A Deep Recurrent Neural Network-Based Explainable Prediction Model for Progression from Atrophic Gastritis to Gastric Cancer
| Autor: | Kyung Joo Lee, Woon Geon Shin, Hyon Hee Kim, Young Seo Lim, Seung-In Seo, Jaeyoung Kim |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
progression to gastric cancer from atrophic gastritis
risk factor detection Technology medicine.medical_specialty QH301-705.5 Atrophic gastritis QC1-999 03 medical and health sciences 0302 clinical medicine gastric cancer prediction deep recurrent neural network medical checkup data Regular exercise Internal medicine medicine General Materials Science Biology (General) QD1-999 Instrumentation 030304 developmental biology Fluid Flow and Transfer Processes 0303 health sciences business.industry Physics Process Chemistry and Technology Significant difference Cancer type General Engineering Cancer Engineering (General). Civil engineering (General) medicine.disease Computer Science Applications Chemistry National health insurance 030220 oncology & carcinogenesis Smoking status Cancer development TA1-2040 business |
| Zdroj: | Applied Sciences; Volume 11; Issue 13; Pages: 6194 Applied Sciences, Vol 11, Iss 6194, p 6194 (2021) |
| ISSN: | 2076-3417 |
| DOI: | 10.3390/app11136194 |
| Popis: | Gastric cancer is the fifth most common cancer type worldwide and one of the most frequently diagnosed cancers in South Korea. In this study, we propose DeepPrevention, which comprises a prediction module to predict the possibility of progression from atrophic gastritis to gastric cancer and an explanation module to identify risk factors for progression from atrophic gastritis to gastric cancer, to identify patients with atrophic gastritis who are at high risk of gastric cancer. The data set used in this study was South Korea National Health Insurance Service (NHIS) medical checkup data for atrophic gastritis patients from 2002 to 2013. Our experimental results showed that the most influential predictors of gastric cancer development were sex, smoking duration, and current smoking status. In addition, we found that the average age of gastric cancer diagnosis in a group of high-risk patients was 57, and income, BMI, regular exercise, and the number of endoscopic screenings did not show any significant difference between groups. At the individual level, we identified that there were relatively strong associations between gastric cancer and smoking duration and smoking status. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|