A Study on the Feasibility of Optimizing Gastric Cancer Screening to Reduce Screening Costs in China Using a Gradient Boosting Machine: A prospective, large-sample, single-center study
Bibliographic record
Abstract
Abstract Background and aim: The current cancer screening model in our country involves preliminary screening and identification of individuals who require gastroscopy, in order to control screening costs. The purpose of this study is to optimize the screening process using Gradient Boosting Machines (GBM), a machine learning technique, based on a large-scale prospective gastric cancer screening dataset. The ultimate goal is to further reduce the cost of initial cancer screening. Methods The study constructs a GBM machine learning model based on prospective, large-sample Taizhou City gastric cancer screening data and validates it with data from the Minimum Security Cohort Group (MLGC) in Taizhou City. Both data analysis and machine learning model construction were performed using the R programming language. Results A total of 195,640 cases were used as the training set, and 32,994 cases were used as an external validation set. A GBM was built based on the training set, yielding area under the curve (AUC) and area under the precision-recall curve (AUCPR) values of 0.99938 and 0.99823, respectively. External validation of the model yielded AUC and AUCPR values of 0.99742 and 0.99454, respectively. Through a visual analysis of the model, it was determined that the variable for Helicobacter pylori IgG could be eliminated. The GBM model was then reconstructed without the H. pylori IgG variable. In the training set, the new model achieved an AUC of 0.99817 and an AUCPR of 0.99462, whereas in the external validation set, it achieved an AUC of 0.99742 and an AUCPR of 0.99454. Conclusion This study utilized a dataset of 230,000 samples to train and validate a GBM model, optimizing the initial screening process by excluding the detection of H. pylori IgG antibodies while maintaining satisfactory discriminative performance. This conclusion will contribute to a reduction in the current cost of gastric cancer screening, demonstrating its economic value. Furthermore, the conclusion is derived from a large sample size, giving it clinical significance and generalizability.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".