Predicting metastasis in gastric cancer patients: machine learning-based approaches.

Gastric cancer (GC), with a 5-year survival rate of less than 40%, is known as the fourth principal reason of cancer-related mortality over the world. This study aims to develop predictive models using different machine learning (ML) classifiers based on both demographic and clinical variables to predict metastasis status of patients with GC. The data applied in this study including 733 of GC patients, divided into a train and test groups at a ratio of 8:2, diagnosed at Taleghani tertiary hospital. In order to predict metastasis in GC, ML-based algorithms, including Naive Bayes (NB), Random Forest (RF), Support Vector Machine (SVM), Neural Network (NN), Decision Tree (RT) and Logistic Regression (LR), with 5-fold cross validation were performed. To assess the model performance, F1 score, precision, sensitivity, specificity, area under the curve (AUC) of receiver operating characteristic (ROC) curve and precision-recall AUC (PR-AUC) were obtained. 262 (36%) experienced metastasis among 733 patients with GC. Although all models have optimal performance, the indices of SVM model seems to be more appropiate (training set: AUC: 0.94, Sensitivity: 0.94; testing set: AUC: 0.85, Sensitivity: 0.92). Then, NN has the higher AUC among ML approaches (training set: AUC: 0.98; testing set: AUC: 0.86). The RF of ML-based models, which determine size of tumor and age as two essential variables, is considered as the third efficient model, because of higher specificity and AUC (84% and 87%). Based on the demographic and clinical characteristics, ML approaches can predict the metastasis status in GC patients. According to AUC, sensitivity and specificity in both SVM and NN can be regarded as better algorithms among 6 applied ML-based methods.

The Relationship between Serum Selenium and Zinc with Gastroesophageal Cancers in the Southeast of Iran.

BACKGROUND: Selenium (Se) and zinc (Zn) have antioxidant and anticancer properties. OBJECTIVE: The aim of this study was to evaluate the serum levels of Se and Zn and the correlation between the levels of these two elements with risk of incidence of esophageal cancer (EC) and gastric cancer (GC). MATERIALS AND METHODS: In a case-control study, we selected sixty patients with GC or EC as the intervention group and 120 age-matched individuals as the control group. Exclusion criteria were the individuals with kidney and liver failure and the consumer of dietary supplements such as Se and Zn. Measurement of serum Se was done in a graphite furnace system and atomic absorption device of Varian and of serum Zn was done by a flame photometer system (flame) and atomic absorption device of Varian. RESULTS: In thirty patients of ECs, 90% were squamous cell carcinoma and 10% adenocarcinoma, and out of thirty patients of GCs, 90% were intestinal type and 10% diffuse type. The level of two elements in cancer patients was lower than the control group (P < 0.05). There was no significant different between two cancer groups for level of Se and Zn, but there was a significant difference between the control group with two other groups. CONCLUSION: Our study confirmed the findings from previous prospective studies and randomized trials that reducing of lower levels of Se and Zn can effect on incidence of cancer.

Association between Programmed Cell Death 6 Interacting Protein Insertion/Deletion Polymorphism and the Risk of Breast Cancer in a Sample of Iranian Population.

It has been suggested that genetic factors contribute to patients' vulnerability to breast cancer (BC). The programmed cell death 6 interacting protein (PDCD6IP) encodes for a protein that is known to bind to the products of the PDCD6 gene, which is involved in the apoptosis pathway. The aim of this case-control study is to investigate the relationship between the PDCD6IP 15 bp insertion/deletion (I/D) polymorphism (rs28381975) and BC risk in an Iranian population. A total of 491 females, including 266 BC patients and 225 control subjects without cancer, were enrolled into the study. Our findings revealed that the PDCD6IP 15 bp I/D polymorphism decreased the risk of BC in codominant (OR = 0.44, 95% CI = 0.31-0.65, p < 0.0001, I/D versus DD; OR = 0.39, 95% CI = 0.17-0.88, p = 0.030, I/I versus DD) and dominant (OR = 0.44, 95% CI = 0.30-0.63, p < 0.0001, D/I + I/I versus D/D) tested inheritance models. Also, the PDCD6IP I allele significantly decreased the risk of BC (OR = 0.59, 95% CI = 0.45-0.78, p < 0.001) compared to the D allele.

Association between LAPTM4B gene polymorphism and breast cancer susceptibility in an Iranian population.

Lysosome associated protein transmembrane 4beta (LAPTM4B) contribute to the risk of numerous cancers. The present study focused on the possible association between LAPTM4B polymorphism and the risk of breast cancer (BC) in an Iranian population in southeast Iran. This case control study includes 311 BC patients and 225 healthy women. Genomic DNA was extracted from the whole blood by salting out method and LAPTM4B genotype was investigated using polymerase chain reaction. Our findings showed that LAPTM4B genotype was not associated with the risk of BC in any inheritance model tested. The minor allele frequency in case and control group was 0.297 and 0.278, respectively. The minor allele (LAPTM4B*2) was not associated with BC risk in comparison with LAPTM4B*1 allele (odds ratio 1.10, 95 % confidence intervals 0.84-1.44, p = 0.495). Moreover, LAPTM4B polymorphism was not associated with clinical and pathological characteristics in the patient group. In conclusion, the findings of our study suggested that the polymorphism of LAPTM4B gene was not associated with susceptibility to BC and clinicopathological characteristics in an Iranian population.

The effect of Cannabis sativa L. (hemp seed) on hematological parameters in guinea pigs.

The objective of this study was to investigate the effect of ingestion of powder of hemp seed on blood picture. This study was experienced on five guinea pigs that fed with normal diet (fresh vegetable and tab water), in addition were force-fed 5 g/kg/day of the powder of hemp seed for 60 days by means of an endogastric tube and syringe. At the beginning day and the termination of study day-60 the blood was taken from animals and the erythrocyte number, leukocyte number, packed cell volume (PCV), and hemoglobin concentration values were determined. The result on analysis showed that erythrocyte-count and PCV significantly decreased (p < 0.05) whereas hemoglobin concentration and leukocyte number values showed a steady decline which was not significant (P > 0.05). None of the values fell below the normal physiological range of the experimental animals. This shows that hemp seed which contains tetrahydrocannabinols as its active constituents has long term significant toxicological implication such as bone marrow suppression with respect to the concentration given on the erythrocytes of mammals. It is recommended that individuals who have anemia or immunity complication should not use hemp seed in their food preparation on regular basis.