Risk factor profiles for gastric cancer prediction with respect to Helicobacter pylori:A study of a tertiary care hospital in Pakistan

BACKGROUND Gastric cancer(GC)is the fourth leading cause of cancer-related deaths worldwide.Diagnosis relies on histopathology and the number of endoscopies is increasing.Helicobacter pylori(H.pylori)infection is a major risk factor.AIM To develop an in-silico GC prediction model to reduce the number of diagnostic surgical procedures.The meta-data of patients with gastroduodenal symptoms,risk factors associated with GC,and H.pylori infection status from Holy Family Hospital Rawalpindi,Pakistan,were used with machine learning.METHODS A cohort of 341 patients was divided into three groups[normal gastric mucosa(NGM),gastroduodenal diseases(GDD),and GC].Information associated with socioeconomic and demographic conditions and GC risk factors was collected using a questionnaire.H.pylori infection status was determined based on urea breath test.The association of these factors and histopathological grades was assessed statistically.K-Nearest Neighbors and Random Forest(RF)machine learning models were tested.RESULTS This study reported an overall frequency of 64.2%(219/341)of H.pylori infection among enrolled subjects.It was higher in GC(74.2%,23/31)as compared to NGM and GDD and higher in males(54.3%,119/219)as compared to females.More abdominal pain(72.4%,247/341)was observed than other clinical symptoms including vomiting,bloating,acid reflux and heartburn.The majority of the GC patients experienced symptoms of vomiting(91%,20/22)with abdominal pain(100%,22/22).The multinomial logistic regression model was statistically significant and correctly classified 80%of the GDD/GC cases.Age,income level,vomiting,bloating and medication had significant association with GDD and GC.A dynamic RF GC-predictive model was developed,which achieved>80%test accuracy.CONCLUSION GC risk factors were incorporated into a computer model to predict the likelihood of developing GC with high sensitivity and specificity.The model is dynamic and will be further improved and validated by including new data in future research studies.Its use may reduce unnecessary endoscopic procedures.It is freely available.

A Comparison of Transverse Palatal Width in Adult Untreated Cleft Palate Patients with Normal Adult Palates: A Pilot Study

Objective: The purpose of this pilot study is to compare the transverse palatal widths in untreated adult cleft palate patients with normal adult patients. Methods and Materials: The study was conducted in Bangladesh recruiting 10 patients with adult sized untreated cleft palate and 15 patients with normal adult sized palates. The control group was comprised of 7 males and 8 females with a mean age of 30.5 ± 4.4 years. The affected group comprised of 7 males and 3 females with a mean age 17 ± 3.3 years. Alginate impressions of the maxillary arch were taken and poured into plaster dental casts. The inter-canine, inter-premolar and intermolar widths were measured to evaluate the maxillary growth pattern in patients with unoperated cleft palate. Due to the small sample size, both independent T-test and Mann Whitney non-parametric tests were performed to analyze the statistical significance of the data. Results: According to both the T-test and Mann Whitney non-parametric tests, the inter-premolar width including both the first and second premolars was statistically significantly smaller in the affected group with p values of 0.003 and 0.00 respectively. There was no significant difference in the inter-canine width between the affected and control group due to the variable canine position in cleft palate patients. Due to small sample size, no significant difference in the intermolar width between the affected and control group could be established. Conclusion: The interpremolar width is significantly smaller in patients with adult sized cleft palates than individuals with normal adult sized palates.