Value of Serological Biomarker Panel in Diagnosis of Atrophic Gastritis and Helicobacter pylori Infection

Background: Gastric cancer is one of the most common types of cancer worldwide. Helicobacter pylori infection is clearly correlated with gastric carcinogenesis. Therefore, the use of a new non-invasive test, known as the GastroPanel test, can be very helpful to identify patients at a high risk, including those with atrophic gastritis, intestinal metaplasia, and dysplasia. This study aimed to compare the results of GastroPanel test with the pathological findings of patients with gastric atrophy to find a safe and simple alternative for endoscopy and biopsy as invasive methods. Methods: This cross-sectional study was performed on patients with indigestion, who were referred to Motahari Clinic and Shahid Faghihi Hospital of Shiraz, Iran, since April 2017 until August 2017 for endoscopy of the upper gastrointestinal tract. The serum levels of gastrin-17 (G17), pepsinogen I (PGI), and pepsinogen II (PGII), as well as H. pylori antibody IgG, were determined by ELISA assays. Two biopsy specimens from the antrum and gastric body were taken for standard histological analyses and rapid urease test. A pathologist examined the biopsy specimens of patients blindly. Results: A total of 153 patients with indigestion (62.7% female; mean age, 63.7 years; 37.3% male; mean age, 64.9 years) were included in this study. The G17 levels significantly increased in patients with chronic atrophic gastritis (CAG) of the body (9.7 vs. 32.8 pmol/L; P = 0.04) and reduced in patients with antral CAG (1.8 vs. 29.1 pmol/L; P = 0.01). The results were acceptable for all three types of CAG, including the antral, body, and multifocal CAG (AUCs of 97%, 91%, and 88% for body, antral, and multifocal CAG, respectively). The difference in PGII level was not significant. Also, the PGI and PGI/PGII ratio did not show a significant difference (unacceptably low AUCs for all). The H. pylori antibody levels were higher in patients infected with H. pylori (251 EIU vs. 109 EIU, AUC = 70, P = 0.01). There was a significant relationship between antibody tests and histopathology. Conclusion: Contrary to Biohit's claims, the GastroPanel kit is not accurate enough to detect CAG; therefore, it cannot be used for establishing a clinical diagnosis.

Predictors of Death in the Liver Transplantation Adult Candidates: An Artificial Neural Networks and Support Vector Machine Hybrid-Based Cohort Study

BACKGROUND

Model for end-stage liver disease (MELD) is currently used for liver transplantation (LT) allocation, however, it is not a sufficient criterion.

OBJECTIVE

This current study aims to perform a hybrid neural network analysis of different data, make a decision tree and finally design a decision support system for improving LT prioritization.

MATERIAL AND METHODS

In this cohort follow-up-based study, baseline characteristics of 1947 adult patients, who were candidates for LT in Shiraz Organ Transplant Center, Iran, were assessed and followed for two years and those who died before LT due to the end-stage liver disease were considered as dead cases, while others considered as alive cases. A well-organized checklist was filled for each patient. Analysis of the data was performed using artificial neural networks (ANN) and support vector machines (SVM). Finally, a decision tree was illustrated and a user friendly decision support system was designed to assist physicians in LT prioritization.

RESULTS

Between all MELD types, MELD-Na was a stronger determinant of LT candidates' survival. Both ANN and SVM showed that besides MELD-Na, age and ALP (alkaline phosphatase) are the most important factors, resulting in death in LT candidates. It was cleared that MELD-Na <23, age <53 and ALP <257 IU/L were the best predictors of survival in LT candidates. An applicable decision support system was designed in this study using the above three factors.

CONCLUSION

Therefore, Meld-Na, age and ALP should be used for LT allocation. The presented decision support system in this study will be helpful in LT prioritization by LT allocators.