A Deep Recurrent Neural Network-Based Explainable Prediction Model for Progression from Atrophic Gastritis to Gastric Cancer
Source abstract
Abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Helicobacter pylori-related gastroenterology studies · Gastric Cancer Management and Outcomes · Colorectal Cancer Screening and Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Statistics and Information Science, Dongduk Women’s University, Seoul 02748, Korea
Department of Internal Medicine, Kangdong Sacred Heart Hospital, Hallym University College of Medicine, Seoul 05355, Korea
Funding
Ministry of Health & Welfare, Republic of Korea
References (55)
Show source-provided references
1. Global Cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries10.3322/caac.21492 ↗
2. Diagnosis and management of high-risk group for gastric cancer10.5009/gnl14118 ↗
3. National cancer screening program for gastric cancer in Korea: Nationwide treatment benefit and cost10.1002/cncr.32753 ↗
4. Mortality reduction from gastric cancer by endoscopic and radiographic screening10.1111/cas.12829 ↗
5. Benefits and harms of endoscopic screening for gastric cancer10.3748/wjg.v22.i28.6385 ↗
6. Prediction of future gastric cancer risk using a machine learning algorithm and comprehensive medical checkup data: A case-control study10.1038/s41598-019-48769-y ↗
7. Gastric cancer: Descriptive epidemiology, risk factors, screening, and prevention10.1158/1055-9965.EPI-13-1057 ↗
8. Screening and surveillance for gastric cancer in the United States: Is it needed?10.1016/j.gie.2016.02.028 ↗
9. Risk factors and incidence of gastric cancer after detection Helicobacter pylori infection: A large cohort study10.1053/j.gastro.2019.10.019 ↗
10. Atrophic gastritis increases the risk of gastric cancer in asymptomatic population in Korea10.5009/gnl17356 ↗
11. A guide to deep learning in healthcare10.1038/s41591-018-0316-z ↗
12. Deep learning for health informatics10.1109/JBHI.2016.2636665 ↗
13. Deep learning for healthcare: Review, opportunities and challenges10.1093/bib/bbx044 ↗
14. Opportunities and challenges in developing deep learning models using electronic health records data: A systematic review10.1093/jamia/ocy068 ↗
15. Deep HER: A survey of recent advances in deep learning techniques for electronic health record (HER) analysis10.1109/JBHI.2017.2767063 ↗
16. Predicting healthcare trajectories from medical records: A deep learning approach10.1016/j.jbi.2017.04.001 ↗
17. Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., and Elhadad, N. (2015, January 10–13). Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission. Proceedings of the Knowledge Discovery and Database, Sydney, Australia.10.1145/2783258.2788613 ↗
18. Deep Patient: An unsupervised representation to predict the future of patients the electronic health records10.1038/srep26094 ↗
19. Doctor AI: Predicting clinical events via recurrent neural networks
20. XAI-Explainable artificial intelligence10.1126/scirobotics.aay7120 ↗
21. Techniques for interpretable machine learning10.1145/3359786 ↗
22. Choi, E., Bahadori, M.T., Kulas, J.A., Schuetz, A., Stewart, W.F., and Sun, K. (2016, January 5–10). RETAIN: An interpretable predictive model for healthcare using reverse time attention mechanism. Proceedings of the 30th Conference on Neural Information Processing Systems, Barcelona, Spain.
23. Ahmed, M., Seraj, R., and Islam, S.M.S. (2020). The K-means Algorithm: A comprehensive survey and performance evaluation. Electronics, 9.10.3390/electronics9081295 ↗
24. Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13–17). “Why should I trust you?” Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939778 ↗
25. Conversion of National Health Insurance Service-National Sample Cohort (NHIS-NSC) database into Observational Medical Outcomes Partnership-Common Data Model (OMOP-CDM)
26. Opportunities and challenges in developing risk prediction models with electronic health records data: A systematic review10.1093/jamia/ocw042 ↗
27. Weng, S.F., Reps, J., Kai, J., Caribaldi, J.M., and Qureshi, N. (2017). Can machine-learning improve cardiovascular risk prediction using routine clinical data?. PLoS ONE, 12.10.1371/journal.pone.0174944 ↗
28. Deep learning for electronic health records: A comparative review of multiple deep neural architectures10.1016/j.jbi.2019.103337 ↗
29. Deepr: A convolutional net for medical records10.1109/JBHI.2016.2633963 ↗
30. Recurrent neural networks and robust time series prediction10.1109/72.279188 ↗
31. Bidirectional recurrent neural networks10.1109/78.650093 ↗
32. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
33. Explainable artificial intelligence model to predict acute critical illness from electronic health records10.1038/s41467-020-17431-x ↗
34. Visualizing data using t-SNE
35. SMOTE: Synthetic Minority Over-sampling Technique10.1613/jair.953 ↗
36. He, H., Bai, Y., Garcia, E.A., and Li, S. (2008, January 1–8). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. Proceedings of the IEEE International Joint Conference on Neural Networks, Hong Kong, China.
37. Editorial: Special issue on learning form imbalanced data sets10.1145/1007730.1007733 ↗
38. Johnson, J.M., and Khoshgoftaar, T.M. (2019). Survey on deep learning with class imbalance. J. Big Data, 6–27.10.1186/s40537-019-0192-5 ↗
39. Ding, W., Huang, D., Chen, Z., Yu, X., and Lin, W. (2017, January 12–15). Facial action recognition using very deep networks for highly imbalanced class distribution. Proceedings of the APSIPA ASC, Kuala Lumpur, Malaysia.10.1109/APSIPA.2017.8282246 ↗
40. Pascanu, R., Gulcehre, C., Cho, K., and Bengio, Y. (2014, January 14–16). How to construct deep recurrent neural networks. Proceedings of the Second International Conference on Learning Representations, Banff, AB, Canada.
41. Maximally selected Chi-squared statistics10.2307/2529881 ↗
42. Unsupervised K-Means Clustering Algorithm10.1109/ACCESS.2020.2988796 ↗
43. Statistical problems in assessing methods of medical diagnosis with special reference to x-ray techniques10.2307/4586294 ↗
44. Diagnostic tests: Sensitivity and specificity10.1136/bmj.308.6943.1552 ↗
45. Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation
46. Algorithm AS 136: A K-means clustering algorithm
47. The application of cluster analysis in strategic management research: An analysis and critique10.1002/(SICI)1097-0266(199606)17:6<441::AID-SMJ819>3.0.CO;2-G ↗
48. (2021, June 30). InterpretML, Interpret-Text-Alpha Release. Available online: https://github.com/interpretml/interpret.
49. Artificial intelligence in gastric cancer: Application and future perspectives10.3748/wjg.v26.i36.5408 ↗
50. Immunomarker support vector machine classifier for prediction of gastric cancer survival and adjuvant chemotherapeutic benefit10.1158/1078-0432.CCR-18-0848 ↗
51. Development and validation of a CT-based radiomic nomogram for preoperative prediction of early recurrence in advanced gastric cancer10.1016/j.radonc.2019.11.023 ↗
52. Deep neural network-assisted computed tomography diagnosis of metastatic lymph nodes from gastric cancer10.1097/CM9.0000000000000532 ↗
53. A multi-tier stacked ensemble algorithm for improving classification accuracy10.1109/MCSE.2018.2873940 ↗
54. A prediction and interpretation framework of acute kidney injury in critical care10.1016/j.jbi.2020.103653 ↗
55. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery10.1038/s41551-018-0304-0 ↗