◽  
Transient Elastography ◽  
Venous Pressure ◽  
Liver Stiffness ◽  
Alcoholic Cirrhosis ◽  
Hepatic Venous Pressure Gradient ◽  
Ratio Score ◽  
Noninvasive Method ◽  
Cutoff Value

Background/Aims: The hepatic venous pressure gradient (HVPG) reflects portal hypertension, but its measurement is invasive. Transient elastography (TE) is a noninvasive method for evaluating liver stiffness (LS). We investigated the correlation between the value of LS, LS to platelet ratio (LPR), LS-spleen diameter-to-platelet ratio score (LSPS) and HVPG according to the etiology of cirrhosis, especially focused on alcoholic cirrhosis.Methods: Between January 2008 and March 2017, 556 patients who underwent HVPG and TE were consecutively enrolled. We evaluated LS, LPR, and LSPS according to the etiology of cirrhosis and analyzed their correlations with HVPG.Results: The LS value was higher in patients with alcoholic cirrhosis than viral cirrhosis based on the HVPG (43.5 vs. 32.0 kPa, P<0.001). There were no significant differences in the LPR or LSPS between alcoholic and viral cirrhosis groups, and the areas under the curves for the LPR and LSPS in subgroups according to HVPG levels were not superior to that for LS. In alcoholic cirrhosis, the LS cutoff value for predicting an HVPG ≥10 mmHg was 32.2 kPa with positive predictive value (PPV) of 94.5% and 36.6 kPa for HVPG ≥12 mmHg with PPV of 91.0%.Conclusions: The LS cutoff value should be determined separately for patients with alcoholic and viral cirrhosis. In alcoholic cirrhosis, the LS cutoff values were 32.2 and 36.6 kPa for predicting an HVPG ≥10 and ≥12 mmHg, respectively. However, there were no significant differences in the LPR or LSPS between alcoholic and viral cirrhosis groups.

Derivation and Validation of a Model to Predict Clinically Significant Portal Hypertension Using Transient Elastography and FIB-4

2022 ◽  
Vol Publish Ahead of Print ◽  
Author(s):  
Bubu A. Banini ◽  
Samarth Patel ◽  
Jonathan W. Yu ◽  
Le Kang ◽  
Christopher Bailey ◽  
...  
Keyword(s):  
Portal Hypertension ◽  
Transient Elastography ◽  
Clinically Significant

scholarly journals Prognostic Markers in Patients with Cirrhosis and Portal Hypertension Who Have Not Bled

2011 ◽  
Vol 31 (3) ◽  
pp. 147-154 ◽  
Author(s):  
Maria Poca ◽  
Angela Puente ◽  
Isabel Graupera ◽  
Càndid Villanueva
Keyword(s):  
Portal Hypertension ◽  
Prognostic Value ◽  
Prognostic Markers ◽  
Transient Elastography ◽  
Serum Markers ◽  
Promising Technique ◽  
Prognostic Information ◽  
Compensated Cirrhosis ◽  
Clinically Significant ◽  
Complications Of Cirrhosis

Prognostic markers of compensated cirrhosis should mainly investigate factors involved with progression to decompensation because death in cirrhosis is related with decompensation. Portal hypertension plays a crucial role in the pathophysiology of most complications of cirrhosis. Accordingly, HVPGmonitoring has strong prognostic value. An HVPG ≥ 10 mmHg determines a significantly higher risk of developing decompensation. Esophageal varices also can develop when the HVPG is ≥ 10 mmHg, although an HVPG ≥ 12 mmHg is required for variceal bleeding to occur. Monitoring the changes induced by the treatment of portal hypertension on HVPG, provides strong prognostic information. In compensated cirrhosis hemodynamic response is appropriate when the HVPG decreased to <10 mmHg or by > 10% from baseline, because the incidence of complications such as bleeding or ascites significantly decrease when these targets are achieved. Whether serum markers, such as the FibroTest, they, may be valuable to predict decompensation should be established. Transient Elastography is a promising technique that has shown an excellent accuracy to detect severe portal hypertension. However, whether it can adequately determine clinically significant portal hypertension, and risk of developing varices and decompensation, should be established. Magnetic Resonance Elastography is also promising.

Sign in / Sign up

Export Citation Format

Share Document