Development and validation of an interpretable machine learning model for predicting chronic atrophic gastritis in elderly patients - Summary - MDSpire
Advertisement
Development and validation of an interpretable machine learning model for predicting chronic atrophic gastritis in elderly patients
To develop and validate interpretable machine learning models for predicting chronic atrophic gastritis (CAG) in elderly patients and to identify key predictive factors.
Approach:
Data Collection: Collected 28 candidate variables covering demographics, lifestyle, medical history, psychological status, and clinical symptoms from January 2023 to October 2025.
Key Findings:
The MLP model achieved an AUC of 0.826 (95% CI: 0.788–0.864) in internal validation and 0.780 (95% CI: 0.745–0.815) in temporal validation.
Key risk factors identified include Helicobacter pylori infection, age, smoking status, and high-salt pickled food intake.
Fruit and vegetable intake was identified as a protective factor.
Interpretation:
The developed ML model provides a non-invasive tool for risk stratification of CAG in elderly patients.
Limitations:
The study is limited to a specific population from a single hospital, which may affect generalizability and introduce biases related to data collection.
The retrospective design may introduce biases related to data collection.
Conclusion:
The study successfully developed an interpretable ML model for predicting CAG in elderly patients, utilizing eight readily available clinical variables.
