Using Machine Learning to Predict Progression in the Gastric Precancerous Process in a Population from a Developing Country Who Underwent a Gastroscopy for Dyspeptic Symptoms
Background. Gastric cancer is the fourth most common cancer and the third most common cause of cancer deaths worldwide. Morbidity and mortality from gastric cancer may be decreased by identification of those that are at high risk for progression in the gastric precancerous process so that they can b...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-01-01
|
| Series: | Gastroenterology Research and Practice |
| Online Access: | http://dx.doi.org/10.1155/2019/8321942 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832556414312120320 |
|---|---|
| author | Susan Thapa Lori A. Fischbach Robert Delongchamp Mohammed F. Faramawi Mohammed S. Orloff |
| author_facet | Susan Thapa Lori A. Fischbach Robert Delongchamp Mohammed F. Faramawi Mohammed S. Orloff |
| author_sort | Susan Thapa |
| collection | DOAJ |
| description | Background. Gastric cancer is the fourth most common cancer and the third most common cause of cancer deaths worldwide. Morbidity and mortality from gastric cancer may be decreased by identification of those that are at high risk for progression in the gastric precancerous process so that they can be monitored over time for early detection and implementation of preventive strategies. Method. Using machine learning, we developed prediction models for gastric precancerous progression in a population from a developing country with a high rate of gastric cancer who underwent gastroscopies for dyspeptic symptoms. In the data imputed for completeness, we divided the data into a training and a validation test set. Using the training set, we used the random forest method to rank potential predictors based on their predictive importance. Using predictors identified by the random forest method, we conducted best subset linear regressions with the leave-one-out cross-validation approach to select predictors for overall progression and progression to dysplasia or cancer. We validated the models in the test set using leave-one-out cross-validation. Results. We observed for all models that complete intestinal metaplasia and incomplete intestinal metaplasia were the strongest predictors for further progression in the precancerous process. We also observed that a diagnosis of no gastritis, superficial gastritis, or antral diffuse gastritis at baseline was a predictor of no progression in the gastric precancerous process. The sensitivities and specificities were 86% and 79% for the general model and 100% and 82% for the location-specific model, respectively. Conclusion. We developed prediction models to identify gastroscopy patients that are more likely to progress in the gastric precancerous process, among whom routine follow-up gastroscopies can be targeted to prevent gastric cancer. Future external validation is needed. |
| format | Article |
| id | doaj-art-daf30c90373c40d6b3b2f7d6c5528a34 |
| institution | Kabale University |
| issn | 1687-6121 1687-630X |
| language | English |
| publishDate | 2019-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Gastroenterology Research and Practice |
| spelling | doaj-art-daf30c90373c40d6b3b2f7d6c5528a342025-02-03T05:45:29ZengWileyGastroenterology Research and Practice1687-61211687-630X2019-01-01201910.1155/2019/83219428321942Using Machine Learning to Predict Progression in the Gastric Precancerous Process in a Population from a Developing Country Who Underwent a Gastroscopy for Dyspeptic SymptomsSusan Thapa0Lori A. Fischbach1Robert Delongchamp2Mohammed F. Faramawi3Mohammed S. Orloff4Department of Epidemiology, College of Public Health, University of Arkansas for Medical Sciences, Little Rock 72205, USADepartment of Epidemiology, College of Public Health, University of Arkansas for Medical Sciences, Little Rock 72205, USADepartment of Epidemiology, College of Public Health, University of Arkansas for Medical Sciences, Little Rock 72205, USADepartment of Epidemiology, College of Public Health, University of Arkansas for Medical Sciences, Little Rock 72205, USADepartment of Epidemiology, College of Public Health, University of Arkansas for Medical Sciences, Little Rock 72205, USABackground. Gastric cancer is the fourth most common cancer and the third most common cause of cancer deaths worldwide. Morbidity and mortality from gastric cancer may be decreased by identification of those that are at high risk for progression in the gastric precancerous process so that they can be monitored over time for early detection and implementation of preventive strategies. Method. Using machine learning, we developed prediction models for gastric precancerous progression in a population from a developing country with a high rate of gastric cancer who underwent gastroscopies for dyspeptic symptoms. In the data imputed for completeness, we divided the data into a training and a validation test set. Using the training set, we used the random forest method to rank potential predictors based on their predictive importance. Using predictors identified by the random forest method, we conducted best subset linear regressions with the leave-one-out cross-validation approach to select predictors for overall progression and progression to dysplasia or cancer. We validated the models in the test set using leave-one-out cross-validation. Results. We observed for all models that complete intestinal metaplasia and incomplete intestinal metaplasia were the strongest predictors for further progression in the precancerous process. We also observed that a diagnosis of no gastritis, superficial gastritis, or antral diffuse gastritis at baseline was a predictor of no progression in the gastric precancerous process. The sensitivities and specificities were 86% and 79% for the general model and 100% and 82% for the location-specific model, respectively. Conclusion. We developed prediction models to identify gastroscopy patients that are more likely to progress in the gastric precancerous process, among whom routine follow-up gastroscopies can be targeted to prevent gastric cancer. Future external validation is needed.http://dx.doi.org/10.1155/2019/8321942 |
| spellingShingle | Susan Thapa Lori A. Fischbach Robert Delongchamp Mohammed F. Faramawi Mohammed S. Orloff Using Machine Learning to Predict Progression in the Gastric Precancerous Process in a Population from a Developing Country Who Underwent a Gastroscopy for Dyspeptic Symptoms Gastroenterology Research and Practice |
| title | Using Machine Learning to Predict Progression in the Gastric Precancerous Process in a Population from a Developing Country Who Underwent a Gastroscopy for Dyspeptic Symptoms |
| title_full | Using Machine Learning to Predict Progression in the Gastric Precancerous Process in a Population from a Developing Country Who Underwent a Gastroscopy for Dyspeptic Symptoms |
| title_fullStr | Using Machine Learning to Predict Progression in the Gastric Precancerous Process in a Population from a Developing Country Who Underwent a Gastroscopy for Dyspeptic Symptoms |
| title_full_unstemmed | Using Machine Learning to Predict Progression in the Gastric Precancerous Process in a Population from a Developing Country Who Underwent a Gastroscopy for Dyspeptic Symptoms |
| title_short | Using Machine Learning to Predict Progression in the Gastric Precancerous Process in a Population from a Developing Country Who Underwent a Gastroscopy for Dyspeptic Symptoms |
| title_sort | using machine learning to predict progression in the gastric precancerous process in a population from a developing country who underwent a gastroscopy for dyspeptic symptoms |
| url | http://dx.doi.org/10.1155/2019/8321942 |
| work_keys_str_mv | AT susanthapa usingmachinelearningtopredictprogressioninthegastricprecancerousprocessinapopulationfromadevelopingcountrywhounderwentagastroscopyfordyspepticsymptoms AT loriafischbach usingmachinelearningtopredictprogressioninthegastricprecancerousprocessinapopulationfromadevelopingcountrywhounderwentagastroscopyfordyspepticsymptoms AT robertdelongchamp usingmachinelearningtopredictprogressioninthegastricprecancerousprocessinapopulationfromadevelopingcountrywhounderwentagastroscopyfordyspepticsymptoms AT mohammedffaramawi usingmachinelearningtopredictprogressioninthegastricprecancerousprocessinapopulationfromadevelopingcountrywhounderwentagastroscopyfordyspepticsymptoms AT mohammedsorloff usingmachinelearningtopredictprogressioninthegastricprecancerousprocessinapopulationfromadevelopingcountrywhounderwentagastroscopyfordyspepticsymptoms |