H. Stefanescu

Spleen stiffness measurement using fibroscan for the noninvasive assessment of esophageal varices in liver cirrhosis patients

Background and Aim:  Splenomegaly in a common finding in liver cirrhosis that should determine changes in the spleens density because of portal and splenic congestion and/or because of tissue hyperplasia and fibrosis. These changes might be quantified by elastography, so the aim of the study was to investigate whether spleen stiffness measured by transient elastography varies as liver disease progresses and whether this would be a suitable method for the noninvasive evaluation of the presence of esophageal varices.

Noninvasive tools and risk of clinically significant portal hypertension and varices in compensated cirrhosis: The “Anticipate” study

In patients with compensated advanced chronic liver disease (cACLD), the presence of clinically significant portal hypertension (CSPH) and varices needing treatment (VNT) bears prognostic and therapeutic implications. Our aim was to develop noninvasive tests‐based risk prediction models to provide a point‐of‐care risk assessment of cACLD patients. We analyzed 518 patients with cACLD from five centers in Europe/Canada with paired noninvasive tests (liver stiffness measurement [LSM] by transient elastography, platelet count, and spleen diameter with calculation of liver stiffness to spleen/platelet score [LSPS] score and platelet‐spleen ratio [PSR]) and endoscopy/hepatic venous pressure gradient measurement. Risk of CSPH, varices, and VNT was modeled with logistic regression. All noninvasive tests reliably identified patients with high risk of CSPH, and LSPS had the highest discrimination. LSPS values above 2.65 were associated with risks of CSPH above 80%. None of the tests identified patients with very low risk of all‐size varices, but both LSPS and a model combining TE and platelet count identified patients with very low risk (<5%) risk of VNT, suggesting that they could be used to triage patients requiring screening endoscopy. LSPS values of <1.33 were associated with a <5% risk of VNT, and 26% of patients had values below this threshold. LSM combined with platelet count predicted a risk <5% of VNT in 30% of the patients. Nomograms were developed to facilitate point‐of‐care risk assessment. Conclusion: A significant proportion of patients with a very high risk of CSPH, and a population with a very low risk of VNT can be identified with simple, noninvasive tests, suggesting that these can be used to individualize medical care. (Hepatology 2016;64:2173‐2184).

Evolutionary-driven support vector machines for determining the degree of liver fibrosis in chronic hepatitis C

OBJECTIVE Hepatic fibrosis, the principal pointer to the development of a liver disease within chronic hepatitis C, can be measured through several stages. The correct evaluation of its degree, based on recent different non-invasive procedures, is of current major concern. The latest methodology for assessing it is the Fibroscan and the effect of its employment is impressive. However, the complex interaction between its stiffness indicator and the other biochemical and clinical examinations towards a respective degree of liver fibrosis is hard to be manually discovered. In this respect, the novel, well-performing evolutionary-powered support vector machines are proposed towards an automated learning of the relationship between medical attributes and fibrosis levels. The traditional support vector machines have been an often choice for addressing hepatic fibrosis, while the evolutionary option has been validated on many real-world tasks and proven flexibility and good performance. METHODS AND MATERIALS The evolutionary approach is simple and direct, resulting from the hybridization of the learning component within support vector machines and the optimization engine of evolutionary algorithms. It discovers the optimal coefficients of surfaces that separate instances of distinct classes. Apart from a detached manner of establishing the fibrosis degree for new cases, a resulting formula also offers insight upon the correspondence between the medical factors and the respective outcome. What is more, a feature selection genetic algorithm can be further embedded into the method structure, in order to dynamically concentrate search only on the most relevant attributes. The data set refers 722 patients with chronic hepatitis C infection and 24 indicators. The five possible degrees of fibrosis range from F0 (no fibrosis) to F4 (cirrhosis). RESULTS Since the standard support vector machines are among the most frequently used methods in recent artificial intelligence studies for hepatic fibrosis staging, the evolutionary method is viewed in comparison to the traditional one. The multifaceted discrimination into all five degrees of fibrosis and the slightly less difficult common separation into solely three related stages are both investigated. The resulting performance proves the superiority over the standard support vector classification and the attained formula is helpful in providing an immediate calculation of the liver stage for new cases, while establishing the presence/absence and comprehending the weight of each medical factor with respect to a certain fibrosis level. CONCLUSION The use of the evolutionary technique for fibrosis degree prediction triggers simplicity and offers a direct expression of the influence of dynamically selected indicators on the corresponding stage. Perhaps most importantly, it significantly surpasses the classical support vector machines, which are both widely used and technically sound. All these therefore confirm the promise of the new methodology towards a dependable support within the medical decision-making.

Feature selection for a cooperative coevolutionary classifier in liver fibrosis diagnosis

This paper presents an automatic tool capable to learn from a patients data set with 24 medical indicators characterizing each sample and to subsequently use the acquired knowledge to differentiate between five degrees of liver fibrosis. The indicators represent clinical observations and the liver stiffness provided by the new, non-invasive procedure of Fibroscan. The proposed technique combines a hill climbing algorithm that selects subsets of important attributes for an accurate classification and a core represented by a cooperative coevolutionary classifier that builds rules for establishing the diagnosis for every new patient. The results of the novel method proved to be superior as compared to the ones obtained by other important classification techniques from the literature. Additionally, the proposed methodology extracts a set of the most meaningful attributes from the available ones.

Expanding the Baveno VI criteria for the screening of varices in patients with compensated advanced chronic liver disease

Patients with compensated advanced chronic liver disease (cACLD) can safely avoid screening endoscopy with a platelet count >150 × 109 cells/L and a liver stiffness measurement (LSM) <20 kPa (Baveno VI criteria). However, the total number of avoided endoscopies using this rule is relatively low. We aimed at expanding the Baveno VI criteria and validating them in additional cohorts. Patients from the Anticipate cohort (499 patients with cACLD of different etiologies) were used to study the performance of different thresholds of platelets and LSM for the identification of patients at very low risk (<5%) of having varices needing treatment (VNT). The new criteria (Expanded‐Baveno VI) were validated in two additional cohorts from London (309 patients) and Barcelona (117 patients). The performance of the new criteria by etiology of cACLD was also assessed. The best new expanded classification rule was platelet count >110 × 109 cells/L and LSM <25 kPa. This was validated in the two additional cohorts. Overall, the Expanded‐Baveno VI criteria would potentially spare 367 (40%) endoscopies (21% with Baveno VI criteria) with a risk of missing VNT of 1.6% (95% confidence interval, 0.7%‐3.5%) in patients within the criteria and 0.6% (95% confidence interval, 0.3%‐1.4%) in the overall population of 925 patients evaluated. The Expanded‐Baveno VI criteria performed well in patients with cACLD with hepatitis C virus and alcoholic and nonalcoholic steatohepatitis. Conclusion: The new Expanded‐Baveno VI criteria spare more endoscopies than the original criteria with a minimal risk of missing VNT in most of the main etiologies of cACLD. (Hepatology 2017;66:1980–1988)

Non-invasive ménage à trois for the prediction of high-risk varices: stepwise algorithm using lok score, liver and spleen stiffness

Liver stiffness (LS), spleen stiffness (SS) and serum markers have been proposed to non‐invasively assess portal hypertension or oesophageal varices (EV) in cirrhotic patients. We aimed to evaluate the performance of a stepwise algorithm that combines Lok score with LS and SS for diagnosing high‐risk EV (HREV) and to compare it with other already‐validated non‐invasive methods.

Noninvasive assessment of portal hypertension in cirrhosis: Liver stiffness and beyond

Liver stiffness measurement (LSM) is a good, but still limited tool to noninvasively assess complications and prognosis in patients with advanced liver disease. This review aims to consider the role of LSM for the diagnosis of portal hypertension-related complications and for assessment of prognosis in cirrhotic patients, and to highlight the drawbacks as well as some alternatives for improving the performance. Hence, this field is far from being closed, and deserves more attention. There is still a place for more carefully designed studies to find new, innovative and reliable approaches.

Serum tests, liver stiffness and artificial neural networks for diagnosing cirrhosis and portal hypertension

BACKGROUND The diagnostic performance of biochemical scores and artificial neural network models for portal hypertension and cirrhosis is not well established. AIMS To assess diagnostic accuracy of six serum scores, artificial neural networks and liver stiffness measured by transient elastography, for diagnosing cirrhosis, clinically significant portal hypertension and oesophageal varices. METHODS 202 consecutive compensated patients requiring liver biopsy and hepatic venous pressure gradient measurement were included. Several serum tests (alone and combined into scores) and liver stiffness were measured. Artificial neural networks containing or not liver stiffness as input variable were also created. RESULTS The best non-invasive method for diagnosing cirrhosis, portal hypertension and oesophageal varices was liver stiffness (C-statistics=0.93, 0.94, and 0.90, respectively). Among serum tests/scores the best for diagnosing cirrhosis and portal hypertension and oesophageal varices were, respectively, Fibrosis-4, and Lok score. Artificial neural networks including liver stiffness had high diagnostic performance for cirrhosis, portal hypertension and oesophageal varices (accuracy>80%), but were not statistically superior to liver stiffness alone. CONCLUSIONS Liver stiffness was the best non-invasive method to assess the presence of cirrhosis, portal hypertension and oesophageal varices. The use of artificial neural networks integrating different non-invasive tests did not increase the diagnostic accuracy of liver stiffness alone.

Value of hepatic elastography and Doppler indexes for predictions of esophageal varices in liver cirrhosis.

AIMS Non-invasive methods are required to diagnose presence and grading of esophageal varices in patients with hepatic cirrhosis and in this respect we have evaluated the role of transient elastography and abdominal ultrasound parameters. MATERIAL AND METHODS Cirrhotic patients were prospectively evaluated by transient elastography and Doppler ultrasound for diagnosis of presence and grading of esophageal varices, the results being compared with the findings of the esophagogastroduodenoscopy. RESULTS Sixty patients with hepatic cirrhosis were analysed. The parameters that reached statistical significance for diagnosis of esophageal varices were: liver stiffness (LSM) > 15 kPa, hemodynamic liver index (PVr1) >/= 0.66, portal vascular resistance (PVR) > 17.66 and splenoportal index (SPI) > 4.77. The only parameter that reached statistical power for the diagnosis of large esophageal varices was LSM at a cut-off value of 28.8 kPa. CONCLUSIONS Assessment of LSM in patients with liver cirrhosis can predict both the presence of esophageal varices and of large esophageal varices. The PVr1, PVR and SPI Doppler indexes can be used to diagnose the presence of esophageal varices but have no role in the prediction of large esophageal varices. Further studies are required to confirm these results and offer a stronger clinical significance.

Non-invasive steatosis assessment in NASH through the computerized processing of ultrasound images: Attenuation versus textural parameters

Ultrasonography is a simple method in diagnosing nonalcoholic steatohepatitis (NASH), providing useful information, but it is subjective and does not accurately differentiate between steatosis grades. The computerized processing of the data that comprises the ultrasonic image (CPU) might transform ultra-sonography into an objective examination. CPU can be achieved either by methods based on the study of parenchymal echogenicity and on the attenuation of the ultrasounds (attenuation and back-scattering coefficients), or by methods based on the quantification of some textural parameters. In the present paper we set out to compare the performance of the attenuation coefficient (AC) and the textural parameters derived from the GLCM matrix 96 NASH patients and 24 healthy subjects were prospectively included in this study. We found a strong correlation between the AC and steatosis and a weak, but statistically significant one, with balooning and lobular inflammation, but not with fibrosis. The multivariate analysis showed, however, that only steatosis influences independently the AC. Of the analyzed textural parameters, only the GLCM entropy correlated weakly, but significantly, with the steatosis degree. Our study proves that the use of the attentuation coefficient computed on the ultrasonographic image can help differentiate healthy from NASH patients, as well as discriminate between various degrees of fatty load. The attenuation coefficient performs better than the textural parameters derived from the GLCM matrix. However, only GLCM entropy, of all textural parameters tested, correlates with steatosis, and even then, only for the differentiation normal vs NASH, not between steatosis grades.