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

作     者：Shahid Aziz Simone König Muhammad Umer Tayyab Saeed Akhter Shafqat Iqbal Maryum Ibrar Tofeeq Ur-Rehman Tanvir Ahmad Alfizah Hanafiah Rabaab Zahra Faisal Rasheed 

作者机构：Patients Diagnostic LabIsotope Application DivisionPakistan Institute of Nuclear Science and TechnologyIslamabad 44000Pakistan Department of MicrobiologyQuaid-i-Azam UniversityIslamabad 45320Pakistan Interdisciplinary Center for Clinical ResearchCore Unit ProteomicsUniversity of MünsterMünster 48149Germany Management Information System DivisionPakistan Institute of Nuclear Science and TechnologyIslamabad 44000Pakistan Centre for Liver and Digestive DiseasesHoly Family HospitalRawalpindi 46300Pakistan Pakistan Scientific and Technological Information CentreQuaid-i-Azam UniversityIslamabad 45320Pakistan Department of PharmacyQuaid-i-Azam UniversityIslamabad 45320Pakistan Faculty of MedicineDepartment of Medical Microbiology and ImmunologyUniversiti Kebangsan MalaysiaCherasKuala Lumpur 56000Malaysia 

出 版 物：《Artificial Intelligence in Gastroenterology》 (胃肠病学中的人工智能（英文）)

年 卷 期：2023年第4卷第1期

页      面：10-27页

学科分类：1002[医学-临床医学] 100201[医学-内科学(含：心血管病、血液病、呼吸系病、消化系病、内分泌与代谢病、肾病、风湿病、传染病)] 10[医学] 

主　　题：Gastric cancer Gastritis Machine learning Prediction model Helicobacter pylori 

摘      要：BACKGROUND Gastric cancer(GC)is the fourth leading cause of cancer-related deaths *** relies on histopathology and the number of endoscopies is *** pylori(***)infection is a major risk *** To develop an in-silico GC prediction model to reduce the number of diagnostic surgical *** meta-data of patients with gastroduodenal symptoms,risk factors associated with GC,and *** infection status from Holy Family Hospital Rawalpindi,Pakistan,were used with machine *** 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 *** infection status was determined based on urea breath *** association of these factors and histopathological grades was assessed statistically.K-Nearest Neighbors and Random Forest(RF)machine learning models were *** This study reported an overall frequency of 64.2%(219/341)of *** infection among enrolled *** 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 *** abdominal pain(72.4%,247/341)was observed than other clinical symptoms including vomiting,bloating,acid reflux and *** 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 ***,income level,vomiting,bloating and medication had significant association with GDD and GC.A dynamic RF GC-predictive model was developed,which achieved80%test *** GC risk factors were incorporated into a computer model to predict the likelihood of developing GC with high sensitivity and *** model is dynamic and will be further improved and validated by including n